iii-directory
v1.2.13Engine introspection, workers registry proxy, filesystem-backed skills, system prompts, and agent profiles, plus lexical function search with a conditional pre-generate hint.
- macOS: arm64
- Linux: arm64 · armv7 · x64
- Windows: arm64 · x64
exact versions are immutable; binary and bundle artifacts are digest-pinned.
full markdown
/workers/iii-directory.md?version=1.2.13. paste it into an llm prompt or pipe it through curl from a worker.install
dependencies
readme
iii-directory
Workers registry HTTP proxy and filesystem-backed skills, system prompts,
and agent profiles for the iii engine. Every
public function sits under a single directory::* namespace, split
into five surfaces (all MCP-agnostic):
| Surface | What clients see | When to use it |
|---|---|---|
Skills (directory::skills::*) |
Enriched listing via directory::skills::list ({ id, title, type, function_id, disable_model_invocation, description, bytes, modified_at } per row), a single-skill reader directory::skills::get { id } returning { id, title, type, function_id, disable_model_invocation, path, body, modified_at } (the full body instead of the list teaser), and directory::skills::index which renders a short per-worker overview document (one ## + first paragraph + read more link per type: index skill). Authored by create, edited by update, removed by delete. title prefers the YAML frontmatter title: (then name:) over the body H1; type is lifted from frontmatter type: (e.g. index, how-to, reference) and serialised as null when absent. System-installed agent skills under the read-only agents_skills_folder are served too (see On-disk layout). |
Orientation: "when and why to use my worker's tools" |
System prompts (directory::system-prompts::*) |
Identity prompts listed by list, read by get, authored by create, edited by update, and removed by delete. The list response keeps its prompts field name. Stored under any system-prompts/ path segment; create writes . |
What the chat's system-prompt picker offers as an identity prompt (enrich or replace) |
Agent Profiles (directory::agents::*) |
Reusable session identities whose file body is the system prompt, with display name, emoji logo, a skills filter, and optional model + reasoning_effort in required frontmatter. list rows carry the display/configuration metadata and get adds system_prompt and unknown_skills. Stored as direct files. See Agent profile storage. |
A named identity selected with harness::send { options: { agent } } |
Search (directory::search_functions) |
One to six external capabilities → compact function-id candidates (installed, plus registry workers under installable), with a conditional pre-generate hint pointing agents at it. |
"Which functions do I call for this task?" |
Registry (directory::registry::*) |
HTTP proxy over api.workers.iii.dev with workers::{list,info}. Rows share the core name / description / version fields with the engine's engine::workers::list and add publication metadata (type, config, supported_targets, total_downloads, dependencies, optional image). workers::list is cursor-paginated with a server-authored page size. |
"What's published in the public registry?" |
Engine introspection (functions / triggers / registered triggers /
workers) is served by the engine natively at
engine::functions::*, engine::triggers::*,
engine::registered-triggers::*, and engine::workers::*. Call the
engine ids directly. One wrapper survives for callers that can only
reach the directory:: namespace: directory::engine::functions::info
proxies a single function's schema (see its row below).
This worker is where an agent's identity text LIVES. skills/system-prompts/iii-runtime.md
ships here and is the one copy of "how to work against a live iii engine" —
claude-code and pi fetch it with directory::system-prompts::get name=iii-runtime (plus directory::skills::index) for both their headless
turns and their console terminals, rather than compiling a prompt of their own.
Edit that file and every agent reads the edit; no worker release involved.
Skills and system prompts are sourced from skills_folder; agent profiles
use the dedicated agents_folder. Writes are the
directory::skills::download* functions, which pull markdown from either
the workers registry or a GitHub repo and route each
supported family to its configured root, plus the
per-kind single-file editors — directory::skills::{create,update,delete},
directory::system-prompts::{create,update,delete} and
directory::agents::{create,update,delete}. Once downloaded, files
belong to the developer — edit them however you want, in the editor of
your choice: a change made directly on disk fires the matching
on-change with op: "external" (see Custom trigger
types).
directory::registry::workers::* and the engine's engine::workers::*
share the core name / description / version fields so a parser
that touches only those keys works against either surface; the
registry view also surfaces publication metadata (type, config,
supported_targets, total_downloads, dependencies, optional
image) and the engine view adds runtime / connection state.
Table of contents
- Install
- Configuration
- Quickstart: download some skills
- On-disk layout
- Skill ids
- Functions
- Function search & pre-generate hint
- Custom trigger types
- Local development & testing
- Migration from skills v0.2.x
Install
iii trigger compose::add worker=iii-directoryiii trigger compose::add resolves the worker and its dependencies, writes
exact declarations to worker-compose.yaml, and reconciles the Compose project.
For container settings, fetch compose::schema { function_id: "compose::add" } and use
its workers list. For example, after registering the completion wake described below:
{
"operation_id": "<operation-id>",
"workers": [
"state",
{
"worker": "iii-directory",
"start_after": ["state"],
"config_override": { "registry_search": true }
}
]
}The list can mix worker names and objects. Each object accepts scripts, config_name,
config_override, working_dir, environment, env_file, startup_timeout, and
package version as well as worker and start_after. scripts.run is for local
workers only. Supplied maps replace the whole field; omitted settings are retained.
The returned install.payload from function search is a minimal shorthand. If the worker
needs settings, replace its singular worker with an object in workers.
Register a one-shot compose-operation wake before calling compose::add, use the same
operation_id in both calls, and wait for terminal success before using the new functions.
An acceptance response does not mean the worker is ready. See the
container settings example and completion flow
for field behavior, path resolution, and recovery.
Skills
Install the iii-directory agent skill for Claude Code, Cursor, and 30+ other agents:
npx skills add iii-hq/workers --skill iii-directoryBrowse or install every worker skill at once:
npx skills add iii-hq/workers --list
npx skills add iii-hq/workers --allConfiguration
Runtime settings live in the configuration worker under id
iii-directory (the same pattern database and storage use). At boot
the worker registers its JSON Schema, reads the live value via
configuration::get (the configuration worker env-expands ${VAR}), and binds
a configuration trigger so it re-fetches on change.
Persisted values default to ./data/configuration/iii-directory.yaml (fs
adapter). Edit that file directly, call configuration::set id=iii-directory,
or use the Console's global Settings modal — all three propagate without a redeploy.
Fields
# TOPOLOGY — changing any of these requires a worker restart.
skills_folder: skills # under III_COMPOSE_DIR, or the process cwd standalone
local_skills_folder: skills/iii # project-scoped overrides (whole-namespace local-wins)
agents_folder: agents # direct <id>.md agent profiles
agents_skills_folder: .agents/skills # READ-ONLY agent skills, with the same relative-path base
auto_download: true # subscribe to worker-add + run the boot reconcile
# TUNABLE — hot-reload live on `configuration:updated`.
registry_url: https://api.workers.iii.dev # workers registry base URL
download_timeout_ms: 60000 # per git-clone / HTTP request timeout (ms)
registry_cache_ttl_ms: 60000 # in-process TTL for registry::workers::* responses
filter_unregistered: true # hide skills whose namespace isn't an installed worker
inject_hint: false # bind the directory::pre-generate search-hint hook (off: the harness identity prompt already teaches directory-first discovery)
hint_min_workers: 2 # minimum surface width before the hint fires (0 = always)
registry_search: true # include installable registry workers in every searchThe writable skills_folder and agents_folder roots are created when needed.
Zero-config default + seed
With no seed and no stored value the worker uses built-in defaults. Relative
folder paths use III_COMPOSE_DIR when set and the process current directory
otherwise (skills_folder: skills, agents_folder: agents,
registry_url: https://api.workers.iii.dev).
Pass --config to supply a YAML seed: when present and no value is
stored yet, its contents become initial_value on configuration::register
(see config.yaml.example). Engine-managed deployments
inline the config under the worker entry; the engine delivers it via --config.
Hot reload
On configuration::set (or an external edit to the persisted file), the worker
re-fetches the authoritative value. Tunable changes apply in place and the
registry caches are cleared so a repointed registry_url takes effect
immediately. Topology changes (skills_folder / local_skills_folder /
agents_folder / agents_skills_folder / auto_download) are refused with a "restart
required" log; the previous configuration is kept until the worker restarts.
The writable skills_folder, local_skills_folder, and agents_folder are
watch roots, and the watcher creates each one at boot if it is missing.
Direct edits under agents_folder fire
directory::agents::on-change with op: "external"; nested files are ignored.
agents_skills_folder is a watch root too,
but only when it already exists — the worker never creates (or writes)
anything under it. Install your first agents skill while the worker is
running and that root stays unwatched until the next restart: reads still
serve it, since every read re-scans disk, but the live external doorbell
is missing until then. local_skills_folder defaults to skills/iii under
III_COMPOSE_DIR, or under the process current directory when the worker runs
standalone. An empty local root shadows nothing. Because the roots are
restart-required, the watch
roots are fixed for the process lifetime.
Quickstart: download some skills
# Pull a specific worker's directory bundle at a fixed semver from
# the registry. Files land under `<skills_folder>/agent-memory/`.
iii trigger --function-id=directory::skills::download \
--payload='{"worker": "agent-memory", "version": "1.2.3"}'
# Same, but always fetch whatever's tagged `latest` (also the default
# when neither version nor tag is given).
iii trigger --function-id=directory::skills::download \
--payload='{"worker": "agent-memory"}'
# Pull a single subfolder out of a public GitHub repo via
# `git clone --depth 1 --branch main`. Files land under
# `<skills_folder>/frontend-design/`. The `branch` field defaults to
# `main`; pass `"master"` for older repos that haven't migrated.
iii trigger --function-id=directory::skills::download \
--payload='{
"repo": "https://github.com/anthropics/skills",
"skill": "frontend-design"
}'The response is
{ namespace, skills_written, system_prompts_written, agents_written, source }.
The three *_written fields list the files materialised in this run.
Registry entries shaped exactly as agents/ land in
; repo downloads do not install agent profiles.
After every successful download the worker fires the
directory::skills::on-change, directory::system-prompts::on-change,
and/or directory::agents::on-change trigger types so that
subscribers like the mcp worker can
forward MCP notifications/list_changed to their clients.
On-disk layout
The worker uses separate roots for directory content and agent profiles:
skills_folder/
<namespace>/ # one folder per `directory::skills::download` namespace
index.md # → iii://<namespace>/index
contacts.md # → iii://<namespace>/contacts
emails/send-email.md # → iii://<namespace>/emails/send-email
system-prompts/ # ← magic marker for system prompts
reviewer.md # ← identity prompt (needs YAML frontmatter)
system-prompts/ # ← where system-prompts::create writes
pirate.md
agents_folder/ # ← where agents::create writes
release-captain.md # ← agent profile (needs YAML frontmatter)
frontend-design.md # ← `extends: iii` builds on the bundled baseTwo base agent profiles ship inside the worker binary: iii (the harness
default identity, verbatim) and iii-minimal (the minimal directory-first
identity — the same text as the bundled system prompt of that name). Each is
always listed (builtin: true), a local agents_folder/ shadows it,
update on it copy-on-writes that local file, and deleting the file falls
back to the bundled copy. No file is ever seeded on disk.
A second, READ-ONLY root — agents_skills_folder (default .agents/skills
under the same Compose or standalone base) — serves agent skills. It is
scanned shallowly: only becomes an entry
(id , displayed as ); a skill's
reference/, scripts/, or other support payload is never listed. A
missing directory is silently empty. These skills bypass
filter_unregistered (their namespaces are skills, not workers), stay
out of directory::skills::index (a per-WORKER surface), and are
refused by update/delete — edit them with their owning tool, or
copy one into skills_folder on disk to fork it. Precedence is
local_skills_folder > skills_folder > agents_skills_folder,
namespace-wise: a top-level namespace directory in a higher root
shadows the same namespace below.
A few rules:
- Skill ids are the relative path under
skills_folderwith.mdstripped. Each segment must satisfy[a-z0-9_-]{1,64}. - Skill frontmatter is optional. When present, the reader recognises
title:(preferred title),name:(title fallback),type:(free-form classifier),function_id:(canonical bus function id surfaced bylistandget),description:(preferredlistteaser), anddisable-model-invocation:(boolean, defaultfalse, surfaced asdisable_model_invocationby both responses). The body H1 and first paragraph are the title and list-description fallbacks, respectively. Disabled skills remain visible to ordinary directory clients; model index consumers decide whether to filter them. Any other YAML keys are ignored. - System prompts live under any
*/system-prompts/*.mdpath, with YAML frontmatter (descriptionrequired,nameoptional). A path carrying both apromptsand asystem-promptssegment is a system prompt becausesystem-promptsis classified first. Other paths containing apromptssegment are ignored by scans and downloads. - What a system prompt can do, by design. The console's chat picker
can send a selected system prompt with
system_prompt_strategy: "override", which replaces the harness's built-in identity prompt with that file's body verbatim. Files reachsystem-prompts/either by local authoring or viadirectory::skills::downloadfrom a git repo or the registry, so a downloaded bundle can supply one. This is an accepted property, not a hole: it takes a deliberate selection in the UI, the same UI already accepts arbitrary typed text, and the operator ownsskills_folder. Worth knowing before you pointskills_folderat a directory other people can write to. - Agent profiles are direct
files (unrelated to the read-only/ .md agents_skills_folderabove, which holds external tools' skills). Nested profiles and the formerlayout are ignored. Frontmatter is required and must declare a non-empty/**/agents/*.md name(the display name — the id is always the file stem);descriptionmay be empty,logois emoji-only (≤16 bytes, no path characters),skills:filters the skill index (absent/empty = every skill), andmodel:names a model id for sessions using this profile (absent = the send decides), and optionalreasoning_effort:names its provider-native effort. Both are stored verbatim and resolved against the live model catalog where they are used. The body is the system prompt, verbatim, and may be empty — a profile with no prompt of its own contributes only its parent chain (if any) and its non-prompt settings. Unknownskillsids are warnings surfaced byget, never load failures. - Agent profiles inherit.
extends:names one parent profile (chains allowed, at most 8 hops). The resolved system prompt served bygetis the parent's resolved prompt followed by a blank line and this file's body — a blank body contributes nothing, so a profile with no prompt of its own serves its parent chain unchanged;skills,modelandreasoning_effortfall back to the nearest ancestor that sets them when omitted (a non-emptyskillslist replaces, never unions);name,description,logo,iconandcolorare always the profile's own. A chain that does not resolve (unknown parent, loop, too deep) is reported bylist/getasinheritance_error(D415text) while the profile still serves its own file (so the editor can fix it); the harness refuses to run it. - Under a skills root, files outside
prompts/,system-prompts/, and reservedagents/segments are skills.
The download function namespaces by source:
| Source | Destination |
|---|---|
repo=URL skill=NAME branch?=main |
|
worker=NAME version=… |
Skills/prompts under ; exact agents/ entries under |
worker=NAME tag=… (default tag=latest) |
Same routing as the version form |
Re-pulling the same source overwrites files file-by-file — existing siblings outside the response set are preserved (so hand-edited additions survive a re-pull).
Skill ids
Skills are addressed by their relative path under skills_folder with
.md stripped — e.g. →
id "agent-memory/observe". The same string is what
directory::skills::list returns and what directory::skills::get
expects in { "id": ... }. The legacy iii://{id} link form is still
accepted on get (the prefix is auto-stripped), but the worker no
longer parses any other iii:// URI shape — bodies are read solely by
id, and the auto-rendered tree-shaped index that previous releases
served at iii://directory/skills is gone. Consumers that want a
tree-shaped picker iterate list rows themselves and indent by
id.matches('/').count().
Functions
Functions sit under directory::*. All registrations are
namespace-clean; this worker is intentionally agnostic to MCP and any
other adapter.
directory::skills::* (filesystem reader + editor)
| Function ID | Description |
|---|---|
directory::skills::download |
Download directory content. Flexible alias accepting either source set: {repo, skill, branch?} (defaults branch=main) or {worker, version?|tag?} (defaults tag=latest). Prefer the two explicit forms below so the source is unambiguous. |
directory::skills::download_from_repo |
Repo-only form: {repo, skill, branch?}. Copies one skill folder out of a GitHub repo; paths under prompts/ and agents/ are ignored. |
directory::skills::download_from_registry |
Registry-only form: {worker, version?|tag?}. Installs a published worker's bundle from api.workers.iii.dev, routing exact agents/ entries to agents_folder. |
directory::skills::list |
Enriched listing of every fs-backed skill: { id, title, type, function_id, disable_model_invocation, description, bytes, modified_at } per row. title prefers the YAML frontmatter title: over the body H1, type is lifted from frontmatter type: (null when absent), function_id identifies the documented bus function when present, and description is the frontmatter description or first body paragraph — so consumers can render a picker without a follow-up get per row. |
directory::skills::get |
Fetch one skill by id. Returns { id, title, type, function_id, disable_model_invocation, path, body, modified_at }. It shares the list row's identity, classification, function, and invocation metadata, but returns the raw markdown body and absolute on-disk path instead of the teaser and byte count; there is no description field. The path's parent directory is the skill's base directory, where payload like scripts/ and reference/ lives, and is meaningful only to callers on this worker's machine. Accepts a bare id or the same id prefixed with iii://. Pass raw: true to additionally get the FULL on-disk file (frontmatter included) as raw — the round-trip form update takes. |
directory::skills::update |
Overwrite one EXISTING skill file with new full-file content: { id, content } where content is the edited raw from get { raw: true }. Validated against the read invariants (size cap, non-empty body after frontmatter); atomic write; fans out directory::skills::on-change with op: "update". Never creates files (use create). Refuses read-only system-installed skills under agents_skills_folder (D116). |
directory::skills::create |
Create a NEW skill file at from full-file content: { id, content }. Frontmatter is optional (same rules as update: size cap, non-empty body). Refuses an id that already resolves in the visible set — including the → overview alias and system-installed agents skills — or a target path that already exists on disk (D114); an id in a namespace reserved by a system-installed agents skill (D115); and, while filter_unregistered is on, an id the visibility filter would immediately hide (D115). Atomic write; fans out directory::skills::on-change with op: "create". Returns the same shape as update. |
directory::skills::delete |
Permanently remove one EXISTING skill file by { id } (same id forms as get). Resolves against the same visible set as list/get, refuses read-only system-installed skills under agents_skills_folder (D116), removes the file plus any parent directories left empty (so a deleted namespace can't keep shadowing a lower-precedence root), and fans out directory::skills::on-change with op: "delete". Returns { id } (the resolved on-disk id). |
directory::skills::index |
Render one short markdown entry per installed worker (skills with frontmatter type: index). Returns { body, workers_count } where body is a ready-to-paste page: # Skills index, then one ## heading + the worker's first overview paragraph + a Read iii:// pointer the agent can follow with directory::skills::get. Token-light by design; use directory::skills::list for per-skill rows. |
directory::system-prompts::* (filesystem reader + editor)
| Function ID | Description |
|---|---|
directory::system-prompts::list |
Metadata-only listing of every fs-backed system prompt. |
directory::system-prompts::get |
Fetch one system prompt's body + {name, description, modified_at}. Plain shape, no envelope. Pass raw: true to additionally get the FULL on-disk file (frontmatter included) as raw. |
directory::system-prompts::update |
Overwrite one EXISTING system prompt file with new full-file content: { name, content }. The frontmatter must keep a non-empty description (and a valid name when declared) — the same rules the scanner enforces. Atomic write; fans out directory::system-prompts::on-change with op: "update". Returns the system prompt's effective name after the write. |
directory::system-prompts::create |
Create a NEW system prompt file at from full-file content: { name, content }, where content is the FULL file including frontmatter. The frontmatter must carry a non-empty description (and a name matching the request, when declared) — the same rules update enforces. Refuses a name that already exists anywhere in the merged system-prompt scan, and a target path that already exists on disk even if the scanner would skip it. Atomic write; fans out directory::system-prompts::on-change with op: "create". Returns { name, description, bytes, modified_at }. |
directory::system-prompts::delete |
Permanently remove one EXISTING system prompt file by { name }. Resolves against the same merged scan as list/get, fans out directory::system-prompts::on-change with op: "delete", and returns { name }. |
Agent Profiles — directory::agents::* (filesystem reader + editor)
| Function ID | Description |
|---|---|
directory::agents::list |
Metadata-only listing of every agent profile — fs-backed plus the bundled iii / iii-minimal bases (builtin: true until a local file shadows one): { id, name, description, logo, skill_count, model, reasoning_effort, icon, color, extends, modified_at } per row, skill_count/model/reasoning_effort resolved through extends (skill_count: null = every skill; model: null = the send decides). A row whose chain does not resolve carries inheritance_error. |
directory::agents::get |
Fetch one agent profile by { id }: the RESOLVED system_prompt (each ancestor's body root-first, then this file's body), skills + unknown_skills (filter entries matching no visible skill — warnings), model (null = the send decides), provider-native reasoning_effort, display icon/color, extends, builtin, modified_at, and inheritance_error when the chain does not resolve (own file served meanwhile). Pass raw: true to additionally get this profile's FULL on-disk file as raw. |
directory::agents::update |
Overwrite one EXISTING agent profile file with new full-file content: { id, content }. Same rules the scanner enforces (required frontmatter with non-empty name, emoji-only logo; the body — the system prompt — may be empty); the id stays the file stem. Updating a bundled profile creates the local file that shadows it. Atomic write; fans out directory::agents::on-change with op: "update". |
directory::agents::create |
Create a NEW agent profile at from full-file content: { id, content }. Refuses an id that already exists in the configured agent-profile root, and a target path that already exists on disk even if the scanner would skip it; creating a bundled id shadows the bundled copy. Atomic write; fans out directory::agents::on-change with op: "create". Returns { id, name, description, logo, bytes, modified_at }. |
directory::agents::delete |
Permanently remove one EXISTING agent profile file by { id }. Resolves against the same configured root as list/get, fans out directory::agents::on-change with op: "delete", and returns { id }. Deleting the local shadow of a bundled profile falls back to the bundled copy; a bundled profile with no local file has nothing to delete (D414). Sessions already using the profile are unaffected; profiles extending it stop resolving until fixed. |
Engine introspection (native, plus one wrapper)
Engine introspection is served natively; call these ids directly — every
one takes the same filters (prefix, search, worker,
include_internal where applicable). One wrapper is kept for callers
whose policy only admits the directory:: namespace:
| Function ID | Description |
|---|---|
directory::engine::functions::info |
Thin proxy to engine::functions::info for a single function_id: request/response schemas, metadata, and registered triggers. The one directory::engine::* helper that still exists — reach for it only when you cannot call engine::* directly. |
The native ids:
| Function ID | Description |
|---|---|
engine::functions::list |
List functions registered with the engine. |
engine::functions::info |
Single-function detail: schemas, owning worker. |
engine::triggers::list |
List trigger TYPES (the providers, e.g. http, cron). |
engine::triggers::info |
Single trigger-type detail: configuration schema, return schema. |
engine::registered-triggers::list |
List trigger INSTANCES (subscriber rows). |
engine::registered-triggers::info |
Single registered-trigger detail. |
engine::workers::list |
List workers with an open engine WS connection. Daemon-managed providers (http, cron, state) won't appear — call worker::list from the supervisor to see those. |
engine::workers::info |
One worker's detail by name. |
directory::registry::* (workers registry HTTP proxy)
| Function ID | Description |
|---|---|
directory::registry::workers::list |
Browse / search published workers in api.workers.iii.dev. Optional free-text search (matched fuzzy by pg_trgm) and opaque cursor for pagination; page size is server-authored. Response is { workers: [...], pagination: { next_cursor, has_more, page_size } }. Shares the core name / description / version fields with the engine's engine::workers::list. |
directory::registry::workers::info |
Pre-install card for one worker. Fans out two parallel registry calls — GET /w/{slug} for the worker envelope (publication metadata + readme + functions + triggers) and GET /w/{slug}/skills for the skills tree — and merges them into { worker, api_reference, skills_tree, readme? }. The card keeps public function/trigger names and descriptions only: request/response schemas, metadata, internal and search-excluded functions are dropped (browser's schemas alone ran 65 KB; the contract is engine::functions::info after installing), and readme (10–25 KB) is included only with readme: true. The full record stays cached in-process for directory::search_functions. Input still accepts version: (semver) or tag: (e.g. latest); both go on the wire as ?version=…. |
Both directory::registry::* responses are cached in-process for
registry_cache_ttl_ms (default 60s).
There is no directory::skills::register — see
Migration below.
Function search & pre-generate hint
One-shot function search over the live engine catalog (hybrid by default:
BM25 fused with the local MiniLM model, reranked; function_search_mode: lexical for BM25 only), absorbed from the former discovery worker. It returns only compact { function_id, description } candidates, grouped by worker in rank order. The model chooses
the candidates it needs, then fetches their contracts in one
engine::functions::info { function_ids: [...] } call instead of walking the
catalog with engine::functions::list.
| Function | Kind | What it does |
|---|---|---|
directory::search_functions |
public | { capabilities } → { guidance, workers[], installable[]?, latency_ms }: hybrid rank over the live engine catalog in batches of six capabilities (12 candidates per batch across at most max(6, 2 × capabilities) workers, up to 3 batches) plus matching NOT-installed registry workers under installable. capabilities is a required list of non-empty unmet external capability searches (one to six is the norm); entries past the 18th are not searched and are named in guidance. Requests to summarize provided text/content are ignored. |
directory::pre-generate |
internal hook | Injects the conditional search hint into a harness generation (at most once per turn). |
directory::on-functions-change |
internal | Refreshes the search catalog on the engine's functions-available push. |
directory::hint-preview |
internal | The exact hint text per exposure mode, for the configuration UI. |
Ranking pipeline:
- Corpus: the live engine catalog (boot snapshot + push refresh),
slimmed to name + first description sentence + argument names.
engine::ids, functions published withmetadata.internal, and the search itself never participate — the worker's own publicdirectory::*functions are searchable like any other capability. - Scoring: Okapi BM25 (k1 1.2, b 0.75) with the function name indexed at
3× weight, camelCase segmentation (
presignUrl→ presign + url), a 22-word grammatical stoplist, conservative plural folding, JSON-key stripping from capability text, and a two-distinct-terms minimum match. - Capability queries: each
capabilitiesentry is ranked independently against its own leader and is authoritative. Include every currently unmet external capability once in the same call. Write every capability in English, translating non-English requests while preserving proper names, URLs, and function ids. Requests to summarize provided text or content are ignored. Results merge round-robin so every capability gets a candidate before any gets a rider. - Pruning: coverage-aware function floor (≥50% of the leader AND full term coverage or ≥85% score) drops same-worker family riders; a namespace-level floor (40% of the leader) drops trailing workers.
- Registry search (
registry_search, default on): every call also consults the private workers registry in-process with the same capability queries plus informative-term retries (all concurrent; every listed worker is a candidate — the registry is team-authored). Candidates merge round-robin across search variants; their API references are pooled and ranked per capability with BM25 fused with the MiniLM dense lane (same 0.30 admission floor as the installed catalog), so a capability sharing no vocabulary with a contract ("retrieve web news articles" →web::fetch) still surfaces. Returns up to 2 workers / 6 candidates per batch of six capabilities (so up to 6 workers / 18 candidates across three batches; a worker two batches both surface keeps one entry with its functions merged) that WOULD match if installed, withcompose::addguidance. - Session memory (keyed by caller-supplied OTel baggage, fail-open): repeat queries omit candidates already delivered.
The pre-generate hook appends one block pointing the
model at search_functions, telling it to derive capabilities from the goal
and current execution state and to batch selected ids through
engine::functions::info — at most once per turn, and only when every gate
clears: the function is callable in the surface, no search result is in the
current task window yet, the surface spans at least hint_min_workers distinct
workers, the current task (from the latest user message) has no real function
results yet, and it does not already name a callable function id. Measured on
26 pre-existing e2e scenarios: an unconditional hint induces redundant
discovery on guided tasks (up to +110% tokens). The hook ships OFF by default
(inject_hint: false): the harness identity prompt already teaches
directory::search_functions as the default discovery path, so the hint is
for deployments running a custom identity prompt without that doctrine. The
hook's transcript annotations (origin.directory) carry only coarse
outcome/reason and counts.
Knobs (inject_hint, hint_min_workers, registry_search) live in the
iii-directory configuration entry and hot-apply — see Configuration.
Custom trigger types
| Trigger type | Fires when | Payload to subscribers |
|---|---|---|
directory::skills::on-change |
After a directory::skills::download that wrote at least one skill markdown file, a directory::skills::update, create, or delete, or external (file pasted/edited/deleted directly on disk — including under agents_skills_folder) |
download: { "op": "download", "namespace": "; update/create/delete: { "op": "; external (file pasted/edited/deleted directly on disk): { "op": "external" } |
directory::system-prompts::on-change |
After a directory::skills::download that wrote at least one system prompt markdown file, a directory::system-prompts::update, create, delete, or external file change |
download: { "op": "download", "namespace": "; update/create/delete: { "op": "; external: { "op": "external" } |
directory::agents::on-change |
After a directory::skills::download that wrote at least one agent profile, a directory::agents::update, create, delete, or external file change |
download: { "op": "download", "namespace": "; update/create/delete: { "op": "; external: { "op": "external" } |
Dispatches are fire-and-forget (Void), so the write path doesn't block on downstream latency.
The external op comes from a filesystem watch over skills_folder,
local_skills_folder, and (when it already exists) the read-only
agents_skills_folder. It is a doorbell, not a ledger: every read re-scans
disk, so a missed event costs a stale open view until the next call, never
data. A burst coalesces into one event per kind, and this worker's own writes
are suppressed — a create or update sends its precise op and never an
extra external.
Loop hazard for subscribers. Suppression covers writes made through this
worker. A subscriber that reacts to { "op": "external" } by writing .md
files under skills_folder by some other route — a shell or coder worker, a
script — is not suppressed and will re-trigger itself. Either write through
directory::*::update / create, or make the reaction idempotent and gated.
Local development & testing
Run from source
On targets with a pinned static ONNX Runtime (Linux glibc x86_64/aarch64,
Apple Silicon macOS, Windows MSVC) every build links it and MiniLM retrieval
and reranking are compiled in. With no ORT_LIB_PATH, ort-sys downloads the
runtime for the build target at build time (SHA-256-verified). For offline or
cached x86_64 Linux builds, provision it once and export the path it prints:
export ORT_LIB_PATH="$(scripts/provision-onnxruntime.sh)" # idempotent, SHA-256 verified
export ORT_PREFER_DYNAMIC_LINK=0Other targets (musl, armv7, Intel macOS) build the BM25-only worker and need nothing extra.
# --config is an optional YAML seed (see config.yaml.example); omit it to
# rely on the value stored in the `configuration` worker (or built-in defaults).
cargo run --release -- --url ws://127.0.0.1:49134 --config ./config.yaml.exampleTests
# Fast, offline — exercises the pure helpers (markdown / id validators
# / fs source) without needing an iii engine.
cargo test --lib
# Full BDD suite — requires an iii engine on ws://127.0.0.1:49134
# (or III_ENGINE_WS_URL). The git-backed download scenarios spin up
# a local fixture repo via `git init`; the registry-backed scenarios
# point a wiremock server at the worker's `registry_url` config.
cargo test
# One feature group at a time. Available tags:
# @engine @read @download @download_repo @download_registry
cargo test --test bdd -- --tags @downloadThe BDD harness lives under tests/. Feature files mirror the
modules in src/functions/. Step definitions under
tests/steps/ drive each feature through the same
iii.trigger path the production binary uses.
api reference (json)
{
"functions": [
{
"description": "Internal: auto-download skills on worker add event.",
"metadata": {
"internal": true
},
"name": "directory::__on_worker_added",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "`worker` trigger payload for `directory::__on_worker_added`. Only `worker` is read; declared as a struct so the function publishes a typed schema.",
"properties": {
"worker": {
"default": null,
"type": [
"string",
"null"
]
}
},
"title": "WorkerAddedEvent",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"ok": {
"type": "boolean"
}
},
"required": [
"ok"
],
"title": "WorkerAddedAck",
"type": "object"
}
},
{
"description": "Create a new agent profile at <agents_folder>/<id>.md from full-file markdown (frontmatter with a non-empty `name`, emoji-only `logo`; the body is the system prompt and may be empty). Rejects ids or paths that already exist; a bundled id is shadowed.",
"metadata": {
"tool": {
"label": "Create agent profile"
}
},
"name": "directory::agents::create",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"content": {
"description": "Full file content, frontmatter included; `name` is required, the body is the system prompt and may be empty.",
"type": "string"
},
"id": {
"description": "New profile id, used as the file stem; lowercase ASCII, digits, `-` and `_` only, and not already taken.",
"type": "string"
}
},
"required": [
"content",
"id"
],
"title": "AgentCreateInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"bytes": {
"description": "Bytes written.",
"format": "uint",
"minimum": 0,
"type": "integer"
},
"description": {
"type": "string"
},
"id": {
"type": "string"
},
"logo": {
"type": [
"string",
"null"
]
},
"modified_at": {
"description": "File mtime after the write, RFC 3339.",
"type": "string"
},
"name": {
"description": "Display name parsed from the (new) frontmatter.",
"type": "string"
}
},
"required": [
"bytes",
"description",
"id",
"modified_at",
"name"
],
"title": "AgentWriteOutput",
"type": "object"
}
},
{
"description": "Delete one existing agent profile's markdown file by id. Deleting the local shadow of a bundled profile falls back to the bundled copy; profiles that extend it stop resolving until fixed.",
"metadata": {
"tool": {
"label": "Delete agent profile"
}
},
"name": "directory::agents::delete",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"description": "Existing agent profile id, as returned by `directory::agents::list`.",
"type": "string"
}
},
"required": [
"id"
],
"title": "AgentDeleteInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"title": "AgentDeleteOutput",
"type": "object"
}
},
{
"description": "Fetch one agent profile by id: the system prompt resolved through its `extends` chain, display fields, skill filter, model, reasoning_effort, and `inheritance_error` when the chain does not resolve. Pass raw: true for the exact on-disk file to edit with directory::agents::update.",
"metadata": {},
"name": "directory::agents::get",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"type": "string"
},
"raw": {
"default": null,
"description": "When true, also return the exact on-disk file (frontmatter included) as `raw`, ready for directory::agents::update.",
"type": [
"boolean",
"null"
]
}
},
"required": [
"id"
],
"title": "AgentGetInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"builtin": {
"description": "Bundled with the worker, no file behind it (see `list`).",
"type": "boolean"
},
"color": {
"description": "Harness subagent color token (closed set, validated at write time); `null` = neutral.",
"type": [
"string",
"null"
]
},
"description": {
"type": "string"
},
"extends": {
"description": "Parent profile id (`extends:`), as declared; `null` = none.",
"type": [
"string",
"null"
]
},
"icon": {
"description": "Harness subagent icon token (closed set, validated at write time); `null` = caller picks.",
"type": [
"string",
"null"
]
},
"id": {
"type": "string"
},
"inheritance_error": {
"description": "Set when the `extends` chain does not resolve (unknown parent, loop, deeper than 8): `system_prompt` and the inherited fields then come from this file alone, `raw` still round-trips so the chain can be fixed, and the harness refuses to run the profile meanwhile.",
"type": [
"string",
"null"
]
},
"logo": {
"type": [
"string",
"null"
]
},
"model": {
"description": "Model id for sessions using this profile, resolved through `extends`; `null` = the send decides. Served verbatim — resolution against the live model catalog happens where it is used.",
"type": [
"string",
"null"
]
},
"modified_at": {
"description": "File mtime as RFC 3339; empty for a bundled profile.",
"type": "string"
},
"name": {
"type": "string"
},
"raw": {
"description": "FULL on-disk file content (this profile's own file, ancestors excluded). Present only when the request set `raw: true`.",
"type": [
"string",
"null"
]
},
"reasoning_effort": {
"description": "Provider-native reasoning effort paired with `model`, resolved through `extends`; `null` = the model/provider default. Served verbatim and validated at use time.",
"type": [
"string",
"null"
]
},
"skills": {
"description": "The skill filter, resolved through `extends` (the nearest profile with a non-empty filter). Empty = every skill.",
"items": {
"type": "string"
},
"type": "array"
},
"system_prompt": {
"description": "The RESOLVED identity: every ancestor's body root-first, then this file's body, frontmatter stripped, joined by a blank line; blank bodies are skipped, so a profile with no prompt of its own serves its parent chain unchanged and a prompt-less profile without `extends` serves `\"\"`. A profile that has a body and no `extends` serves that body verbatim.",
"type": "string"
},
"unknown_skills": {
"description": "Filter entries that resolve to no currently visible skill. Warnings — the agent profile still loads.",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"builtin",
"description",
"id",
"modified_at",
"name",
"skills",
"system_prompt",
"unknown_skills"
],
"title": "AgentGetOutput",
"type": "object"
}
},
{
"description": "List agent profiles (id, name, description, logo, icon, color, model, reasoning_effort, skill_count, extends, modified_at) from the agents folder plus the bundled ones (`builtin: true`). Inherited fields resolve through `extends`; skill_count null means every skill.",
"metadata": {},
"name": "directory::agents::list",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "ListAgentsInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"AgentEntry": {
"properties": {
"builtin": {
"description": "Bundled with the worker, no file behind it: editing it creates the local file (which then shadows this entry); there is nothing to delete.",
"type": "boolean"
},
"color": {
"description": "Harness subagent color token for display identities; `null` = neutral.",
"type": [
"string",
"null"
]
},
"description": {
"type": "string"
},
"extends": {
"description": "Parent profile id (`extends:`), as declared; `null` = none.",
"type": [
"string",
"null"
]
},
"icon": {
"description": "Harness subagent icon token for spawn display identities; `null` = caller picks.",
"type": [
"string",
"null"
]
},
"id": {
"description": "Flat agent profile id (the file stem) — what `harness::send { options: { agent } }` will take.",
"type": "string"
},
"inheritance_error": {
"description": "Set when the `extends` chain does not resolve (unknown parent, loop, too deep): the row carries the profile's own fields only, and the harness refuses to run it until the chain is fixed.",
"type": [
"string",
"null"
]
},
"logo": {
"description": "Emoji logo, `null` when the agent profile has none.",
"type": [
"string",
"null"
]
},
"model": {
"description": "Model id for sessions using this profile, resolved through `extends`; `null` = the send decides.",
"type": [
"string",
"null"
]
},
"modified_at": {
"description": "File mtime as RFC 3339; empty for a bundled profile.",
"type": "string"
},
"name": {
"description": "Display name from frontmatter (`name:`).",
"type": "string"
},
"reasoning_effort": {
"description": "Provider-native reasoning effort paired with `model`, resolved through `extends`; `null` = the model/provider default.",
"type": [
"string",
"null"
]
},
"skill_count": {
"description": "Length of the agent profile's skill filter, resolved through `extends`; `null` = no filter (every skill).",
"format": "uint",
"minimum": 0,
"type": [
"integer",
"null"
]
}
},
"required": [
"builtin",
"description",
"id",
"modified_at",
"name"
],
"type": "object"
}
},
"properties": {
"agents": {
"items": {
"$ref": "#/definitions/AgentEntry"
},
"type": "array"
}
},
"required": [
"agents"
],
"title": "ListAgentsOutput",
"type": "object"
}
},
{
"description": "Overwrite one existing agent profile with full-file markdown (frontmatter with a non-empty `name`, emoji-only `logo`; the body is the system prompt and may be empty). Updating a bundled profile creates a local file that shadows it.",
"metadata": {
"tool": {
"label": "Update agent profile"
}
},
"name": "directory::agents::update",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"content": {
"description": "FULL new file content, frontmatter block included — the string `directory::agents::get { raw: true }` returns, edited.",
"type": "string"
},
"id": {
"description": "Existing agent profile id, as returned by `directory::agents::list`.",
"type": "string"
}
},
"required": [
"content",
"id"
],
"title": "AgentUpdateInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"bytes": {
"description": "Bytes written.",
"format": "uint",
"minimum": 0,
"type": "integer"
},
"description": {
"type": "string"
},
"id": {
"type": "string"
},
"logo": {
"type": [
"string",
"null"
]
},
"modified_at": {
"description": "File mtime after the write, RFC 3339.",
"type": "string"
},
"name": {
"description": "Display name parsed from the (new) frontmatter.",
"type": "string"
}
},
"required": [
"bytes",
"description",
"id",
"modified_at",
"name"
],
"title": "AgentWriteOutput",
"type": "object"
}
},
{
"description": "Read full detail for one engine function: schemas, owning worker, and registered triggers that target it. Proxies to the engine's native engine::functions::info.",
"metadata": {},
"name": "directory::engine::functions::info",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"function_id": {
"description": "Fully-qualified function id on the bus (e.g. `sandbox::create`).",
"type": "string"
}
},
"required": [
"function_id"
],
"title": "FunctionInfoInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"RegisteredTriggerSummary": {
"description": "Trigger instance summary for the response envelope.",
"properties": {
"config": true,
"id": {
"type": "string"
},
"trigger_type": {
"type": "string"
}
},
"required": [
"config",
"id",
"trigger_type"
],
"type": "object"
}
},
"description": "Response shape for `directory::engine::functions::info`.\n\nMirrors the shape of the old `directory::engine::functions::info` but WITHOUT the `how_guide` and `related_skills` fields.",
"properties": {
"description": {
"type": [
"string",
"null"
]
},
"function_id": {
"type": "string"
},
"metadata": true,
"registered_triggers": {
"items": {
"$ref": "#/definitions/RegisteredTriggerSummary"
},
"type": "array"
},
"request_schema": true,
"response_schema": true,
"worker_name": {
"type": [
"string",
"null"
]
}
},
"required": [
"function_id",
"registered_triggers"
],
"title": "FunctionInfoOutput",
"type": "object"
}
},
{
"description": "Internal: the exact search-hint text per exposure mode, for the configuration UI.",
"metadata": {
"internal": true,
"trace_hidden": true
},
"name": "directory::hint-preview",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "HintPreviewRequest",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "The exact hint text per exposure mode, for the configuration UI. The live block's `functions_generation` attribute varies per generation; the preview renders it as 0.",
"properties": {
"agent_trigger": {
"type": "string"
},
"native": {
"type": "string"
}
},
"required": [
"agent_trigger",
"native"
],
"title": "HintPreviewResponse",
"type": "object"
}
},
{
"description": "Internal: reload tunable iii-directory settings from the authoritative configuration when it changes.",
"metadata": {
"internal": true
},
"name": "directory::on-config-change",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Trigger payload for `directory::on-config-change`. The handler ignores it (it re-fetches from the authoritative configuration); the empty struct exists so the function publishes a typed request schema rather than AnyValue.",
"title": "OnConfigChangeRequest",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"ok": {
"type": "boolean"
}
},
"required": [
"ok"
],
"title": "OnConfigChangeResponse",
"type": "object"
}
},
{
"description": "Internal: refresh the search catalog after the engine function set changes.",
"metadata": {
"internal": true,
"trace_hidden": true
},
"name": "directory::on-functions-change",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"event": {
"type": [
"string",
"null"
]
}
},
"title": "OnFunctionsChangeEvent",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"ok": {
"type": "boolean"
}
},
"required": [
"ok"
],
"title": "AckResponse",
"type": "object"
}
},
{
"description": "Internal: inject the conditional search hint into one harness generation.",
"metadata": {
"internal": true,
"trace_hidden": true
},
"name": "directory::pre-generate",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"ExposeKind": {
"oneOf": [
{
"enum": [
"agent_trigger",
"native"
],
"type": "string"
},
{
"description": "Forward compatibility: an exposure mode this build does not know gets the mode-neutral call instruction rather than a deserialization error.",
"enum": [
"other"
],
"type": "string"
}
]
},
"GeneratePayload": {
"properties": {
"expose": {
"allOf": [
{
"$ref": "#/definitions/ExposeKind"
}
],
"description": "How the harness exposes functions to the model for this generation. Absent on harnesses that predate the field, which only ever exposed through agent_trigger by default."
},
"functions_generation": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"messages": {
"items": true,
"type": "array"
},
"system_prompt": {
"type": "string"
},
"tools": {
"items": {
"$ref": "#/definitions/ToolSchema"
},
"type": "array"
}
},
"required": [
"functions_generation",
"messages",
"system_prompt",
"tools"
],
"type": "object"
},
"ToolSchema": {
"description": "One catalog entry: the contract fields search runs on.",
"properties": {
"description": {
"type": "string"
},
"name": {
"type": "string"
},
"parameters": true
},
"required": [
"description",
"name",
"parameters"
],
"type": "object"
}
},
"properties": {
"depth": {
"format": "uint32",
"minimum": 0,
"type": "integer"
},
"generate": {
"$ref": "#/definitions/GeneratePayload"
},
"session_id": {
"type": "string"
},
"step": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"turn_id": {
"type": "string"
}
},
"required": [
"depth",
"generate",
"session_id",
"step",
"turn_id"
],
"title": "PreGenerateHookRequest",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"DiscoveryOutcome": {
"enum": [
"hint_injected",
"skipped"
],
"type": "string"
},
"DiscoveryPassV1": {
"description": "The durable transcript row for one hook pass. Coarse by design: outcome, reason, and counts only — no prompts, messages, tool contracts, session ids, or timings ever leave the hook.",
"properties": {
"allowed_functions": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"functions_generation": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"outcome": {
"$ref": "#/definitions/DiscoveryOutcome"
},
"reason": {
"anyOf": [
{
"$ref": "#/definitions/DiscoveryReason"
},
{
"type": "null"
}
]
}
},
"required": [
"allowed_functions",
"functions_generation",
"outcome"
],
"type": "object"
},
"DiscoveryReason": {
"enum": [
"search_unavailable",
"already_searched",
"narrow_surface",
"already_operating",
"task_guided",
"hint_already_sent"
],
"type": "string"
},
"DiscoveryTranscriptAnnotation": {
"properties": {
"data": {
"$ref": "#/definitions/DiscoveryPassV1"
},
"summary": {
"type": "string"
},
"type": {
"type": "string"
},
"version": {
"format": "uint8",
"minimum": 0,
"type": "integer"
}
},
"required": [
"data",
"summary",
"type",
"version"
],
"type": "object"
},
"PreGenerateAnnotations": {
"properties": {
"directory": {
"$ref": "#/definitions/DiscoveryTranscriptAnnotation"
}
},
"required": [
"directory"
],
"type": "object"
},
"PreGenerateMutations": {
"properties": {
"append_messages": {
"description": "Ephemeral tail messages for this generation only. The hint rides here rather than as a system-prompt mutation: the system prompt is the provider's first input item, and a once-per-turn append there invalidated the entire prompt-cache prefix twice per turn.",
"items": true,
"type": "array"
}
},
"required": [
"append_messages"
],
"type": "object"
}
},
"properties": {
"annotations": {
"$ref": "#/definitions/PreGenerateAnnotations"
},
"decision": {
"type": "string"
},
"mutations": {
"anyOf": [
{
"$ref": "#/definitions/PreGenerateMutations"
},
{
"type": "null"
}
]
}
},
"required": [
"annotations",
"decision"
],
"title": "PreGenerateHookResponse",
"type": "object"
}
},
{
"description": "Preview one registry worker before installing: envelope (version, kind, dependencies, config), its public function and trigger names with descriptions, and skill file paths. Schemas are omitted — install, then read contracts with engine::functions::info. Pass `readme: true` for the README prose; `version` or `tag` (default tag \"latest\").",
"metadata": {},
"name": "directory::registry::workers::info",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "`directory::registry::workers::info` input. Pass either `version` or `tag`; if neither is provided we fall back to `tag: \"latest\"`.",
"properties": {
"name": {
"description": "Worker name in the registry (e.g. `\"resend\"`).",
"type": "string"
},
"readme": {
"default": false,
"description": "Include the README markdown (10–25 KB for most workers). Off by default: the card is for judging fit before `compose::add`; the README is for setup prose and examples.",
"type": "boolean"
},
"tag": {
"default": null,
"type": [
"string",
"null"
]
},
"version": {
"default": null,
"description": "Mutually exclusive with `tag`. If neither is provided we fall back to `tag: \"latest\"`.",
"type": [
"string",
"null"
]
}
},
"required": [
"name"
],
"title": "WorkerInfoInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"ApiReference": {
"properties": {
"functions": {
"default": [],
"items": {
"$ref": "#/definitions/ApiReferenceFunction"
},
"type": "array"
},
"triggers": {
"default": [],
"items": {
"$ref": "#/definitions/ApiReferenceTrigger"
},
"type": "array"
}
},
"type": "object"
},
"ApiReferenceFunction": {
"properties": {
"description": {
"type": [
"string",
"null"
]
},
"metadata": true,
"name": {
"type": "string"
},
"request_schema": true,
"response_schema": true
},
"required": [
"name"
],
"type": "object"
},
"ApiReferenceTrigger": {
"properties": {
"description": {
"type": [
"string",
"null"
]
},
"invocation_schema": true,
"metadata": true,
"name": {
"type": "string"
},
"return_schema": true
},
"required": [
"name"
],
"type": "object"
},
"Dependency": {
"description": "Worker dependency entry. Mirrors the `Dependency` schema in `openapi.yaml`.",
"properties": {
"name": {
"type": "string"
},
"version": {
"type": "string"
}
},
"required": [
"name",
"version"
],
"type": "object"
},
"SkillsTree": {
"properties": {
"skills": {
"default": [],
"items": {
"$ref": "#/definitions/SkillsTreeSkill"
},
"type": "array"
}
},
"type": "object"
},
"SkillsTreeSkill": {
"properties": {
"path": {
"type": "string"
}
},
"required": [
"path"
],
"type": "object"
},
"Worker": {
"description": "Shared worker envelope used by both `directory::registry::workers::list` rows and the `worker` field of `directory::registry::workers::info`. Field names match the OpenAPI `WorkerListItem` schema. The shared core fields (`name`, `description`, `version`) line up with the engine's `engine::workers::list` row shape so callers learn one envelope across local + registry surfaces.",
"properties": {
"author": {
"anyOf": [
{
"$ref": "#/definitions/WorkerAuthor"
},
{
"type": "null"
}
],
"default": null
},
"config": {
"default": {},
"description": "Free-form runtime configuration block from the publish payload."
},
"dependencies": {
"default": [],
"items": {
"$ref": "#/definitions/Dependency"
},
"type": "array"
},
"description": {
"default": null,
"type": [
"string",
"null"
]
},
"image": {
"description": "Container image tag, populated only for `type=image` workers.",
"type": [
"string",
"null"
]
},
"name": {
"type": "string"
},
"repo": {
"default": null,
"type": [
"string",
"null"
]
},
"supported_targets": {
"default": [],
"items": {
"type": "string"
},
"type": "array"
},
"total_downloads": {
"default": 0,
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"type": {
"default": null,
"description": "Worker kind — `binary`, `image`, or `engine`.",
"type": [
"string",
"null"
]
},
"version": {
"default": null,
"description": "Latest published version (worker-list) or the resolved version (worker-info, when called with `version` / `tag`).",
"type": [
"string",
"null"
]
}
},
"required": [
"name"
],
"type": "object"
},
"WorkerAuthor": {
"description": "Author block for a published worker. Field names match the `WorkerAuthor` schema in `openapi.yaml` (`pfp`, `verified`).",
"properties": {
"name": {
"type": [
"string",
"null"
]
},
"pfp": {
"default": null,
"description": "Profile picture URL. `null` when the author hasn't uploaded one.",
"type": [
"string",
"null"
]
},
"verified": {
"default": false,
"type": "boolean"
}
},
"type": "object"
}
},
"properties": {
"api_reference": {
"$ref": "#/definitions/ApiReference"
},
"readme": {
"type": [
"string",
"null"
]
},
"skills_tree": {
"$ref": "#/definitions/SkillsTree"
},
"worker": {
"allOf": [
{
"$ref": "#/definitions/Worker"
}
],
"description": "Same shape as `directory::registry::workers::list` rows (and the engine's `engine::workers::list` rows for the shared core fields)."
}
},
"required": [
"api_reference",
"skills_tree",
"worker"
],
"title": "WorkerInfoOutput",
"type": "object"
}
},
{
"description": "List workers from the public registry, optionally filtered by fuzzy `search` (default order: downloads). Cursor-paginated: pass back `pagination.next_cursor` as `cursor`.",
"metadata": {},
"name": "directory::registry::workers::list",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "`directory::registry::workers::list` input. Mirrors the engine's `engine::workers::list` search input so callers can switch between local and registry surfaces without re-learning the API. Adds `cursor` for paging because the registry is paged (server-authored page size — the client cannot override it).",
"properties": {
"cursor": {
"default": null,
"description": "Cursor from a previous call's `pagination.next_cursor`; omit for the first page.",
"type": [
"string",
"null"
]
},
"search": {
"default": null,
"description": "Optional free-text query, fuzzy-matched by the registry; omitted means ordered by downloads.",
"type": [
"string",
"null"
]
}
},
"title": "WorkerListInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"Dependency": {
"description": "Worker dependency entry. Mirrors the `Dependency` schema in `openapi.yaml`.",
"properties": {
"name": {
"type": "string"
},
"version": {
"type": "string"
}
},
"required": [
"name",
"version"
],
"type": "object"
},
"Pagination": {
"description": "Pagination envelope returned alongside a worker-list page. Mirrors the OpenAPI `Pagination` schema.",
"properties": {
"has_more": {
"default": false,
"type": "boolean"
},
"next_cursor": {
"default": null,
"description": "Opaque cursor for the next page. `null` on the last page.",
"type": [
"string",
"null"
]
},
"page_size": {
"default": 0,
"description": "Server-authored page size. The client cannot override this.",
"format": "uint32",
"minimum": 0,
"type": "integer"
}
},
"type": "object"
},
"Worker": {
"description": "Shared worker envelope used by both `directory::registry::workers::list` rows and the `worker` field of `directory::registry::workers::info`. Field names match the OpenAPI `WorkerListItem` schema. The shared core fields (`name`, `description`, `version`) line up with the engine's `engine::workers::list` row shape so callers learn one envelope across local + registry surfaces.",
"properties": {
"author": {
"anyOf": [
{
"$ref": "#/definitions/WorkerAuthor"
},
{
"type": "null"
}
],
"default": null
},
"config": {
"default": {},
"description": "Free-form runtime configuration block from the publish payload."
},
"dependencies": {
"default": [],
"items": {
"$ref": "#/definitions/Dependency"
},
"type": "array"
},
"description": {
"default": null,
"type": [
"string",
"null"
]
},
"image": {
"description": "Container image tag, populated only for `type=image` workers.",
"type": [
"string",
"null"
]
},
"name": {
"type": "string"
},
"repo": {
"default": null,
"type": [
"string",
"null"
]
},
"supported_targets": {
"default": [],
"items": {
"type": "string"
},
"type": "array"
},
"total_downloads": {
"default": 0,
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"type": {
"default": null,
"description": "Worker kind — `binary`, `image`, or `engine`.",
"type": [
"string",
"null"
]
},
"version": {
"default": null,
"description": "Latest published version (worker-list) or the resolved version (worker-info, when called with `version` / `tag`).",
"type": [
"string",
"null"
]
}
},
"required": [
"name"
],
"type": "object"
},
"WorkerAuthor": {
"description": "Author block for a published worker. Field names match the `WorkerAuthor` schema in `openapi.yaml` (`pfp`, `verified`).",
"properties": {
"name": {
"type": [
"string",
"null"
]
},
"pfp": {
"default": null,
"description": "Profile picture URL. `null` when the author hasn't uploaded one.",
"type": [
"string",
"null"
]
},
"verified": {
"default": false,
"type": "boolean"
}
},
"type": "object"
}
},
"properties": {
"pagination": {
"$ref": "#/definitions/Pagination"
},
"workers": {
"items": {
"$ref": "#/definitions/Worker"
},
"type": "array"
}
},
"required": [
"pagination",
"workers"
],
"title": "WorkerListOutput",
"type": "object"
}
},
{
"description": "Search available functions for the unmet external capabilities of a step (usually one to six, at most eighteen per call); returns compact function-id candidates grouped by worker.",
"metadata": {},
"name": "directory::search_functions",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"capabilities": {
"description": "Non-empty capability searches derived from the goal and current execution state, usually one to six and at most eighteen per call (searched in batches of six). For one search at each decision point, include all unmet external capabilities once. Exclude intrinsic reasoning, summarization, planning, or formatting, and do not repeat needs already represented or satisfied. Requests to summarize provided text or content are ignored. Write every entry in English, translating non-English user requests while preserving proper names, URLs, and function IDs.",
"items": {
"minLength": 1,
"type": "string"
},
"minItems": 1,
"type": "array",
"uniqueItems": true
}
},
"required": [
"capabilities"
],
"title": "SearchFunctionsRequest",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"FunctionCandidate": {
"properties": {
"description": {
"description": "First description sentence, capped at 160 bytes.",
"type": "string"
},
"function_id": {
"type": "string"
}
},
"required": [
"description",
"function_id"
],
"type": "object"
},
"InstallCall": {
"description": "A ready-made `compose::add` target and payload. Under agent-trigger exposure, the caller still supplies the wrapper's user-facing `description`.",
"properties": {
"function": {
"type": "string"
},
"payload": true
},
"required": [
"function",
"payload"
],
"type": "object"
},
"InstallableWorker": {
"description": "A registry worker that is NOT installed but carries functions matching the requested capabilities. `name` is the registry slug `compose::add` installs.",
"properties": {
"description": {
"type": "string"
},
"functions": {
"description": "Compact candidates only. If the remaining task needs these functions, reuse their IDs and fetch the required contracts through `engine::functions::info`.",
"items": {
"$ref": "#/definitions/FunctionCandidate"
},
"type": "array"
},
"install": {
"allOf": [
{
"$ref": "#/definitions/InstallCall"
}
],
"description": "The `compose::add` target and payload; agent-trigger callers add `description`."
},
"name": {
"type": "string"
},
"version": {
"type": "string"
}
},
"required": [
"description",
"functions",
"install",
"name",
"version"
],
"type": "object"
},
"SearchWorker": {
"properties": {
"functions": {
"items": {
"$ref": "#/definitions/FunctionCandidate"
},
"type": "array"
},
"namespace": {
"type": "string"
}
},
"required": [
"functions",
"namespace"
],
"type": "object"
}
},
"properties": {
"guidance": {
"type": "string"
},
"installable": {
"description": "Matching workers from the private registry. Their functions are NOT callable until the worker is installed.",
"items": {
"$ref": "#/definitions/InstallableWorker"
},
"type": "array"
},
"latency_ms": {
"format": "double",
"type": "number"
},
"workers": {
"items": {
"$ref": "#/definitions/SearchWorker"
},
"type": "array"
}
},
"required": [
"guidance",
"installable",
"latency_ms",
"workers"
],
"title": "SearchFunctionsResponse",
"type": "object"
}
},
{
"description": "Create a new skill at <skills_folder>/<id>.md from full-file markdown (frontmatter optional, non-empty body). Rejects ids or paths that already exist, including system-installed skills. Use directory::skills::update to edit existing skills.",
"metadata": {
"tool": {
"label": "Create skill"
}
},
"name": "directory::skills::create",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"content": {
"description": "Full file content, frontmatter optional; only the size cap and a non-empty body are enforced.",
"type": "string"
},
"id": {
"description": "New skill id, used as the file path under skills_folder (`/`-separated segments of `[a-z0-9_-]`), not already taken.",
"type": "string"
}
},
"required": [
"content",
"id"
],
"title": "SkillCreateInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"bytes": {
"description": "Bytes written.",
"format": "uint",
"minimum": 0,
"type": "integer"
},
"function_id": {
"description": "Frontmatter `function_id:` of the content, `null` when absent.",
"type": [
"string",
"null"
]
},
"id": {
"description": "The created skill's id (normalized form of the input id).",
"type": "string"
},
"modified_at": {
"description": "File mtime after the write, RFC 3339.",
"type": "string"
},
"title": {
"description": "Title resolved from the content (frontmatter `title:`, then `name:`, then body H1, then the id) — what `list` rows will show.",
"type": "string"
},
"type": {
"description": "Frontmatter `type:` of the content, `null` when absent.",
"type": [
"string",
"null"
]
}
},
"required": [
"bytes",
"id",
"modified_at",
"title"
],
"title": "SkillCreateOutput",
"type": "object"
}
},
{
"description": "Delete one existing skill's markdown file by id (same id forms as directory::skills::get); refuses read-only system-installed skills.",
"metadata": {
"tool": {
"label": "Delete skill"
}
},
"name": "directory::skills::delete",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"description": "Existing skill id — the same forms `directory::skills::get` accepts (bare id, `<id>.md`, `SKILL(S).md`, `iii://<id>`).",
"type": "string"
}
},
"required": [
"id"
],
"title": "SkillDeleteInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"description": "Id of the skill whose file was removed — the RESOLVED on-disk id (e.g. `ns/index` for input `ns`), not the input form.",
"type": "string"
}
},
"required": [
"id"
],
"title": "SkillDeleteOutput",
"type": "object"
}
},
{
"description": "Download skills into skills_folder from exactly one source: {repo, skill, branch?} clones a GitHub skill folder; {worker, version?|tag?} pulls from the workers registry. Prefer the explicit download_from_registry / download_from_repo.",
"metadata": {
"tool": {
"label": "Download skills"
}
},
"name": "directory::skills::download",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"branch": {
"default": null,
"description": "Source A: branch to clone. Defaults to `\"main\"`. Pass `\"master\"` (or any other branch name) for repos whose default branch is not `main`.",
"type": [
"string",
"null"
]
},
"repo": {
"default": null,
"description": "Source A: GitHub repo URL. Pair with `skill`.",
"type": [
"string",
"null"
]
},
"skill": {
"default": null,
"description": "Source A: subfolder under `skills/` inside the repo. Doubles as the destination namespace inside `skills_folder`.",
"type": [
"string",
"null"
]
},
"tag": {
"default": null,
"description": "Registry tag to pull (default `latest`); mutually exclusive with `version`.",
"type": [
"string",
"null"
]
},
"version": {
"default": null,
"description": "Source B: explicit semver to pull. Mutually exclusive with `tag`.",
"type": [
"string",
"null"
]
},
"worker": {
"default": null,
"description": "Source B: workers registry name. Pair with exactly one of `version` / `tag`.",
"type": [
"string",
"null"
]
}
},
"title": "DownloadInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"agents_written": {
"items": {
"type": "string"
},
"type": "array"
},
"namespace": {
"type": "string"
},
"skills_written": {
"items": {
"type": "string"
},
"type": "array"
},
"source": true,
"system_prompts_written": {
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"agents_written",
"namespace",
"skills_written",
"source",
"system_prompts_written"
],
"title": "DownloadOutput",
"type": "object"
}
},
{
"description": "Download one worker's directory bundle from the workers registry into skills_folder. `worker` is required; pass `version` (exact semver) or `tag` (default \"latest\"), not both. Files are overwritten file-by-file.",
"metadata": {
"tool": {
"label": "Download skills (registry)"
}
},
"name": "directory::skills::download_from_registry",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Input for `directory::skills::download_from_registry`. The required `worker` field is what makes this function's source unambiguous at the schema level.",
"properties": {
"tag": {
"default": null,
"description": "Registry tag to pull (e.g. `\"latest\"`). Mutually exclusive with `version`. Defaults to `\"latest\"` when neither is provided.",
"type": [
"string",
"null"
]
},
"version": {
"default": null,
"description": "Explicit semver to pull. Mutually exclusive with `tag`.",
"type": [
"string",
"null"
]
},
"worker": {
"description": "Worker name in the registry (e.g. `\"shell\"`).",
"type": "string"
}
},
"required": [
"worker"
],
"title": "RegistryDownloadInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"agents_written": {
"items": {
"type": "string"
},
"type": "array"
},
"namespace": {
"type": "string"
},
"skills_written": {
"items": {
"type": "string"
},
"type": "array"
},
"source": true,
"system_prompts_written": {
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"agents_written",
"namespace",
"skills_written",
"source",
"system_prompts_written"
],
"title": "DownloadOutput",
"type": "object"
}
},
{
"description": "Download one skill folder from a GitHub repo into skills_folder: `repo` (https/ssh/git@ URL) and `skill` (subfolder under `skills/`, also the destination namespace) are required; `branch` defaults to \"main\".",
"metadata": {
"tool": {
"label": "Download skills (repo)"
}
},
"name": "directory::skills::download_from_repo",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Input for `directory::skills::download_from_repo`. The required `repo` + `skill` fields make this function's source unambiguous at the schema level.",
"properties": {
"branch": {
"default": null,
"description": "Branch to clone. Defaults to `\"main\"`.",
"type": [
"string",
"null"
]
},
"repo": {
"description": "GitHub repo URL (validated: https / ssh / git@ only).",
"type": "string"
},
"skill": {
"description": "Subfolder under `skills/` inside the repo. Doubles as the destination namespace inside `skills_folder`.",
"type": "string"
}
},
"required": [
"repo",
"skill"
],
"title": "RepoDownloadInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"agents_written": {
"items": {
"type": "string"
},
"type": "array"
},
"namespace": {
"type": "string"
},
"skills_written": {
"items": {
"type": "string"
},
"type": "array"
},
"source": true,
"system_prompts_written": {
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"agents_written",
"namespace",
"skills_written",
"source",
"system_prompts_written"
],
"title": "DownloadOutput",
"type": "object"
}
},
{
"description": "Fetch one skill by id and return its raw markdown body plus id, title, type, function_id, and modified_at. A worker overview is addressed by the bare worker name; `<id>.md` and `iii://<id>` forms are accepted. On a miss, D110 names the closest ids.",
"metadata": {
"tool": {
"label": "Get skill"
}
},
"name": "directory::skills::get",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"description": "Skill id as returned by directory::skills::list (e.g. `directory/skills/list`); `<id>.md` and `iii://<id>` forms are accepted.",
"type": "string"
},
"raw": {
"default": null,
"description": "When true, also return the exact on-disk file (frontmatter included) as `raw`, ready for directory::skills::update.",
"type": [
"boolean",
"null"
]
}
},
"required": [
"id"
],
"title": "SkillGetInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"body": {
"description": "Raw markdown body (post-frontmatter) from disk.\n\nNote: there is no `description` field. `description` is the body's first paragraph, which is already inside `body` — every caller asking for the body would otherwise pay for the prefix twice. Use `directory::skills::list` rows when you want the teaser without the full body.",
"type": "string"
},
"disable_model_invocation": {
"description": "Whether model-facing indexes should omit this skill from invocation candidates.",
"type": "boolean"
},
"function_id": {
"description": "Frontmatter `function_id:` when present — the canonical bus function id this skill documents (e.g. `sandbox::create`). The response's `id` field is the SKILL path on disk; `function_id` is what the agent should pass to `agent_trigger`. `null` when the skill isn't 1:1 with a single function.",
"type": [
"string",
"null"
]
},
"id": {
"type": "string"
},
"modified_at": {
"description": "File mtime as RFC 3339.",
"type": "string"
},
"path": {
"description": "Absolute on-disk path of the skill file. Its parent directory is the skill's base directory — where payload the body references by relative path (`scripts/`, `reference/`, agent-skills convention) lives. Only meaningful to callers sharing this worker's filesystem (shell/file tools on the same machine).",
"type": "string"
},
"raw": {
"description": "FULL on-disk file content (frontmatter block included). Present only when the request set `raw: true`. This is the exact string to hand back to `directory::skills::update`; fallback notes that `get` may prepend to `body` are never added here.",
"type": [
"string",
"null"
]
},
"title": {
"description": "Frontmatter `title:` when present and non-empty, otherwise the first `# H1` line in the body, otherwise the bare `id`.",
"type": "string"
},
"type": {
"description": "Frontmatter `type:` (e.g. `index`, `how-to`, `reference`). `null` when the file has no frontmatter or omits the key.",
"type": [
"string",
"null"
]
}
},
"required": [
"body",
"disable_model_invocation",
"id",
"modified_at",
"path",
"title"
],
"title": "SkillGetOutput",
"type": "object"
}
},
{
"description": "Read a per-worker overview: one markdown block per installed worker (title, first paragraph, and the directory::skills::get call for the reference). For per-skill rows use directory::skills::list.",
"metadata": {},
"name": "directory::skills::index",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "IndexSkillsInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"body": {
"description": "Rendered markdown document — one short `## <title>` block per installed worker (each worker's root overview doc, whether or not it declares frontmatter `type: index`), carrying the worker's first-paragraph overview and a `directory::skills::get` call to read the full reference. Sorted lex by id.",
"type": "string"
},
"workers_count": {
"description": "Number of worker entries rendered (i.e. the count of worker overview rows that survived the filter). Cheap sanity check that doesn't require re-parsing the body.",
"format": "uint",
"minimum": 0,
"type": "integer"
}
},
"required": [
"body",
"workers_count"
],
"title": "IndexSkillsOutput",
"type": "object"
}
},
{
"description": "List skills, one row per skill (id, title, type, function_id, description, bytes, modified_at). Filters: `search` (substring on id/title/description), `prefix` (worker namespace), `type`; `include_description: false` for lighter rows. Pass a row's `function_id`, not its `id`, to agent_trigger.",
"metadata": {},
"name": "directory::skills::list",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"include_description": {
"default": null,
"description": "When `false`, the response omits the first-paragraph `description` field on every row. Useful for token-light pickers that only need `id` + `title` + `type`. Default `true`.",
"type": [
"boolean",
"null"
]
},
"prefix": {
"default": null,
"description": "Exact prefix match against `id`. Combine with `search` to scope a fuzzy match to one worker namespace, e.g. `prefix: \"sandbox/\"`.",
"type": [
"string",
"null"
]
},
"search": {
"default": null,
"description": "Case-insensitive substring match against `id`, `title`, and (when `include_description` is true) the first body paragraph. Omitted rows are filtered out cheaply on the FsSkill { id } pass before the per-file frontmatter read, so a narrowed list is dramatically cheaper for the caller than the unfiltered one.",
"type": [
"string",
"null"
]
},
"type": {
"default": null,
"description": "Exact match against the frontmatter `type:` field (`index`, `how-to`, `reference`, ...). `null` for entries with no frontmatter `type:`.",
"type": [
"string",
"null"
]
}
},
"title": "ListSkillsInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"SkillEntry": {
"properties": {
"bytes": {
"format": "uint",
"minimum": 0,
"type": "integer"
},
"description": {
"description": "First paragraph of the body, empty when the file has only headings. Also empty when the caller passed `list { include_description: false }` for a token-light row.",
"type": "string"
},
"disable_model_invocation": {
"description": "Whether model-facing indexes should omit this skill from invocation candidates.",
"type": "boolean"
},
"function_id": {
"description": "Frontmatter `function_id:` when present — the canonical bus function id this skill documents (e.g. `sandbox::create`). The row's `id` field is the SKILL path on disk (e.g. `sandbox/skills/sandbox/create`); `function_id` is what an agent should pass to `agent_trigger`. `null` for skills that aren't 1:1 with a single function (index/reference).",
"type": [
"string",
"null"
]
},
"id": {
"type": "string"
},
"modified_at": {
"description": "File mtime as RFC 3339 (best effort; empty if unavailable).",
"type": "string"
},
"title": {
"description": "Frontmatter `title:` when present and non-empty, otherwise the first `# H1` line in the body, otherwise the bare `id`.",
"type": "string"
},
"type": {
"description": "Frontmatter `type:` (e.g. `index`, `how-to`, `reference`). `null` when the file has no frontmatter or omits the key.",
"type": [
"string",
"null"
]
}
},
"required": [
"bytes",
"description",
"disable_model_invocation",
"id",
"modified_at",
"title"
],
"type": "object"
}
},
"properties": {
"skills": {
"items": {
"$ref": "#/definitions/SkillEntry"
},
"type": "array"
}
},
"required": [
"skills"
],
"title": "ListSkillsOutput",
"type": "object"
}
},
{
"description": "Overwrite one existing skill with full-file markdown (pass back the `raw` from directory::skills::get { raw: true }, edited). Never creates files; refuses read-only system-installed skills.",
"metadata": {
"tool": {
"label": "Update skill"
}
},
"name": "directory::skills::update",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"content": {
"description": "FULL new file content, frontmatter block included — the string `directory::skills::get { raw: true }` returns, edited.",
"type": "string"
},
"id": {
"description": "Skill id to overwrite (same forms directory::skills::get accepts); the file must already exist.",
"type": "string"
}
},
"required": [
"content",
"id"
],
"title": "SkillUpdateInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"bytes": {
"description": "Bytes written.",
"format": "uint",
"minimum": 0,
"type": "integer"
},
"function_id": {
"description": "Frontmatter `function_id:` of the new content, `null` when absent.",
"type": [
"string",
"null"
]
},
"id": {
"description": "The id that was updated (normalized form of the input id).",
"type": "string"
},
"modified_at": {
"description": "File mtime after the write, RFC 3339.",
"type": "string"
},
"title": {
"description": "Title resolved from the NEW content (frontmatter `title:`, then body H1, then the id) — what `list` rows will now show.",
"type": "string"
},
"type": {
"description": "Frontmatter `type:` of the new content, `null` when absent.",
"type": [
"string",
"null"
]
}
},
"required": [
"bytes",
"id",
"modified_at",
"title"
],
"title": "SkillUpdateOutput",
"type": "object"
}
},
{
"description": "Create a new system prompt at <skills_folder>/system-prompts/<name>.md from full-file markdown (non-empty frontmatter `description` required; a declared `name` must match). Rejects names or paths that already exist.",
"metadata": {
"tool": {
"label": "Create system prompt"
}
},
"name": "directory::system-prompts::create",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"content": {
"description": "Full file content, frontmatter included; `description` is required and a declared `name` must match.",
"type": "string"
},
"name": {
"description": "New system prompt name, used as the file stem; same charset as listed names and not already taken.",
"type": "string"
}
},
"required": [
"content",
"name"
],
"title": "SystemPromptCreateInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"bytes": {
"description": "Bytes written.",
"format": "uint",
"minimum": 0,
"type": "integer"
},
"description": {
"description": "Description parsed from the frontmatter.",
"type": "string"
},
"modified_at": {
"description": "File mtime after the write, RFC 3339.",
"type": "string"
},
"name": {
"description": "The created system prompt's name (as requested).",
"type": "string"
}
},
"required": [
"bytes",
"description",
"modified_at",
"name"
],
"title": "SystemPromptCreateOutput",
"type": "object"
}
},
{
"description": "Permanently delete one EXISTING filesystem-backed system prompt by name. Resolves against the same merged scan as directory::system-prompts::list, removes only that prompt's markdown file, and fans out directory::system-prompts::on-change with { op: \"delete\" }.",
"metadata": {
"tool": {
"label": "Delete system prompt"
}
},
"name": "directory::system-prompts::delete",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"name": {
"description": "Existing system prompt name, as returned by `directory::system-prompts::list`.",
"type": "string"
}
},
"required": [
"name"
],
"title": "SystemPromptDeleteInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"name": {
"description": "Name of the system prompt whose file was removed.",
"type": "string"
}
},
"required": [
"name"
],
"title": "SystemPromptDeleteOutput",
"type": "object"
}
},
{
"description": "Fetch one system prompt by name — a filesystem-backed entry, or a worker-bundled one (`builtin: true`) when no local file shadows it. Returns the raw markdown body plus name, description, and modified_at — no envelope, no templating.",
"metadata": {},
"name": "directory::system-prompts::get",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"name": {
"type": "string"
},
"raw": {
"default": null,
"description": "When `true`, the response includes the full on-disk file content (frontmatter included) as `raw`, ready for `directory::system-prompts::update`.",
"type": [
"boolean",
"null"
]
}
},
"required": [
"name"
],
"title": "SystemPromptGetInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"body": {
"type": "string"
},
"builtin": {
"description": "Served from the copy bundled with the worker (no local file yet): an update creates the local file.",
"type": "boolean"
},
"description": {
"type": "string"
},
"modified_at": {
"type": "string"
},
"name": {
"type": "string"
},
"raw": {
"type": [
"string",
"null"
]
}
},
"required": [
"body",
"builtin",
"description",
"modified_at",
"name"
],
"title": "SystemPromptGetOutput",
"type": "object"
}
},
{
"description": "List system prompts (name, description, modified_at) from skills_folder's `system-prompts/` plus the ones bundled with this worker (`builtin: true` until a local file shadows one).",
"metadata": {},
"name": "directory::system-prompts::list",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "ListSystemPromptsInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"SystemPromptEntry": {
"properties": {
"builtin": {
"description": "Bundled with the worker, no file behind it: editing it creates the local file (which then shadows this entry); there is nothing to delete.",
"type": "boolean"
},
"description": {
"type": "string"
},
"modified_at": {
"type": "string"
},
"name": {
"type": "string"
}
},
"required": [
"builtin",
"description",
"modified_at",
"name"
],
"type": "object"
}
},
"properties": {
"prompts": {
"items": {
"$ref": "#/definitions/SystemPromptEntry"
},
"type": "array"
}
},
"required": [
"prompts"
],
"title": "ListSystemPromptsOutput",
"type": "object"
}
},
{
"description": "Overwrite one existing system prompt with full-file markdown; the frontmatter must keep a non-empty `description`. Updating a bundled prompt (`builtin: true`) creates a local file that shadows it. Returns the effective name (frontmatter `name:` wins over the file stem).",
"metadata": {
"tool": {
"label": "Update system prompt"
}
},
"name": "directory::system-prompts::update",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"content": {
"description": "Full file content, frontmatter included; `description` must stay non-empty.",
"type": "string"
},
"name": {
"description": "System prompt name to overwrite, as listed; a bundled prompt (`builtin: true`) is copied to a local file first.",
"type": "string"
}
},
"required": [
"content",
"name"
],
"title": "SystemPromptUpdateInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"bytes": {
"description": "Bytes written.",
"format": "uint",
"minimum": 0,
"type": "integer"
},
"description": {
"description": "Description parsed from the new frontmatter.",
"type": "string"
},
"modified_at": {
"description": "File mtime after the write, RFC 3339.",
"type": "string"
},
"name": {
"description": "The system prompt's EFFECTIVE name after the write: the new frontmatter `name:` when declared, otherwise the file stem. Differs from the input name when the update renames the system prompt.",
"type": "string"
}
},
"required": [
"bytes",
"description",
"modified_at",
"name"
],
"title": "SystemPromptUpdateOutput",
"type": "object"
}
},
{
"description": "Serve the iii-directory worker's injected console UI assets (content function for its console:script / console:style triggers).",
"metadata": {
"internal": true
},
"name": "iii-directory::ui-content",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Input of the content function: the console asks for one asset by path.",
"properties": {
"path": {
"description": "The asset path from the trigger config (e.g. `state/page.js`).",
"type": "string"
}
},
"required": [
"path"
],
"title": "UiContentInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Output of the content function.",
"properties": {
"content": {
"description": "The asset source, verbatim.",
"type": "string"
},
"content_type": {
"description": "MIME type the console should serve the asset with.",
"type": "string"
}
},
"required": [
"content",
"content_type"
],
"title": "UiContentResult",
"type": "object"
}
}
],
"triggers": [
{
"description": "Fires after a directory::skills::download that wrote at least one agent profile, or a directory::agents::update, create, or delete. Also fires with { op: \"external\" } when a watched agents file changes on disk outside this worker.",
"invocation_schema": {},
"metadata": {},
"name": "directory::agents::on-change",
"return_schema": {}
},
{
"description": "Fires after a directory::skills::download that wrote at least one skill markdown file, or a directory::skills::update, create, or delete. Also fires with { op: \"external\" } when a watched skills root changes on disk outside this worker — including the read-only agents skills root, when that root exists at startup.",
"invocation_schema": {},
"metadata": {},
"name": "directory::skills::on-change",
"return_schema": {}
},
{
"description": "Fires after a directory::skills::download that wrote at least one system prompt, or a directory::system-prompts::update, create, or delete. Also fires with { op: \"external\" } when a watched system-prompts root changes on disk outside this worker.",
"invocation_schema": {},
"metadata": {},
"name": "directory::system-prompts::on-change",
"return_schema": {}
}
]
}