caddy-enroll

Estrelas11

Forks3

Atualizado7 de julho de 2026 às 09:09

Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Fonte

wrg32786

wrg32786/aigent-os

Abrir repositório GitHub Ver repositórios do creator

Download

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Outras ocupações de informáticaInformática e Matemática·SOC 15-1299

SKILL.md

readonly

name	caddy-enroll
description	Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".
user-invocable	true

/caddy-enroll

Enroll a skill into Caddy's skill-index.json so prompts matching the skill's triggers surface it as a hint.

When to Use

A new skill was created (often by /skills-builder) and needs to join the index
A skill was copied in from outside (cloned plugin, downloaded skill)
An existing skill's triggers need refreshing after its SKILL.md changed
User says "enroll this skill" / "add this to Caddy" / "update Caddy for /X"

When NOT to Use

The skill is already indexed with correct triggers (check .claude/skill-index.json first)
The skill has no SKILL.md / no description / no clear use case (fix the skill first, enroll after)

Arguments

$1 = path to the skill's SKILL.md or .md file. If omitted, ask which skill.

Protocol

Step 1: Read the target skill

Read the full SKILL.md at the given path. Parse:

name — from the name: frontmatter field, or the filename stem
description — from the description: frontmatter field, or first heading/line

Step 2: Extract structured metadata

Produce this five-field structure:

- what: <one-line what it does>
- triggers: <comma-separated keywords/intents a prompt matcher could catch — 6-12 items, mix multi-word phrases and single keywords>
- use_cases: <3-5 concrete "when user says X, use this">
- anti_cases: <1-3 "do NOT use when...">
- related: <comma-separated related skills from the existing index>

Trigger quality rules:

Multi-word phrases score 3x — prefer them for specific intents
Single words only for unambiguous terms
Avoid stopwords and generic terms ("help", "check", "run", "fix" alone)
Aim for prompts a user would actually type — not jargon from the skill's own docs

Anti-case quality:

Name the sibling skill that SHOULD be used instead
Name any confidentiality or scope boundaries

Step 3: Append to skill-index.json

Read .claude/skill-index.json (relative to AIGENT_ROOT).

If a skill with this name already exists: update its triggers and why — don't clobber triggers the user added manually.

If it's new: append a new entry with {name, triggers, why}.

Validate the file is still valid JSON before writing.

Step 4: Test the enrollment

Run:

echo '{"prompt":"<test prompt that should trigger this skill>"}' | bash $AIGENT_ROOT/daemons/caddy.sh

Confirm the [CADDY] /<name> - <why> hint surfaces. If not, tune the triggers and retry.

Step 5: Confirm

Report:

Skill name and path
Trigger count + short list
Test prompt used + whether it surfaced

Output Format

Enrolled: /<skill-name>
Triggers: <count> (<short list>)
Test: "<prompt>" → [CADDY] /<name> ✓

If the test failed or triggers need work:

Enrolled with warning: triggers need tuning
Test: "<prompt>" → no match
Suggested fix: add trigger "<candidate>"

Why This Exists

Every skill the framework can execute must be enrolled here. Skipping enrollment = skill sits in the golf bag unlabeled. Caddy can't hand it to the AIgent if it's not indexed.

Mais deste repositório

mesmo repositório

context-capsule

wrg32786/aigent-os

The capsule verb, invoked explicitly — reconcile from the live memory, write a resume-ready capsule, then stop. Mid-session checkpoint or completion capsule; a rolling best-effort version of the same write also runs automatically on every Stop event via daemons/stop-capsule-writer.mjs.

2026-07-2511

resume

wrg32786/aigent-os

The resume verb, invoked explicitly — load the newest valid capsule by created_at, re-ground against live memory, then ACT on waiting_on. Mid-session or on explicit ask; the post-clear boot fires the same procedure automatically via daemons/resume-verb.mjs.

2026-07-2511

honesty-check

wrg32786/aigent-os

Run the volunteering ledger before declaring work done. Forces surfacing of what changed/didn't, what was noticed-but-not-fixed, what was guessed, and what tradeoffs were made on the principal's behalf. The standard - the principal should never be surprised later by something the agent knew at the time.

2026-07-2511

trust-decay

wrg32786/aigent-os

Capture a confident agent claim (Phase 1) or resolve one as right/wrong (Phase 2) in vault/memory/TRUST_DECAY.md. Builds the longitudinal record of agent calibration over time. Pairs with /honesty-check (which should reduce Phase 1 frequency) and /diagnose (which surfaces causes that often reveal Phase 2 events).

2026-07-2511

nightly

wrg32786/aigent-os

One evidence-gated pass that sequences /dream, /reconcile, /sweep-now, and /digest over your own vault, with a /system-check gate and a ledger-review pass over the measurement layer (Honesty Ledger, Trust Decay, Failure Modes). Stays exactly as human-gated as the legs it calls -- stages, never auto-applies. Skips a leg gracefully when there is nothing to do; every leg that runs leaves an evidence line.

2026-07-2511

sweep-now

wrg32786/aigent-os

Dispatch Hestia to run all 3 vault sweeps (DELEGATION_TRACKER stale items, HEAT_INDEX dormant flips, broken wikilinks) and append the result to HESTIA_SWEEP_LOG.

2026-07-2511

name	caddy-enroll
description	Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".
user-invocable	true

/caddy-enroll

Enroll a skill into Caddy's skill-index.json so prompts matching the skill's triggers surface it as a hint.

When to Use

A new skill was created (often by /skills-builder) and needs to join the index
A skill was copied in from outside (cloned plugin, downloaded skill)
An existing skill's triggers need refreshing after its SKILL.md changed
User says "enroll this skill" / "add this to Caddy" / "update Caddy for /X"

When NOT to Use

The skill is already indexed with correct triggers (check .claude/skill-index.json first)
The skill has no SKILL.md / no description / no clear use case (fix the skill first, enroll after)

Arguments

$1 = path to the skill's SKILL.md or .md file. If omitted, ask which skill.

Protocol

Step 1: Read the target skill

Read the full SKILL.md at the given path. Parse:

name — from the name: frontmatter field, or the filename stem
description — from the description: frontmatter field, or first heading/line

Step 2: Extract structured metadata

Produce this five-field structure:

- what: <one-line what it does>
- triggers: <comma-separated keywords/intents a prompt matcher could catch — 6-12 items, mix multi-word phrases and single keywords>
- use_cases: <3-5 concrete "when user says X, use this">
- anti_cases: <1-3 "do NOT use when...">
- related: <comma-separated related skills from the existing index>

Trigger quality rules:

Multi-word phrases score 3x — prefer them for specific intents
Single words only for unambiguous terms
Avoid stopwords and generic terms ("help", "check", "run", "fix" alone)
Aim for prompts a user would actually type — not jargon from the skill's own docs

Anti-case quality:

Name the sibling skill that SHOULD be used instead
Name any confidentiality or scope boundaries

Step 3: Append to skill-index.json

Read .claude/skill-index.json (relative to AIGENT_ROOT).

If a skill with this name already exists: update its triggers and why — don't clobber triggers the user added manually.

If it's new: append a new entry with {name, triggers, why}.

Validate the file is still valid JSON before writing.

Step 4: Test the enrollment

Run:

echo '{"prompt":"<test prompt that should trigger this skill>"}' | bash $AIGENT_ROOT/daemons/caddy.sh

Confirm the [CADDY] /<name> - <why> hint surfaces. If not, tune the triggers and retry.

Step 5: Confirm

Report:

Skill name and path
Trigger count + short list
Test prompt used + whether it surfaced

Output Format

Enrolled: /<skill-name>
Triggers: <count> (<short list>)
Test: "<prompt>" → [CADDY] /<name> ✓

If the test failed or triggers need work:

Enrolled with warning: triggers need tuning
Test: "<prompt>" → no match
Suggested fix: add trigger "<candidate>"

Why This Exists

Every skill the framework can execute must be enrolled here. Skipping enrollment = skill sits in the golf bag unlabeled. Caddy can't hand it to the AIgent if it's not indexed.