Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
日本語の概要は準備中です。原文の説明を表示しています。
Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed that no longer exist, skills on disk that aren't enrolled, skills whose descriptions have changed since enrollment). Hardens the auto-enrollment pipeline against silent rot.
日本語の概要は準備中です。原文の説明を表示しています。
実行スコア 未検証
インストール方法を見るインストールする前に、エージェントに与えられる指示の中身を確認できます。
Auto-enrollment makes adding skills easy. Easy adds without periodic audits accumulate drift. /caddy-audit is the quarterly hygiene pass that keeps the skill index honest.
/caddy-explain shows surprising results that suggest the index doesn't match realityLoad .claude/skill-index.json into memory. Each entry has at minimum: name, triggers, why.
List every SKILL.md file in skills/<name>/SKILL.md and any project-scope .claude/skills/<name>.md. For each, parse the YAML frontmatter for name and description.
For each skill in the index, check:
name matchesdescription is consistent with the indexed why (the indexed why is usually a tighter summary; flag if they're contradictory)For each SKILL.md file on disk, check:
If the skill files store original triggers in their frontmatter (not all do), compare to the indexed triggers. If the SKILL.md has been edited since enrollment AND its trigger frontmatter has diverged from the index, flag as TRIGGER-STALE.
This step is best-effort; not all skills carry trigger frontmatter, and that's fine.
🔍 Caddy Audit ({date})
Index: {N} entries. Disk: {M} SKILL.md files.
✅ HEALTHY — {K} skills are correctly indexed and on disk.
⚠️ INDEX-ORPHANS ({count}) — in index, no matching SKILL.md:
- /skill-a — last seen at skills/skill-a/SKILL.md (deleted? renamed?)
- /skill-b — never had a file?
⚠️ DISK-ORPHANS ({count}) — SKILL.md exists, not in index:
- skills/new-thing/SKILL.md — run /caddy-enroll skills/new-thing/SKILL.md
- skills/experimental/SKILL.md — never enrolled
⚠️ TRIGGER-STALE ({count}, best-effort) — SKILL.md frontmatter diverges from index:
- /skill-c — SKILL.md has 12 triggers, index has 8
Recommended actions:
1. {1-3 specific commands the principal should run to remediate}
If the principal wants longitudinal data:
# Save to vault/memory/AUDITS/caddy-{YYYY-MM-DD}.md
This becomes a track record over time of how clean the catalog stays. Patterns surface — "we always have 3-5 disk orphans because /skills-builder doesn't always run /caddy-enroll" — which informs whether the auto-enrollment pipeline needs hardening.
skill-index.json. The principal should approve that — even if "obvious," the entry might exist for a reason (e.g., a planned skill not yet implemented)./caddy-enroll for the affected skill. The skill file is canonical.Auto-enrollment plus the natural rate of skill experimentation produces drift. Without periodic auditing, the index slowly diverges from reality:
why linesThe 200ms latency budget means Caddy can't afford to do this checking on every invocation. Hence the quarterly audit pattern.
/caddy-enroll — the skill that adds a SKILL.md to the index (this audit's complement)/caddy-explain — the inspector for individual scoring decisions/caddy-audit is a member; this is the maintenance loop for the catalog itselfまだレビューはありません。使ってみた感想をお寄せください。
ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。
まだコメントはありません。最初のコメントを書いてみませんか。
Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
日本語の概要は準備中です。原文の説明を表示しています。
Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.
日本語の概要は準備中です。原文の説明を表示しています。
Generate a structured delegation brief for any task
日本語の概要は準備中です。原文の説明を表示しています。
When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which trigger matched, what points it earned, what the threshold was, what other skills were close. Pairs with the legibility thesis. Caddy's decisions should be inspectable on demand.
日本語の概要は準備中です。原文の説明を表示しています。
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>".
日本語の概要は準備中です。原文の説明を表示しています。
Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.
日本語の概要は準備中です。原文の説明を表示しています。