菜单
Safely delete, deprecate, or archive an existing Agent Skill. Use when the user asks to remove, delete, retire, uninstall, or archive a skill, when a skill is superseded, obsolete, or abandoned, or when cleaning up unused skills.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
User-invoked pass that re-derives a project's Claude-native instruction layout — a surface AGENTS.md plus path-scoped .claude/rules/ — as a projection of the installed skill set and the actual codebase. Enumerates every available skill, maps which applies to which path (wiring unwired-but-needed ones, dropping inapplicable ones), grounds every claim against the code, discloses only non-code-recoverable info per path, and drops the inert references/ layer. Read-only toward user-owned notes (roadmaps, scratchpads) — it reports promotion candidates, never rewrites them. Invoke as /meta-dev:revise-agents-md.
Bootstrap a project's instruction files from scratch — a surface AGENTS.md plus path-scoped .claude/rules/ derived from the installed skills and the actual code. Use when the user asks to set up CLAUDE.md/AGENTS.md, bootstrap instruction files or project memory, or initialize the layout for a repo that has none. Not for editing an existing layout's content (update-instructions), tightening one already in place (improve-instructions), or re-deriving the whole layout of a repo that already has one (revise-agents-md).
Raise the quality of a project's instruction files (CLAUDE.md, AGENTS.md, references) WITHOUT changing what they commit to. Use when the user asks to clean up, debloat, or tighten CLAUDE.md or AGENTS.md, audit instruction files, or says their constitution is bloated, messy, or hard to read. Fact or guard changes belong to update-instructions; first-time bootstrap belongs to setup-instructions.
Raise an existing skill's quality against a measurable criterion WITHOUT changing its intended behavior. Use when the user asks to debloat, tighten, shorten, or clean up a skill, fix its formatting or wording, rewrite a description already diagnosed as under-triggering (diagnosing why belongs to review-skill), or run the automated description-optimization loop. Behavior changes belong to update-skill; skills over their size budget belong to restructure-skill.
Reorganize skill architecture — split one skill into several, merge overlapping skills, or move content between SKILL.md, references, and scripts. Use when a skill exceeds its size budgets, when skills overlap or their descriptions collide, when content sits at the wrong loading level, or when the user asks to split, merge, rename, or reorganize skills. Content edits within one healthy skill belong to update-skill or improve-skill.
Read-only audit of a project's instruction files (AGENTS.md, CLAUDE.md, .claude/rules) — never edits them. Use to review, check, audit, or diagnose instruction files, verify every documented claim against the actual codebase, find stale or wrong facts, spot cross-file contradictions or bloat, or get a quality report before deciding what to change. Not for applying fixes (update-instructions / improve-instructions) or first-time bootstrap (setup-instructions).
| name | retire-skill |
| description | Safely delete, deprecate, or archive an existing Agent Skill. Use when the user asks to remove, delete, retire, uninstall, or archive a skill, when a skill is superseded, obsolete, or abandoned, or when cleaning up unused skills. |
| model | sonnet |
Deletion is cheap; safe deletion means knowing nothing still points at the thing. This whole pipeline is a scan, a snapshot, and an rm — seconds, not a project. It exists because the two real risks are dangling references (a hook or skill that still names the deleted skill) and regret (no way back).
~/.claude/skills/ or .claude/skills/) → this pipeline.claude plugin disable <plugin> / the enabledPlugins setting, or hide a bundled skill via skillOverrides. Report which and stop here.~/.agents/skills/) → removing the symlink unregisters it from Claude Code; the target survives. Say so and confirm which side to remove.Search for the skill's name before removing it:
grep -rl "<skill-name>" ~/.claude/hooks/ ~/.claude/settings.json ~/.claude/settings.local.json \
~/.claude/CLAUDE.md ~/.claude/skills/ ~/.claude/agents/ ~/.claude/commands/ .claude/ \
2>/dev/null | grep -v "skills/<skill-name>/"
For every hit, record a disposition: edit it (reference must be removed/repointed — do that first, respecting that hook/settings edits gate on their own rules), ignore it (historical mention), or blocker (something active depends on the skill — stop and tell the user).
Completion criterion: every hit outside the skill's own folder has an explicit disposition; no unresolved blockers.
mkdir -p ~/.claude/skill-archive && cp -r <skill-path> ~/.claude/skill-archive/<name>-$(date +%Y%m%d)/.Completion criterion: a restorable copy exists and its location is recorded.
rm -rf <skill-path> (or rm the symlink).One short message: what was removed, where the archive lives, every cross-reference edited or flagged, and anything the user should do next (e.g. a hook still mentioning the skill by name in a deny message).