plugin-audit
Diff the Anthropic `claude-plugins-official` marketplace against installed plugins and surface the delta, filtering known-unwanted entries (language LSPs you don't use, SaaS integrations you don't use, sample/demo plugins).
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 1
- Forks
- 1
01 前言 Front Matter
- name
- plugin-audit
- triggers
- [ "audit plugins", "what plugins am I missing", "check anthropic marketplace", "plugin delta" ]
- description
- Diff the Anthropic `claude-plugins-official` marketplace against installed plugins and surface the delta, filtering known-unwanted entries (language LSPs you don't use, SaaS integrations you don't use, sample/demo plugins).
02 资源文件 4
- 脚本core.py2.2 KB
- 参考文档manifest.json1.0 KB
- 参考文档manifest.yaml208 B
- 脚本tests/test_core.py1.4 KB
03 SKILL.md 正文
plugin-audit
Keeps the gap between Anthropic's official marketplace and your installed plugin set visible and actionable, without reinstalling things you already have or surfacing language LSPs you'll never use.
When to run
- Monthly hygiene check.
- After a fresh clone / machine setup, before deep work.
- When a new feature lands in claude-plugins-official (watch its README for changelog hints).
One-liner
bash ~/.claude/skills/plugin-audit/audit.sh
Returns:
- A ranked list of plugins present in the marketplace but not installed, with reason to install / skip.
- A short install plan (exact
claude plugin install <name>@claude-plugins-officialcommands for the recommended set).
Exclusions (tune per user)
Edit audit.sh to maintain the user's skip list. Defaults:
- Language LSPs not in use:
clangd-lsp,csharp-lsp,gopls-lsp,jdtls-lsp,kotlin-lsp,lua-lsp,php-lsp,ruby-lsp,rust-analyzer-lsp,swift-lsp,typescript-lsp(TS LSP often skipped if you already have editor-integrated TS tooling). - SaaS integrations not in use:
asana,imessage,telegram,greptile,firebase,gitlab,discord(plugin — you may run Discord via MCP),laravel-boost,terraform(unless running IaC). - Samples:
example-plugin,fakechat,math-olympiad,playground.
Everything else is surfaced with a (candidate) tag.
Output format
Installed: 30 | Available (post-filter): 8 | Delta: 3
Candidates to install:
- session-report — structured end-of-session report
- hookify — hook authoring assistant
- mcp-server-dev — MCP server build patterns
Install plan:
claude plugin install session-report@claude-plugins-official
claude plugin install hookify@claude-plugins-official
claude plugin install mcp-server-dev@claude-plugins-official
Why this exists
Claude's find-skills skill searches the full ecosystem (90k+ skills) and is great for discovery. plugin-audit is narrower and opinionated: it answers "what should I install from the one marketplace I trust, and skip everything else". The two complement each other.
Related
find-skills— community-wide discoveryskill-creator— authoring new skills once installedskill-maintainer— auditing installed skills (not plugins)
04 同仓库更多 Skills
token-audit
Audit historical Claude Code token usage from JSONL session files — shows total spend, cache hit rates, top costly sessions, weekly trends, and where tokens are going. Run after heavy sessions or weekly to measure optimization impact. Answers how many tokens a session used, how expensive was that session, session cost, and token usage report.
smart-model-route
Auto-classify prompt complexity via Haiku (with heuristic fallback) and inject model routing hints for Agent tool calls. Wired as a UserPromptSubmit hook — fires on every prompt, routes low tasks to Haiku, standard to Sonnet, complex to Sonnet with thorough reasoning, and critical (security/arch/migrations) to Opus. Handles model selection, for example choose model by task complexity.
smart-commands
Decision guide for when to proactively use Claude Code slash commands — /think, /model, /compact, /clear. Use when choosing whether to invoke a command before or during a task, or when a complexity-classifier hook has flagged a task as high or critical. Pairs with the complexity-classifier UserPromptSubmit hook. Answers when to compact, should I switch models, and whether to use extended thinking. Use to pick the right /model command and switch model.
spec-ship
暂无简介
spec-new
Create a committed per-feature spec under `docs/specs/YYYY-MM-DD-<slug>/{spec,tasks}.md` with frontmatter (status, created, owner, pr, tags). Promotes an ephemeral `.claude/plans/<name>.md` into a persistent, searchable artifact. Use when starting a feature that's larger than a one-shot PR.
roadmap-refresh
Regenerate `docs/roadmap.md` for a repo from all specs under `docs/specs/` + their frontmatter (status, tags, pr). Produces Now/Next/Recently-shipped sections. Run after creating / shipping a spec, or at the start of a new session for orientation.