跳到正文
cccskills
免费在 GitHub 公开

docs-checker

Audit context files (CLAUDE.md, .claude/ tree, READMEs, docs) for broken references and verifiably stale content. Runs a deterministic offline link/path checker first, then a bounded semantic review where every finding must cite evidence. Reports findings; fixes only on request. Use when the user says "docs check", "/docs-checker", "check the docs for stale content", "audit CLAUDE.md", or when a scheduled cloud routine fires.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md3.7 KB
  • scripts/docs-check.mjs19.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Docs Checker

Audit the repository's context files — CLAUDE.md at any depth, the .claude/ tree (skills, rules, commands), READMEs, and the docs tree — for correctness. This is a conservative audit: report findings with evidence, do not rewrite anything unless the user asks. Style, tone, and level of detail are the author's choices and are out of scope.

Prerequisites

  • Node.js >= 22 (the bundled script uses fs.globSync)

Workflow

1. Deterministic pass

Run the bundled checker from the repo root:

node ${CLAUDE_SKILL_DIR}/scripts/docs-check.mjs $ARGUMENTS

It needs no config and no dependencies. What it does:

  • Checks relative/absolute markdown links and image assets against the working tree
  • Checks backticked source paths in prose (src/foo.ts, @alias/bar) against the codebase, resolving tsconfig/package.json aliases
  • Scans the paths you name (or the repo's docs tree by default), plus every CLAUDE.md and the whole .claude/ tree automatically
  • Cross-repo docs: pass --repo=NAME:DIR for each sibling checkout the docs reference

Exit 0 is clean, 1 means findings (printed as line:col rule message with did-you-mean hints), 2 is bad invocation. Its findings are ground truth — do not second-guess them.

2. Semantic pass

Read the context files the script scanned — but keep this pass on a scoped diet: CLAUDE.md files, the .claude/ tree, and top-level READMEs. Do not crawl the whole docs tree unless the user asked; the script already covered the wide surface.

Look only for claims you can verify against the repo right now:

  • Commands or scripts quoted in docs that don't exist (check package.json scripts, Makefile, bundled scripts)
  • Described behavior that contradicts the code it points at (read the code before claiming this)
  • Instructions that contradict each other across context files
  • Sections duplicated between files (e.g. README and CLAUDE.md drifting apart)
  • References to tools, versions, or structures the repo no longer uses

Rules that keep this pass honest:

  • Every finding must cite its evidence — the file and line that proves the claim stale. If you cannot point at proof, it is not a finding.
  • No style or wording opinions. "Could be clearer" is not a finding.
  • When unsure whether something is stale or intentional, list it under "unverified" rather than asserting it.

3. Report

Present one combined report:

  1. Deterministic findings — the script output, summarized by file
  2. Semantic findings — each as: claim, evidence (file:line on both sides), suggested resolution
  3. Unverified observations — only if any; clearly separated

End with the totals. Do not edit any file. If findings exist, offer to fix them — deterministic findings (broken links, moved paths) are safe to fix mechanically once the user agrees; semantic findings need the user to decide the correct current truth first.

Suppressions

The script honors inline suppressions the user may already have in place:

  • <!-- docs-check-ignore --> at the end of a line
  • <!-- docs-check-disable --> … <!-- docs-check-enable --> around a region
  • --no-agent-docs flag to skip CLAUDE.md/.claude/ scanning

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Structure AI work artifacts under .aiwork/{YYYY-MM-DD}_{slug}/ folders using the project's protocol (intent, triage, research, spec, prd, areas, plan, review, notes, docs/). Use when the user asks to plan, capture an intent, make a spec, triage, research a task, write a report, code review, summarize findings, save the work, document decisions, record this, write that down, persist findings, or references any path under .aiwork/. Also use when starting a non-trivial task that needs a plan or spec before implementation, or when finishing one and capturing notes.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月6日 更新

Use this skill when the user asks to test, verify, interact with, or automate web pages and browsers. Trigger for requests involving Chrome automation, browser testing, web scraping, screenshot capture, element selection, or checking web applications. Also trigger when user mentions "browser tools" explicitly.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月6日 更新

changelog

免费

Show recent Claude Code changes personalized to user's setup. Trigger when user asks about changelog, "what's new", "cc changelog", "claude code updates", "recent changes", or wants to know what changed in Claude Code.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月6日 更新

Review code changes from current branch, an Azure DevOps PR, a git ref, or a diff/patch file. Trigger when user says "review this", "code review", "/df:code-review", or provides a PR id/URL, ticket URL, git ref, or diff path. Read-only — never posts comments.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月6日 更新

Review code changes from the current branch, staged changes, a git ref, or a diff/patch file. Pure git-native — no platform/PR awareness. Trigger when user says "review this", "review diff", "/aiwork:code-review-diff", or provides a git ref or diff path. Read-only — never posts comments.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月6日 更新

Czech typography rules for web development. Use when building web pages in Czech language, writing Czech content, or fixing typography issues in Czech text. Covers punctuation, dashes, quotes, numbers, units, non-breaking spaces, and HTML entities.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月6日 更新

查看 lttr 的全部技能

报告此技能的问题