New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Maintainer Docs Legibility Check

by liaohch3 in liaohch3/claude-tap

Runs local checks on maintainer docs for stale review dates, missing manifest paths and plan state drift, matching what the CI workflow enforces.

MITAuto-check passedDevelopment

Install Maintainer Docs Legibility Check

skills CLI
$ npx skills add liaohch3/claude-tap --skill legibility-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install liaohch3/claude-tap legibility-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/liaohch3/claude-tap.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/legibility-check .claude/skills/legibility-check && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
legibility-check
GitHub stars
3.3k
Token cost
~561 tokens
SKILL.md length
217 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Runs local checks on maintainer docs for stale review dates, missing manifest paths and plan state drift, matching what the CI workflow enforces.

  • Works in 3 steps: Standards freshness — every… → Architecture manifest — every path… → Plan state drift — every…
  • Finishing edits to standards, plans or architecture docs and wanting a check before CI
  • SKILL.md covers What it checks, Run, Fixing common failures and After fixing
  • Calls uv

What it does

After you edit files under .agents/docs/standards, plans or architecture, or AGENTS.md, this skill runs uv run python scripts/check_legibility.py. It has three checks. Each standards file needs frontmatter with an owner, an ISO last_reviewed date and a source_of_truth, and a review older than 60 days gives a warning. Every path under expected_paths in manifest.yaml must exist. Each plan needs a status of active, completed or cancelled, and completed plans may not keep unchecked checkboxes outside code blocks.

The script accepts --freshness-days to change the staleness limit, --strict-freshness to turn stale warnings into failures and --repo-root to point at another checkout. A table maps each failure message to its fix, such as adding a missing frontmatter key, using YYYY-MM-DD dates, creating or removing a manifest entry, or checking off remaining items. You rerun the check until it passes before committing.

When your agent uses it

  • Finishing edits to standards, plans or architecture docs and wanting a check before CI
  • Finding stale last_reviewed dates in maintainer documentation
  • Verifying that every path listed in the architecture manifest still exists

Example prompts

  • “I edited the standards docs, so run the legibility check and fix whatever it flags.”
  • “Run the check with --strict-freshness so stale files fail.”
  • “Which plans are marked completed but still have unchecked boxes?”

Requirements

  • uv and Python
  • The repository's scripts/check_legibility.py

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Standards freshness — every .agents/docs/standards/*.md must have frontmatter with owner, last_reviewed (ISO date), and source_of_truth…
  2. Architecture manifest — every path listed in .agents/docs/architecture/manifest.yaml under expected_paths: must exist in the repo.
  3. Plan state drift — every .agents/docs/plans/**/*.md must have a status frontmatter field (active, completed, or cancelled). Completed…

What it can do on your machine

Read from SKILL.md and the folder at commit e17ed32. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Maintainer Docs Legibility Check loads about 561 tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 217 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~561

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from liaohch3/claude-tap at commit e17ed32, republished under its MIT licence (© liaohch3). 217 words, ~561 tokens.

Download SKILL.mdSave it as .claude/skills/legibility-check/SKILL.md (or your agent's skills folder).
name
legibility-check
description
Validate maintainer docs structure, standards freshness, manifest paths, and plan state. Run this after modifying any file under .agents/docs/standards/, .agents/docs/plans/, .agents/docs/architecture/, or AGENTS.md — it catches stale metadata, broken manifest paths, and plan state drift before CI does.
user_invocable
true

Legibility Check

Run deterministic checks for maintainer docs that mirror what CI enforces via .github/workflows/legibility.yml. Catching these locally saves a round-trip to CI.

What it checks

  1. Standards freshness — every .agents/docs/standards/*.md must have frontmatter with owner, last_reviewed (ISO date), and source_of_truth. Files reviewed more than 60 days ago produce a warning.
  2. Architecture manifest — every path listed in .agents/docs/architecture/manifest.yaml under expected_paths: must exist in the repo.
  3. Plan state drift — every .agents/docs/plans/**/*.md must have a status frontmatter field (active, completed, or cancelled). Completed plans must not contain unchecked - [ ] checkboxes (outside fenced code blocks).

Run

bash
uv run python scripts/check_legibility.py

Options:

  • --freshness-days N — change the staleness threshold (default: 60)
  • --strict-freshness — promote stale warnings to failures
  • --repo-root PATH — override repo root (default: cwd)

Fixing common failures

FailureFix
missing frontmatter key 'X'Add the missing key to the YAML frontmatter block at the top of the file
last_reviewed must be ISO dateUse YYYY-MM-DD format
last_reviewed ... is staleUpdate last_reviewed to today's date after reviewing the content
expected path missing: XEither create the file or remove the stale entry from manifest.yaml
status must be one of [...]Add status: active (or completed/cancelled) to plan frontmatter
completed plan still contains unchecked TODOCheck off remaining items or change status back to active

After fixing

Re-run the check to confirm all issues are resolved before committing:

bash
uv run python scripts/check_legibility.py && echo "All clear"

© liaohch3, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/legibility-check of liaohch3/claude-tap.

Open the folder on GitHubat commit e17ed32

Compare with similar skills

Maintainer Docs Legibility Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Maintainer Docs Legibility Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Maintainer Docs Legibility Check this skillliaohch3/claude-tap3.3k—~561Automated safety check: PassMIT
Module Completeness Checkfengshao1227/ccg-workflow5.9k—~473Automated safety check: NotesMIT
BiSheng SDD Document Reviewdataelement/bisheng12k—~717Automated safety check: PassApache-2.0
GAIA Agent Eval Scorecardamd/gaia1.6k—~2.6kAutomated safety check: PassMIT
Aholo Renderer Package Rulesmanycoretech/aholo-viewer1.1k—~191Automated safety check: PassMIT
Vibe Doc Quality Gateash1794/vibe-engineering163—~653Automated safety check: PassMIT

Similar skills

  • Module Completeness Check

    fengshao1227/ccg-workflow

    Scans a module directory for the required README.md and DESIGN.md plus recommended files and reports what is missing, so a module is not delivered incomplete.

    5.9k GitHub stars~473 tokensUpdated 25 days ago
    DevelopmentAuto-check: notes

  • BiSheng SDD Document Review

    dataelement/bisheng

    Reviews BiSheng spec, design and tasks documents with checklists for PRD gaps, handover readiness and acceptance traceability, producing a report or an LGTM.

    12k GitHub stars~717 tokensUpdated yesterday
    DevelopmentAuto-check passed

  • GAIA Agent Eval Scorecard

    amd/gaia

    Adds a release eval scorecard to a GAIA hub agent by writing a harness adapter, running a real eval, and wiring the result into the agent's README and release gate.

    1.6k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed

  • Aholo Renderer Package Rules

    manycoretech/aholo-viewer

    Work on the @manycore/aholo-viewer package. Use only when the user explicitly asks for renderer source, package build, public exports, JSDoc/API docs…

    1.1k GitHub stars~191 tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Vibe Doc Quality Gate

    ash1794/vibe-engineering

    Performs a fast 6-point quality check for technical documents (specs, design docs, READMEs).

    163 GitHub stars~653 tokensUpdated 3 days ago
    Testing & QAAuto-check passed

  • Diagram Design

    cathrynlavery/diagram-design

    Creates branded diagrams, from architecture, flowchart and sequence to charts and maps, as self-contained HTML with inline SVG, with import from draw.io, Mermaid and Excalidraw.

    49k GitHub starsUsed in 1 repo~7.6k tokens
    DevelopmentAuto-check passed

More from liaohch3/claude-tap

All 11 skills in this repo

  • Codex E2E Trace Validation

    liaohch3/claude-tap

    Runs a real Codex CLI session through claude-tap and produces trace evidence and viewer screenshots for pull requests that touch capture, proxying or the viewer.

    3.3k GitHub stars~3k tokensUpdated yesterday
    Auto-check passed

  • Terminal Demo Video Recorder

    liaohch3/claude-tap

    Records a real tmux end-to-end run with asciinema, converts it to a GIF and MP4, and captures trace viewer screenshots with Playwright.

    3.3k GitHub stars~545 tokensUpdated yesterday
    Auto-check passed

  • JS-in-HTML Testing

    liaohch3/claude-tap

    Tests JavaScript embedded in an HTML file in two layers: pytest checks of the logic ported to Python, and Playwright runs in a real browser for the DOM.

    3.3k GitHub stars~924 tokensUpdated yesterday
    Auto-check passed

  • Playwright Screen Recording

    liaohch3/claude-tap

    Records headless Playwright sessions as .webm videos to show a bug fix working or to give pull request reviewers visual evidence.

    3.3k GitHub stars~714 tokensUpdated yesterday
    Auto-check passed

  • PR Preflight Check

    liaohch3/claude-tap

    Runs a single merge-readiness check on a pull request: metadata, GitHub Actions status, local lint, format and test gates, and PR body rules, ending in READY or NOT_READY.

    3.3k GitHub stars~615 tokensUpdated yesterday
    Auto-check passed

  • Push and PyPI Release

    liaohch3/claude-tap

    Pushes the current work to GitHub and, when pending commits change code, bumps the version in pyproject.toml so CI publishes a new PyPI release.

    3.3k GitHub stars~509 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Maintainer Docs Legibility Check

What does Maintainer Docs Legibility Check do?

Runs local checks on maintainer docs for stale review dates, missing manifest paths and plan state drift, matching what the CI workflow enforces. py. It has three checks.

When should I use Maintainer Docs Legibility Check?

Maintainer Docs Legibility Check fits situations like: finishing edits to standards, plans or architecture docs and wanting a check before CI; finding stale last_reviewed dates in maintainer documentation; verifying that every path listed in the architecture manifest still exists.

How do I install Maintainer Docs Legibility Check in Claude Code?

Run `npx skills add liaohch3/claude-tap --skill legibility-check -a claude-code`. Or copy the skill folder (.agents/skills/legibility-check in liaohch3/claude-tap) into .claude/skills/legibility-check in your project. Claude Code loads it when a task matches its description.

How do I install Maintainer Docs Legibility Check in Codex?

Run `npx skills add liaohch3/claude-tap --skill legibility-check -a codex`. Or copy the skill folder (.agents/skills/legibility-check in liaohch3/claude-tap) into .agents/skills/legibility-check in your project. Codex loads it when a task matches its description.

Can I use Maintainer Docs Legibility Check in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add liaohch3/claude-tap --skill legibility-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/legibility-check, .gemini/skills/legibility-check, .github/skills/legibility-check and .opencode/skills/legibility-check in your project.

What does Maintainer Docs Legibility Check need to run?

Going by SKILL.md and its folder, Maintainer Docs Legibility Check needs the command-line tools its instructions call (uv). Our summary lists: uv and Python; The repository's scripts/check_legibility.py.

Does Maintainer Docs Legibility Check access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Maintainer Docs Legibility Check safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Maintainer Docs Legibility Check use?

Maintainer Docs Legibility Check is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Maintainer Docs Legibility Check use?

About 561 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Maintainer Docs Legibility Check?

Skills that share tags, products or a category with Maintainer Docs Legibility Check: Module Completeness Check (fengshao1227/ccg-workflow, 5.9k stars), BiSheng SDD Document Review (dataelement/bisheng, 12k stars), GAIA Agent Eval Scorecard (amd/gaia, 1.6k stars) and Aholo Renderer Package Rules (manycoretech/aholo-viewer, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Maintainer Docs Legibility Check?

liaohch3 (a GitHub user) maintains it in liaohch3/claude-tap, which has 3,271 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 10, 2026.

Source: liaohch3/claude-tap on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.