Legibility Check

Legibility Check is a Quality skill for Claude Code, published by liaohch3 in claude-tap.

3.1K stars266 forkson liaohch3/claude-tapAdded 2026/08/17+1% in starsRepository updated 2026/08/16

agent-debuggingagent-observabilityai-agentsai-toolsapi-debuggingclaude-codecodexcodex-clicursor-clideveloper-toolsgemini-clihermes-agentkimillmllm-proxyopencodepi-coding-agentproxytracetrace-viewer

Install in seconds

Install Legibility Check

Copy Legibility Check into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/liaohch3/claude-tap/tree/main/.agents/skills/legibility-check ~/.claude/skills/legibility-check

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/liaohch3/claude-tap.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .agents/skills/legibility-check/SKILL.md in liaohch3/claude-tap
Installs to: ~/.claude/skills/legibility-check
Collection: One of 11 skills cataloged from this repository
Category: Quality — 1354 skills

What Legibility Check does

Legibility Check runs deterministic checks on maintainer docs to catch stale standards metadata, broken architecture manifest paths, and plan state drift before CI does. Use it after modifying files under .agents/docs/standards/, .agents/docs/plans/, .agents/docs/architecture/, or AGENTS.md.

Legibility Check is cataloged under Quality on DirSkills. Legibility Check comes from a repository tagged agent-debugging, agent-observability, ai-agents, ai-tools and api-debugging.

Documentation

README

Excerpt

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

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.
Architecture manifest — every path listed in .agents/docs/architecture/manifest.yaml under expected_paths: must exist in the repo.
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

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Legibility Check

What else does liaohch3 publish alongside Legibility Check?
Legibility Check is one of 11 skills that DirSkills catalogs from liaohch3/claude-tap, the repository it ships in. Its siblings there include Claude Tap E2E Test, Codex E2E Test and Demo Video Generation. Each one is a separate skill with its own page in this directory, installs the same way Legibility Check does, and is maintained by liaohch3 in that same repository. The rest of the collection is listed on the liaohch3/claude-tap page.
How does Legibility Check compare to other Quality skills?
Legibility Check ranks #428 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Legibility Check against them. Open each page to compare what they document and how they install.