New: 97,000+ 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

Docs Audit

by willdady in willdady/platypus

Audit one section of the docs content against the code, and report what is wrong, stale, fragile, off-voice, or missing.

MITAuto-check passed

Install Docs Audit

skills CLI
$ npx skills add willdady/platypus --skill docs-audit -a claude-code

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

GitHub CLI
$ gh skill install willdady/platypus docs-audit --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/willdady/platypus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/docs-audit .claude/skills/docs-audit && 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
docs-audit
GitHub stars
116
Token cost
~1.2k tokens
SKILL.md length
666 words
Files
2
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Audit one section of the docs content against the code, and report what is wrong, stale, fragile, off-voice, or missing.

  • Works in 5 steps: Pick the section and build the suspect… → List every claim → Verify each claim against source → …
  • SKILL.md covers Step 1 — Pick the section and…, Step 2 — List every claim, Step 3 — Verify each claim… and Step 4 — Classify, plus 2 more sections
  • Calls git

What it does

Docs Audit is an agent skill from willdady/platypus. Audit one section of the docs content against the code, and report what is wrong, stale, fragile, off-voice, or missing.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `VOICE.md`).

The repository describes itself as: Self-hosted AI Agents for your whole team — on your infrastructure, your models, around the clock. The licence is MIT.

Example prompts

  • “/docs-audit”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Pick the section and build the suspect pool
  2. List every claim
  3. Verify each claim against source
  4. Classify
  5. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 2147848. 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:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, 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

Docs Audit loads about 1.2k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 666 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 willdady/platypus at commit 2147848, republished under its MIT licence (© willdady). 666 words, ~1,191 tokens.

Download SKILL.mdSave it as .claude/skills/docs-audit/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
docs-audit
description
Audit one section of the docs content against the code, and report what is wrong, stale, fragile, off-voice, or missing.
disable-model-invocation
true

Audit one section of apps/docs/content against the source, and report every claim that no longer holds.

apps/docs/content/docs-contract.test.ts already pins the claims with exactly one authoritative source — env tables, webhook events, core Plugin names, field limits, internal links, heading anchors. Assume those are green and do not re-check them. Your job is everything that needs judgement, above all the ~150 bolded UI labels across building-with-platypus/, which nothing can see.

Never answer from memory. Every verdict cites a file and a line in the code. A claim you did not open the source for is a claim you did not check.

Step 1 — Pick the section and build the suspect pool

Audit one section per run — one top-level directory of the docs content. List what is actually there rather than working from a remembered set, so a section added since cannot be the one you never audit. Ask the user which if they did not say.

Find when the section was last touched, then list what changed in the code since:

bash
git log -1 --format=%H -- apps/docs/content/<section>
git log <that-sha>..HEAD --oneline -- apps/backend apps/frontend packages/schemas

Drift concentrates where code moved and docs did not, so read that commit list before you read the pages — it tells you which claims to distrust.

Done when: you have the section, the last-touch SHA, and the commit list.

Step 2 — List every claim

Read each page in the section in full. Then write out every falsifiable claim it makes, each with its file:line.

A claim is anything a reader could act on and find wrong: a UI label, a field name, a menu path, a default, a limit, an ordering, a behaviour, a "this requires that", a "you cannot do X".

List every claim, not a sample. Coverage has to be a property of the procedure, because it will not be a property of your attention. A page with sixty claims produces sixty rows.

Done when: every page in the section has been read end to end and every claim is on the list with a line number.

Step 3 — Verify each claim against source

For each claim, open the code that decides it and record the verdict as doc file:line vs code file:line.

Where to look:

  • UI labels, fields, menu paths → apps/frontend/app/**, apps/frontend/components/**
  • limits, enums, required fields → packages/schemas/index.ts
  • endpoints, status codes, errors → apps/backend/src/routes/**
  • run behaviour, steps, timeouts → apps/backend/src/runs/**
  • plugins, Sandboxes, tool sets → apps/backend/src/plugins/**
  • deployment, env, first boot → .example.env, compose*.yaml, apps/backend/index.ts

Check exhaustive lists in both directions: everything the code has appears in the doc, and everything the doc lists exists in the code. A missing row is invisible to a reader — they cannot miss what they were never shown.

Done when: every claim has a verdict and a code citation.

Show full SKILL.md (225 more words)Show less

Step 4 — Classify

ClassMeaning
WRONGContradicts the code. A reader following it fails.
STALEWas true, describes something that has since moved or been renamed.
FRAGILETrue today, with no anchor — it will rot and nothing will notice.
TONEAccurate but off-voice against VOICE.md.
GAPThe code does something user-facing that no page mentions.

Step 5 — Report

Rank by reader cost: what breaks a deployment first, then what wastes an hour, then what merely reads badly. Not by page order, and not by how easy the fix is.

For each finding give the doc file:line, the code file:line, what the page says, what the code does, and the proposed edit.

FRAGILE defaults to deletion, not correction. Correcting an anchorless claim resets the clock; deleting it stops the bleeding. Keep it only when it earns its maintenance — say why in the finding. Otherwise the audit's own output becomes next year's backlog.

Close with the claim count, how many you verified, and what you could not check — a claim you could not resolve is a finding, not a silence.

The honest limit

This skill is user-invoked only, so its value is bounded entirely by someone remembering to type it. Nothing schedules it and nothing reminds you. Pair it with a release checklist or /loop, or accept that the contract test is the only thing actually running.

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

Files

SKILL.md and 1 other file in .agents/skills/docs-audit of willdady/platypus.

  • SKILL.md
  • VOICE.md

Open the folder on GitHubat commit 2147848

Compare with similar skills

Docs Audit 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.

Docs Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Docs Audit this skillwilldady/platypus116—~1.2kAutomated safety check: PassMIT
Resume Section Builderdavila7/claude-code-templates32k2 repos~2.4kAutomated safety check: PassMIT
Draft Sectionbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~529Automated safety check: NotesCustom licence
Segmenting Clinical Sectionsmaziyarpanahi/openmed5.5k—~1.8kAutomated safety check: PassApache-2.0
Brief Section Drafteranthropics/claude-for-legal9.6k2 repos~4kAutomated safety check: PassApache-2.0
Validate Docs SectionNethereum/Nethereum2.3k—~15kAutomated safety check: PassMIT

Similar skills

  • Resume Section Builder

    davila7/claude-code-templates

    Create targeted resume sections optimized for different experience levels and roles.

    32k GitHub starsUsed in 2 repos~2.4k tokens
    Business, Finance & HRAuto-check passed

  • Draft Section

    brycewang-stanford/Auto-Empirical-Research-Skills

    Drafts academic prose for a manuscript section from bullet points or an outline.

    4.5k GitHub stars~529 tokensUpdated 2 days ago
    Research & ScienceAuto-check: notes

  • Segmenting Clinical Sections

    maziyarpanahi/openmed

    Split a clinical note into canonical sections (Chief Complaint, HPI, PMH, Medications, Allergies, Assessment & Plan, etc.) before running OpenMed NER or de-identification, so section context…

    5.5k GitHub stars~1.8k tokensUpdated yesterday
    DatabasesAuto-check passed

  • Brief Section Drafter

    anthropics/claude-for-legal

    Official

    Draft a brief section in house style, consistent with the case theory — every fact cited, every case checked, every argument tied to the theory.

    9.6k GitHub starsUsed in 2 repos~4k tokens
    Auto-check passed

  • Validate Docs Section

    Nethereum/Nethereum

    Validate and perfect a Nethereum documentation section end-to-end.

    2.3k GitHub stars~15k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed

  • Discussion Section Architect

    aipoch/medical-research-skills

    Structures and writes discussion sections for academic papers and research reports.

    2k GitHub stars~2.5k tokensUpdated 20 days ago
    Research & ScienceAuto-check passed

More from willdady/platypus

  • API Conventions

    willdady/platypus

    Response-body conventions for the Platypus backend API — the error key for failures, the message key for 2xx status messages, and when to throw a typed error instead of returning a response.

    116 GitHub stars~655 tokensUpdated today
    Auto-check passed

  • Platypus Tools

    willdady/platypus

    Platypus tools and tool sets — writing a tool, contributing a tool set from a plugin, scoping tools to a workspace, sharing a tool across sets, chat icons, and custom tool UI.

    116 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Add API Endpoint

    willdady/platypus

    Guide for adding new API endpoints to the Platypus backend using Hono.js — routing, tenant scoping middleware, validation, and database access.

    116 GitHub stars~955 tokensUpdated today
    Auto-check passed

  • Database Schema Changes

    willdady/platypus

    Guide for making database schema changes in Platypus using Drizzle ORM — editing the schema, pushing to a dev database, and generating the migration that ships.

    116 GitHub stars~527 tokensUpdated today
    Auto-check passed

  • Form Conventions

    willdady/platypus

    Post-save conventions for Platypus frontend forms — where a save lands the user, and what the submit button is called.

    116 GitHub stars~916 tokensUpdated today
    Auto-check passed

  • Pre Release Check

    willdady/platypus

    The final gate before a release is cut — go green, reconcile the release PR against what actually landed, sweep what CI can't see, check the roadmap and ADR statuses, optionally deep-review, then…

    116 GitHub stars~3.1k tokensUpdated today
    Auto-check passed

Questions about Docs Audit

What does Docs Audit do?

Audit one section of the docs content against the code, and report what is wrong, stale, fragile, off-voice, or missing. Docs Audit is an agent skill from willdady/platypus. Audit one section of the docs content against the code, and report what is wrong, stale, fragile, off-voice, or missing.

How do I install Docs Audit in Claude Code?

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

How do I install Docs Audit in Codex?

Run `npx skills add willdady/platypus --skill docs-audit -a codex`. Or copy the skill folder (.agents/skills/docs-audit in willdady/platypus) into .agents/skills/docs-audit in your project. Codex loads it when a task matches its description.

Can I use Docs Audit 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 willdady/platypus --skill docs-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/docs-audit, .gemini/skills/docs-audit, .github/skills/docs-audit and .opencode/skills/docs-audit in your project.

What does Docs Audit need to run?

Going by SKILL.md and its folder, Docs Audit needs the command-line tools its instructions call (git).

Does Docs Audit access the network?

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

Is Docs Audit 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 Docs Audit use?

Docs Audit 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 Docs Audit use?

About 1.2k tokens (SKILL.md is roughly 4.8k 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 Docs Audit?

Skills that share tags, products or a category with Docs Audit: Resume Section Builder (davila7/claude-code-templates, 32k stars), Draft Section (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Segmenting Clinical Sections (maziyarpanahi/openmed, 5.5k stars) and Brief Section Drafter (anthropics/claude-for-legal, 9.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Docs Audit?

willdady (a GitHub user) maintains it in willdady/platypus, which has 116 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

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