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

Docs

by guardana in guardana/guardana

Documentation work in this repo — the five places a user-visible change must answer, the page conventions the site build enforces, the tests that pin prose to the registry, and a simplification pass…

Apache-2.0Auto-check passedSecurity

Install Docs

skills CLI
$ npx skills add guardana/guardana --skill docs -a claude-code

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

GitHub CLI
$ gh skill install guardana/guardana docs --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/guardana/guardana.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/docs .claude/skills/docs && 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
GitHub stars
129
Token cost
~1k tokens
SKILL.md length
515 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

Documentation work in this repo — the five places a user-visible change must answer, the page conventions the site build enforces, the tests that pin prose to the registry, and a simplification pass…

  • Works in 5 steps: Inventory with scout: size, last commit,… → Mark, sentence by sentence: true and… → Readability and wording are text-broker… → …
  • Update the docs
  • SKILL.md covers The five places, every…, What the build enforces, A page that is easy to read and A simplification pass
  • Calls uv

What it does

Docs is an agent skill from guardana/guardana. Documentation work in this repo — the five places a user-visible change must answer, the page conventions the site build enforces, the tests that pin prose to the registry, and a simplification pass that makes a page shorter and truer without inventing a claim. Use for "update the docs", "the README is stale", "simplify this page", "add a usage page", or when /ship needs the five places answered.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Security, covering Technical documentation and Prompt injection and agent security. The repository describes itself as: Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions. The licence is Apache-2.0.

When your agent uses it

  • Update the docs
  • The README is stale
  • Simplify this page
  • Add a usage page

Example prompts

  • “update the docs”
  • “the README is stale”
  • “simplify this page”
  • “/docs”

Requirements

  • Python 3

Workflow steps

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

  1. Inventory with scout: size, last commit, which tests pin the page, which pages link to it.
  2. Mark, sentence by sentence: true and needed · true, belongs elsewhere (move it) ·
  3. Readability and wording are text-broker work (content-model): a rewrite comes back with
  4. Run the gates that will notice: uv run pytest packages/guardana-core/tests/test_docs_consistency.py…
  5. Report what got shorter (lines before / after), what was cut and why, what moved where.

What it can do on your machine

Read from SKILL.md and the folder at commit ae7ee8b. 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

Docs loads about 1k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 515 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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 guardana/guardana at commit ae7ee8b, republished under its Apache-2.0 licence (© guardana). 515 words, ~1,030 tokens.

Download SKILL.mdSave it as .claude/skills/docs/SKILL.md (or your agent's skills folder).
name
docs
description
Documentation work in this repo — the five places a user-visible change must answer, the page conventions the site build enforces, the tests that pin prose to the registry, and a simplification pass that makes a page shorter and truer without inventing a claim. Use for "update the docs", "the README is stale", "simplify this page", "add a usage page", or when /ship needs the five places answered.
argument-hint
[page or change to document | audit | simplify <page>]

Documentation — shorter, truer, generated where it can be

Target: $ARGUMENTS

The five places, every user-visible change

wherewhen it needs an edit
CHANGELOG.md under [Unreleased]any user-visible change — say why, not only what
FEATURES.mda new capability, or one whose shape changed (a registry test refuses a built-in rule or evaluator missing from it)
docs/a new command gets usage-<command>.md; a changed one gets its page reconciled; docs/index.md lists it under the right heading
site/index.htmla headline claim moved: a count, a run mode, what the terminal demo prints
ROADMAP.mdthe direction moved — delete what shipped, add what was deferred with the reason

Then uv run python scripts/generate_docs.py for a rule, evaluator or taxonomy change — never edit docs/generated/ by hand — and the four --check scripts prove the site agrees.

What the build enforces

  • Every docs/**/*.md starts with front matter: title, nav_order (unique), summary, status (stable / beta / draft; design documents take the first word of their **Status:** line). A page missing any of them fails build_site.py.
  • Every page is listed in docs/index.md; the nav is built from that map and refuses a page it cannot reach. Only docs/work/ is left out — it is work in flight, not documentation.
  • Every local link points at a file that exists (test_docs_consistency.py); no page promises a version that already shipped (**v0.x, "coming in 0.x"); every count in prose equals the registry (test_docs_pages_state_the_real_counts.py, test_landing_page.py, test_readme_rule_table.py); the built site equals its sources (test_documentation_site.py).
  • A design document is named for its topic, never a date, carries a status line and is superseded rather than rewritten (docs/design/README.md).
Show full SKILL.md (257 more words)Show less

A page that is easy to read

One page, one job, the answer first. A usage-*.md page says what the command does, the command to type, what it writes, its exit codes, then the options — in fenced blocks, never in prose. History, incidents and measurements belong in CHANGELOG.md or docs/maintainers/lessons.md, not on a user page: a user page that explains why a rule exists three times is a page nobody finishes. A sentence that a test could pin (a count, a flag, a path) is written so the test can find it; a sentence nothing can check is a claim to cut.

A simplification pass

  1. Inventory with scout: size, last commit, which tests pin the page, which pages link to it.
  2. Mark, sentence by sentence: true and needed · true, belongs elsewhere (move it) · untrue or unverifiable (fix or cut, with the evidence) · repeated (keep one copy).
  3. Readability and wording are text-broker work (content-model): a rewrite comes back with every path, flag, count, rule id and link byte-identical, and a verdict that CUTS a sentence needs both engines to agree. The facts stay yours: a model never changes a number.
  4. Run the gates that will notice: uv run pytest packages/guardana-core/tests/test_docs_consistency.py packages/guardana-core/tests/test_documentation_site.py -q and scripts/ci_local.sh --quiet before the commit.
  5. Report what got shorter (lines before / after), what was cut and why, what moved where.

The maintainer-facing pages (docs/maintainers/), CONTRIBUTING.md and CLAUDE.md follow the same rules; CLAUDE.md additionally has a line budget the setup gate enforces, and the story behind a rule goes to docs/maintainers/lessons.md.

© guardana, Apache-2.0. 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 .claude/skills/docs of guardana/guardana.

Open the folder on GitHubat commit ae7ee8b

Compare with similar skills

Docs 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Docs this skillguardana/guardana129—~1kAutomated safety check: PassApache-2.0
Forensifyalexgreensh/repo-forensics188—~2.5kAutomated safety check: NotesCustom licence
Skylos Securityduriantaco/skylos843—~545Automated safety check: PassApache-2.0
Agentic GitHub Actions Auditortrailofbits/skills7.4k6 repos~5.4kAutomated safety check: NotesCC-BY-SA-4.0
Plugin Scanneriflytek/skillhub5.2k2 repos~1.1kAutomated safety check: NotesApache-2.0
Security GuidejnMetaCode/shellward140—~644Automated safety check: WarnApache-2.0

Similar skills

  • Forensify

    alexgreensh/repo-forensics

    Cross-agent self-inspection of your AI-agent stack. An agent skill from alexgreensh/repo-forensics.

    188 GitHub stars~2.5k tokensUpdated 10 days ago
    SecurityAuto-check: notes

  • Skylos Security

    duriantaco/skylos

    Investigate and harden Skylos security behavior. An agent skill from duriantaco/skylos.

    843 GitHub stars~545 tokensUpdated today
    SecurityAuto-check passed

  • Agentic GitHub Actions Auditor

    trailofbits/skills

    Official

    Statically audits GitHub Actions workflows that run AI coding agents, tracing attacker-controlled input to agent prompts and flagging unsafe sandbox, trigger and allowlist settings.

    7.4k GitHub starsUsed in 6 repos~5.4k tokens
    SecurityAuto-check: notes

  • Plugin Scanner

    iflytek/skillhub

    Scan AI agent skills, plugins, MCP servers, and agent tooling for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them.

    5.2k GitHub starsUsed in 2 repos~1.1k tokens
    SecurityAuto-check: notes

  • Security Guide

    jnMetaCode/shellward

    OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation

    140 GitHub stars~644 tokensUpdated 9 days ago
    SecurityAuto-check: warnings

  • Agent Security Audit

    OWASP/secure-agent-playbook

    Audit AI agent configurations for security risks — excessive permissions, prompt injection surfaces, data exfiltration paths, and missing guardrails.

    187 GitHub stars~542 tokensUpdated 12 days ago
    SecurityAuto-check passed

More from guardana/guardana

All 16 skills in this repo

  • Content Model

    guardana/guardana

    Route wording work to GPT (codex CLI) or Gemini (agy CLI) instead of writing it with Claude — landing-page copy, a readability rewrite of a README or docs page, attack and judge prompts for a rule…

    129 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Ship

    guardana/guardana

    Commit and push a finished change the way this repo requires — explicit paths, one commit per logical change, no attribution, the five documentation places answered, the site checks before a push (a…

    129 GitHub stars~836 tokensUpdated today
    Auto-check: notes

  • Add A Rule

    guardana/guardana

    Add security coverage to Guardana the way this repository requires — as a rule, evaluator or target, never by patching the engine — with the fixtures, the framework mapping and the documentation…

    129 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Auto

    guardana/guardana

    Autonomous, non-interactive run of the whole lifecycle for one development task — size, plan, build, gate, review, fix, commit — without stopping for questions.

    129 GitHub stars~792 tokensUpdated today
    Auto-check passed

  • False Green Audit

    guardana/guardana

    Hunt for the failure this project exists to prevent — code that compiles, types, tests green, and quietly reports "all clear" about something it never examined.

    129 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Gate

    guardana/guardana

    Run this project's verification — the full local CI mirror (ruff, mypy, import contract, pytest with PostgreSQL, coverage floors, dogfood, generated docs and site, the isolated example suites, the…

    129 GitHub stars~776 tokensUpdated today
    Auto-check passed

Categories

Questions about Docs

What does Docs do?

Documentation work in this repo — the five places a user-visible change must answer, the page conventions the site build enforces, the tests that pin prose to the registry, and a simplification pass…. Docs is an agent skill from guardana/guardana. Documentation work in this repo — the five places a user-visible change must answer, the page conventions the site build enforces, the tests that pin prose to the registry, and a simplification pass that makes a page shorter and truer without inventing a claim.

When should I use Docs?

Docs fits situations like: update the docs; the README is stale; simplify this page; add a usage page.

How do I install Docs in Claude Code?

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

How do I install Docs in Codex?

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

Can I use Docs 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 guardana/guardana --skill docs -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, .gemini/skills/docs, .github/skills/docs and .opencode/skills/docs in your project.

What does Docs need to run?

Going by SKILL.md and its folder, Docs needs the command-line tools its instructions call (uv). Our summary lists: Python 3.

Does Docs 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 Docs 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 use?

Docs is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Docs use?

About 1k tokens (SKILL.md is roughly 4.1k 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?

Skills that share tags, products or a category with Docs: Forensify (alexgreensh/repo-forensics, 188 stars), Skylos Security (duriantaco/skylos, 843 stars), Agentic GitHub Actions Auditor (trailofbits/skills, 7.4k stars) and Plugin Scanner (iflytek/skillhub, 5.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Docs?

guardana (a GitHub organization) maintains it in guardana/guardana, which has 129 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 7, 2026.

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