Agent skill

Audit Library

by selfishprimate in selfishprimate/gerillass

Sweep every mixin and function in Gerillass and report where it misbehaves — silent failures, unhelpful errors, questionable output, and gaps in test coverage.

Custom licenceAuto-check passedTesting & QA

Install Audit Library

skills CLI
$ npx skills add selfishprimate/gerillass --skill audit-library -a claude-code

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

GitHub CLI
$ gh skill install selfishprimate/gerillass audit-library --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/selfishprimate/gerillass.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/audit-library .claude/skills/audit-library && 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
audit-library
GitHub stars
171
Token cost
~2k tokens
SKILL.md length
1,152 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
Custom licence

At a glance

Sweep every mixin and function in Gerillass and report where it misbehaves — silent failures, unhelpful errors, questionable output, and gaps in test coverage.

  • Works in 5 steps: The suite → The adversarial sweep → Generated files → …
  • Comprehensively test the library
  • SKILL.md covers 1. The suite, 2. The adversarial sweep, 3. Generated files and 4. What the tests do not assert, plus 2 more sections
  • Calls npm, node and git

What it does

Audit Library is an agent skill from selfishprimate/gerillass. Sweep every mixin and function in Gerillass and report where it misbehaves — silent failures, unhelpful errors, questionable output, and gaps in test coverage. Use when asked to audit or comprehensively test the library, before a release, or after a change that touches many mixins.

Its SKILL.md is about 2k 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 Testing & QA, covering CSS and styling and Test coverage. The repository describes itself as: Gerillass is a Sass mixin library containing a set of Sass mixins and functions to help front-end developers generate scalable CSS outputs.

When your agent uses it

  • Comprehensively test the library
  • Before a release
  • After a change that touches many mixins

Example prompts

  • “/audit-library”

Workflow steps

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

  1. The suite
  2. The adversarial sweep
  3. Generated files
  4. What the tests do not assert
  5. The packed artifact

What it can do on your machine

Read from SKILL.md and the folder at commit 65f6638. 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:

    • npm
    • node
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use npm and 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

Audit Library loads about 2k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 1,152 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,152 words (~2,030 tokens).

“npm test only checks inputs somebody already thought of. This audit throws arguments nobody wrote a test for at all 55 mixins and all 24 functions, at every argument position, and reports what the library does with them. Run it…”

— opening of SKILL.md by selfishprimate, Custom licence
name
audit-library

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/audit-library of selfishprimate/gerillass.

Open the folder on GitHubat commit 65f6638

Compare with similar skills

Audit Library 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.

Audit Library compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit Library this skillselfishprimate/gerillass171—~2kAutomated safety check: PassCustom licence
Sanity Visual Regressionsanity-io/sanity6.4k—~3.4kAutomated safety check: PassMIT
Chrome Tracelayoutit/polycss759—~2kAutomated safety check: PassMIT
Ds Test Componentbaloise/design-system114—~2.1kAutomated safety check: PassApache-2.0
Manage HTML Teststelerik/kendo-themes158—~1.8kAutomated safety check: PassNone
Scenario MapOwl-Listener/inclusive-design-skills103—~568Automated safety check: PassMIT

Similar skills

  • Sanity Visual Regression

    sanity-io/sanity

    Official

    Add, review, and maintain Chromatic visual regression coverage in the Sanity monorepo via dev/storybook stories, the vitest browser-mode suite, and Playwright e2e snapshots.

    6.4k GitHub stars~3.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Chrome Trace

    layoutit/polycss

    Capture and analyze Chrome/Chromium performance traces with Playwright around a concrete browser interaction.

    759 GitHub stars~2k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Ds Test Component

    baloise/design-system

    Auto-generate all test files for DS components including visual, a11y, component, page object, and unit tests.

    114 GitHub stars~2.1k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Manage HTML Tests

    telerik/kendo-themes

    Create or update visual test scenarios for a Kendo UI component in the HTML package.

    158 GitHub stars~1.8k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Scenario Map

    Owl-Listener/inclusive-design-skills

    Map inclusive usage scenarios across ability spectrums for a product or feature.

    103 GitHub stars~568 tokensUpdated 4 mo ago
    Testing & QAAuto-check passed
  • Requirements

    rizsotto/Bear

    Write, modify, or review a requirement file under docs/requirements -- pick the single owning file, keep the text contract-only, name IDs so they need no explanation, and verify cross-references and…

    6.5k GitHub stars~2k tokensUpdated yesterday
    Testing & QAAuto-check passed

More from selfishprimate/gerillass

  • Gerillass

    selfishprimate/gerillass

    Use the Gerillass Sass mixin library — loading it, the mixin catalogue, and the argument forms that are easy to get wrong.

    171 GitHub stars~5k tokensUpdated 8 days ago
    Auto-check passed
  • Commit And PR

    selfishprimate/gerillass

    Write a Gerillass commit message and a pull request title and description to the house standard.

    171 GitHub stars~889 tokensUpdated 8 days ago
    Auto-check passed
  • New Mixin

    selfishprimate/gerillass

    Scaffold a new Gerillass mixin or utility function with the project's conventions, wire it into the folder index, describe it in meta/, and test it.

    171 GitHub stars~2.1k tokensUpdated 8 days ago
    Auto-check passed
  • Release

    selfishprimate/gerillass

    Cut and publish a Gerillass release — version bump, changelog, tag, GitHub release, npm publish, and post-publish verification.

    171 GitHub stars~2.9k tokensUpdated 8 days ago
    Auto-check passed
  • Sass Test

    selfishprimate/gerillass

    Write or debug sass-true unit tests for Gerillass mixins and utility functions.

    171 GitHub stars~1.5k tokensUpdated 8 days ago
    Auto-check passed

Questions about Audit Library

What does Audit Library do?

Sweep every mixin and function in Gerillass and report where it misbehaves — silent failures, unhelpful errors, questionable output, and gaps in test coverage. Audit Library is an agent skill from selfishprimate/gerillass. Sweep every mixin and function in Gerillass and report where it misbehaves — silent failures, unhelpful errors, questionable output, and gaps in test coverage.

When should I use Audit Library?

Audit Library fits situations like: comprehensively test the library; before a release; after a change that touches many mixins.

How do I install Audit Library in Claude Code?

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

How do I install Audit Library in Codex?

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

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

What does Audit Library need to run?

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

Does Audit Library access the network?

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

Is Audit Library 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 Audit Library use?

Audit Library has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Audit Library use?

About 2k tokens (SKILL.md is roughly 8.1k 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 Audit Library?

Skills that share tags, products or a category with Audit Library: Sanity Visual Regression (sanity-io/sanity, 6.4k stars), Chrome Trace (layoutit/polycss, 759 stars), Ds Test Component (baloise/design-system, 114 stars) and Manage HTML Tests (telerik/kendo-themes, 158 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit Library?

selfishprimate (a GitHub user) maintains it in selfishprimate/gerillass, which has 171 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on September 30, 2026.

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