agentleFS
Sign inStart free
StachbooStachboo/claude-skills/skills/audit/SKILL.md

audit

Skill0 starsChanged 43 days agoMITView on GitHub

Audit any URL (and optionally its local repo) for performance, accessibility, SEO, best-practices, and security (HTTP headers, TLS, dependency CVEs, exposed secrets). Produces audit-report.md + audit.json. Triggers: "audit", "audit du site", "perf et sécurité", "/audit <url>".

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use delight, teach-impeccable and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • HK-hubSkill

    delight

    Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.

    Also in 32 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 19 projects that use this

  • zwy123zwySkill

    normalize

    将用户随意输入的提示词规范化为结构清晰、便于大模型执行的标准化提示词。适用于需要整理、统一提示词格式时调用。

    Also in 19 projects that use this

  • SkillPilotCHSkill

    level-up

    Eine Automatisierung pro Woche finden, scopen, shippen. Output landet als proposed-Eintrag in cadence.md mit konkreten Implementations-Schritten.

    Also in 12 projects that use this

  • ww-w-aiSkill

    pm-discovery

    PM Agent Team - Automated product discovery, strategy, and PRD generation. Runs PM analysis workflow to produce comprehensive PRD before PDCA Plan phase.

    Also in 3 projects that use this

  • +7 more from HK-hub

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 176 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the command via Bash (from the skill dir).

    line 22
  2. Very specific:

    Read the generated audit-report.md.

    line 23
  3. Very specific:

    Do not fabricate metrics. If a table cell says N/A, report it as N/A with its reason.

    line 28
  4. Very specific:

    Do not run cso/ln-* skills as subprocesses (interactive-hang risk) — this skill is self-contained.

    line 29
  5. Very specific:

    If audit.config.json is absent (fresh deploy), copy audit.config.example.json to audit.config.json.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 176 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/audit — Web performance & security auditor

What this does

Runs scripts/run.mjs which fans out 5 collectors (lighthouse, headers, tls, deps, secrets), merges schema-validated findings into audit.json, and renders audit-report.md. You (the model) never invent a number — every metric comes from a collector; failed probes are N/A with a reason.

Invocation

node scripts/run.mjs <url|name> [local-path] [flags]
  • <url|name>: a full https://… URL, or a key from audit.config.json.
  • [local-path]: repo dir for deps+secrets (optional; omitted ⇒ those render N/A).
  • Flags: --mobile-only --desktop-only --no-lab --runs N --live-only --local-only --all --json-only --fast --out <path> --fail-on <never|red|yellow> --require-complete.
  • Exit codes: 0 ok · 1 gate échoué (le site) · 2 plantage de l'auditeur · 3 audit.json invalide (ne pas s'y fier). Le gate est opt-in : sans --fail-on/--json-only, un site rouge sort quand même 0 — le verdict se lit dans le rapport, pas dans le code retour.

Steps for the model

  1. Resolve the target. If the user gave a name, confirm it exists in audit.config.json; if they gave a URL with no local path and a matching project exists, offer to add the local path.
  2. Run the command via Bash (from the skill dir). Stream stderr to the user.
  3. Read the generated audit-report.md.
  4. Author the "Top fixes" section (the ONLY place you add analysis): read reference/fixes-map.md + reference/scoring.md, pick the highest risk×ease FAIL findings, and for each give the concrete target file (glob the local repo to confirm: vercel.json / _headers / astro.config / next.config / pnpm up) with a paste-ready snippet. Mark this section > LLM-advice.
  5. Present the report. Never edit the measured tables.

Hard rules

  • Do not fabricate metrics. If a table cell says N/A, report it as N/A with its reason.
  • Do not run cso/ln-* skills as subprocesses (interactive-hang risk) — this skill is self-contained.
  • Heavy installs are forbidden; the only on-disk add is npx lighthouse (cached, ~tens of MB), gated on Chrome present.

Setup (first run)

  • If audit.config.json is absent (fresh deploy), copy audit.config.example.json to audit.config.json. Without it, full https://… URLs still work; only named targets and --all need the config.
  • Optional but recommended: get a free PageSpeed Insights API key (https://developers.google.com/speed/docs/insights/v5/get-started) and put it in audit.config.json psiApiKey or env AUDIT_PSI_KEY. Without it, perf uses local Lighthouse (Chrome required).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free