agentsclimarketplace
Sign in

Shelves

Audit & compliance

7,541 rows from 1,970 repositories

Checking a thing against a standard somebody else wrote.

What Audit & compliance skills agree on

1,290 skill files read, by 960 of the 1,589 authors on this shelf whose files we hold, 2026-09-06

The middle one of the 178 measured here is ~1.6k tokens long, counted with cl100k_base

Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.

What they tell the agent to do

  1. Read product marketing context before asking questions29 of 960 in 11 filesalso worded as Check for product marketing context first.; Read product marketing context first
  2. Rank findings by severity29 of 960 in 22 filesalso worded as Categorize findings by severity; Classify findings by severity
  3. Generate audit report22 of 960also worded as Generate report; Generate full security audit report
  4. Run the audit script20 of 960 in 19 filesalso worded as Run the audit command; Run the audit script for each site
  5. Generate a prioritized action plan report19 of 960 in 11 filesalso worded as Generate prioritized action plan; Generate a prioritized action plan
  6. Ensure one H1 per page15 of 960 in 5 filesalso worded as Maintain one H1 per page.; Check for one H1 per page
  7. Ensure sitemap exists and is accessible14 of 960 in 4 filesalso worded as Ensure XML sitemap is accessible and submitted.; Verify xml sitemap exists and is accessible
  8. Verify alt text on all images12 of 960 in 3 filesalso worded as Include alt text on all images.; Verify all non text content has alt text
  9. Determine the audit scope before starting12 of 960 in 4 filesalso worded as Define audit scope before starting; Define scope before auditing the system
  10. Detect business type from homepage signals11 of 960 in 7 filesalso worded as Detect the business type by analyzing homepage signals; Fetch the homepage and detect business type
  11. Delegate specialized tasks to subagents11 of 960 in 7 filesalso worded as Delegate tasks to available subagents; Delegate analysis to 5 specialized subagents
  12. Present findings organized by severity11 of 960also worded as Report findings grouped by severity; Separate findings by severity
  13. Classify every finding by severity11 of 960also worded as Assign a severity to every finding.; classify every finding using the severity framework
  14. Ensure all pages have canonical tags10 of 960 in 4 filesalso worded as verify all pages have canonical tags
  15. Classify goods using GRI rules and chapter analysis10 of 960 in 4 filesalso worded as Classify products using GRI rules; Classify products using GRI rules and analysis

What they tell it not to do

  1. Do not modify files25 of 960also worded as Do not modify any files; Do not modify files unless explicitly asked.
  2. Do not invent a plausible entry to fill a field19 of 960also worded as Never invent a plausible entry to fill a field; Never invent a plausible entry
  3. Do not apply fixes15 of 960 in 12 filesalso worded as Do not auto-apply fixes; Never apply fixes
  4. Never modify code or infrastructure15 of 960 in 11 filesalso worded as Do not modify code; Never modify code
  5. Do not modify the code being audited14 of 960 in 12 filesalso worded as Do not modify code during evaluation; Never modify or delete audit entries
  6. Never fabricate findings13 of 960also worded as Do not fabricate findings; Never fabricate evidence
  7. Do not report no schema found using web_fetch12 of 960 in 5 filesalso worded as Do not report no schema found using web fetch; Never report no schema found based solely on web fetch
  8. Do not remove focus outlines without a visible replacement12 of 960 in 8 filesalso worded as Never remove focus outlines; Do not use outline none without focus visible
  9. Never proceed with a transaction while a screening hit is unresolved10 of 960 in 4 filesalso worded as Never proceed with an unresolved screening hit; Do not proceed with transactions during unverified hits
  10. Do not fix issues while auditing10 of 960 in 8 filesalso worded as Don't fix issues.; Do not fix issues found during the audit

What they expect to be installed

  1. git126 of 960
  2. grep120 of 960
  3. python356 of 960
  4. curl56 of 960
  5. bash53 of 960
  6. python43 of 960 in 42 files
  7. node43 of 960
  8. find41 of 960
  9. Glob41 of 960 in 40 files
  10. gh36 of 960

What they ask it to produce

  1. Audit report142 of 960 in 135 filesalso worded as Security Audit Report; Audit Report Structure
  2. Findings39 of 960also worded as Detailed findings; findings report
  3. Structured report30 of 960also worded as Structured audit report; structured findings report
  4. Markdown report29 of 960also worded as Markdown audit report; Single Markdown report
  5. FULL-AUDIT-REPORT.md23 of 960 in 20 filesalso worded as audit-report.md; ADS-AUDIT-REPORT.md
  6. Compliance report22 of 960 in 21 filesalso worded as completion report; compliance-report.md
  7. Accessibility audit report20 of 960 in 18 filesalso worded as accessibility audit reports; Accessibility issue report
  8. ACTION-PLAN.md18 of 960 in 14 filesalso worded as Action plan; plan.md

When Audit & compliance authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 960 authors, with the skills that name each one

How Audit & compliance skills are built

6,496 skill directories by 1,628 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 3 files, 19.1 KB beside SKILL.md

Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.

The shape

  1. SKILL.md is the whole skill618 of 1,628 authors, 3,194 of 6,496 skills
  2. files ship beside it1,010 of 1,628 authors, 3,302 of 6,496 skills
  3. executable scripts ship inside391 of 1,628 authors, 1,038 of 6,496 skills

The folders they converge on

  1. references/648 of 1,628 authors, 2,079 of 6,496 skills
  2. scripts/344 of 1,628 authors, 931 of 6,496 skills
  3. agents/184 of 1,628 authors, 529 of 6,496 skills
  4. assets/134 of 1,628 authors, 334 of 6,496 skills
  5. evals/110 of 1,628 authors, 207 of 6,496 skills
  6. examples/72 of 1,628 authors, 141 of 6,496 skills

  • Ponytail audit

    DietrichGebert/ponytail/.openclaw/skills/ponytail-audit Skill

    102,911★ repo

    Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

  • Agentic actions auditor

    trailofbits/skills/plugins/agentic-actions-auditor/skills/agentic-actions-auditor Skill

    6,559★ repo

    Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows

  • Document review

    open-gitagent/opengap/examples/full/skills/document-review Skill

    2,907★ repo

    A framework-agnostic, git-native standard for defining AI agents

  • Accessibility

    addyosmani/web-quality-skills/skills/accessibility Skill

    2,628★ repo

    Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.

  • Ad account auditor

    aaron-he-zhu/aaron-marketing-skills/ad/activate/ad-account-auditor Skill

    2,560★ repo

    120 marketing skills + 8 commands for Claude Code & AI agents across 7 disciplines — SEO/GEO, influencer, paid ads, email, product launch, organic social & brand narrative — on one shared contract, with 8 auditor gates: CORE-EEAT · CITE · STAR · ROAS · SEND · RAMP · ECHO · TALE.

  • Audit reproducibility

    pedrohcgs/claude-code-my-workflow/.claude/skills/audit-reproducibility Skill

    1,465★ repo

    A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.

  • Oma academic writer

    first-fluke/oh-my-agent/.agents/skills/oma-academic-writer Skill

    1,226★ repo

    Portable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with your codebase, conventions, and engineering standards.

  • Anti entropy governance

    GanyuanRan/Aegis/skills/anti-entropy-governance Skill

    990★ repo

    Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

  • Ai governance reviewer carl ditzler

    lawve-ai/awesome-legal-skills/skills/ai-governance-reviewer-carl-ditzler Skill

    no license641★ repo

    A curated list of awesome Agent Skills for automating legal work

  • Ln 21 documentation auditor

    levnikolaevich/claude-code-skills/plugins/codebase-audit-suite/skills/ln-21-documentation-auditor Skill

    535★ repo

    18 standalone skills for Claude Code and Codex: review, audit, optimization, testing, product discovery, and safe repository publishing.

  • Accessibility audit

    rampstackco/claude-skills/dist/pi/.agents/skills/accessibility-audit Skill

    531★ repo

    Stack-agnostic Claude Skills covering the full website lifecycle: brand, design, content, SEO, dev, ops, growth, and research. Build, ship, audit, optimize.

  • Content quality auditor

    ViryaZheng/recomby-geo/plugins/recomby-geo/skills/content-quality-auditor Skill

    507★ repo

    GEO 领域 AI 员工开源方案 · Open-source GEO AI-employee solution (MIT). GEO Skills package + curated lists of agents and office CLIs that make up the AI-employee stack.

  • A11y audit

    plugin87/ux-ui-agent-skills/.claude/skills/a11y-audit Skill

    no license493★ repo

    Turn Claude into a Senior Design Architect — DTCG design tokens, 42 components, WCAG 2.2 accessibility, any-framework code, 138 design systems, and runnable skills.

  • Ai discoverability audit

    BrianRWagner/ai-marketing-claude-code-skills/ai-discoverability-audit Skill

    no license393★ repo

    Marketing frameworks that AI actually executes. Designed for Claude Code, but could be used for OpenClaw, etc.

  • Seo audit skill

    seo-skills/seo-audit-skill Skill

    380★

    A comprehensive SEO audit command-line tool with 108 audit rules across 12 categories. Analyze any website for SEO best practices, Core Web Vitals, security headers, structured data, accessibility, and more.

  • Accessibility compliance

    jamditis/claude-skills-journalism/dev-toolkit/skills/accessibility-compliance Skill

    360★ repo

    Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing, and more

  • Audit xcode security settings

    superagents-lab/xcode27-skills/audit-xcode-security-settings Skill

    no license276★ repo

    Apple's official Agent Skills exported from Xcode 27 — SwiftUI, UIKit modernization, Swift Testing, C bounds-safety, and security hardening for AI coding agents.

  • Accessibility auditor

    OneWave-AI/claude-skills/accessibility-auditor Skill

    248★ repo

    172 production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture. Built and maintained by OneWave AI.

  • Accessibility audit

    billy-enrizky/openbrowser-ai/plugin/skills/accessibility-audit Skill

    238★ repo

    OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.

  • Absolute audit

    maddhruv/absolute/skills/absolute-audit Skill

    206★ repo

    Absolute Skills to 10x your Development Lifecycle

  • Canvas accessibility auditor

    vishalsachdev/canvas-mcp/skills/canvas-accessibility-auditor Skill

    191★ repo

    Canvas LMS MCP server — 80+ tools and 5 agent skills for students & educators. Works with Claude, Cursor, Codex, and 40+ agents. v1.1.0

  • Aelf skills

    AElfProject/aelf-skills Skill

    no license184★

    Unified aelf skills hub for discovery, routing, bootstrap, and health checks across OpenClaw, Codex, Cursor, and Claude Code.

  • Module audit

    wednesday-solutions/ai-agent-skills/skills/agents/module-audit Skill

    165★ repo

    Pre-configured agent skills for Vibe Coded projects. These skills provide AI coding assistants (Claude Code, Cursor, etc.) with specific guidelines for code quality and design standards.

  • Compliance check

    guangshu100/BidMaster-Pro/skills/check/compliance_check Skill

    140★ repo

    全流程 智能招投标 Agent：标书生成 · 招投标解读 · 标书检查 · 标书文档ai排版 · 商机发现 一键完成。 21 项合规检查 · 多模型切换 · RAG 知识库 · OCR 抽取。 从招标公告到可交付 docx 文档，全流程 AI 自动化。

  • Gdpr compliance checker

    goSprinto/compliance-skills/gdpr-compliance-checker Skill

    130★ repo

  • Accessibility audit websites

    TheGoat395/Codex-Skills/skills/accessibility-audit-websites Skill

    117★ repo

    Codex-first Agent Skills library for premium frontend, website, motion, accessibility, QA, and handoff workflows.

  • Google ads audit

    cognyai/claude-code-marketing-skills/skill-pipeline/google-ads-audit Skill

    no license92★ repo

    Marketing skills for Claude Code — SEO audits and implementation, ad analysis, ad optimization. Free skills need no account. $9/mo for live Search Console, Bing & LinkedIn data.

  • Fable audit

    deepklarity/harness-kit/.claude/skills/fable-audit Skill

    89★ repo

    A kit for building with AI agents and also the engineering patterns around it.

  • Audit

    ScaleBrick/founder-marketing-skills/skills/audit Skill

    88★ repo

    Open-source marketing skills for founders. Keyword research, growth strategy, social search audit, competitor analysis. Install with npx skills.

  • Audit context

    DheerG/swarms/skills/audit-context Skill

    84★ repo

    Achieve extraordinary results with claude code across a variety of tasks

  • Audit and fix

    nelsonwerd/idea-to-ship-skills/skills/audit-and-fix Skill

    82★ repo

    Composable Agent Skills (Claude + OpenAI Codex) for taking an idea from fuzzy → validated → sequenced build → shipped — a manual tier (ideate, deep-dive, prompt-pack) and an autonomous tier (autopilot, build-loop, audit-and-fix).

  • Audit finding fix

    apache/magpie/skills/audit-finding-fix Skill

    78★ repo

    Agent-assisted maintainership and development framework for Apache projects — Triage, Mentoring, Drafting (agent-authored fixes with human review), and Pairing (developer-side dev-cycle) skills shipping; Agentic Autonomous (auto-merge) on the roadmap.

  • Agent interaction audit

    JasonxzWen/harness-hub/skills/agent-interaction-audit Skill

    no license77★ repo

    Repository-first deterministic migration and atomic Skill source for Claude Code and Codex.

  • cloud-audit

    gebalamariusz/cloud-audit/io.github.gebalamariusz/cloud-audit MCP server

    68★ repo

    AWS security scanner with attack chain detection, IAM privilege escalation, and fixes

  • Research architect audit

    mmTheBest/Research-Architect/dist/codex/skills/research-architect-audit Skill

    67★ repo

    An end-to-end research workflow skill for turning ideas into evidence-backed, citation-supported manuscript drafts

  • Ads audit

    naveedharri/benai-skills/plugins/ads/skills/ads-audit Skill

    55★ repo

  • Blocked audit

    SlanchaAI/ingot/evals/fixtures/skills/blocked-audit Skill

    49★ repo

    Change management, SkillOpt optimization, and evidence-gated evals for agent skills.

  • Auditor skill

    solanabr/auditor-skill Skill

    48★

    Claude Code / agentic security skill for Solana programs and software. Full audit-firm lifecycle, executable PoC + fix-patch delivery, a Rust pre-scanner + cross-audit memory, 1,346 checks across 20 checklists, and 131 real-world attack vectors.

  • Accessibility audit

    cuellarfr/design-skills/accessibility-audit Skill

    48★ repo

    UX and design skills for Claude Code — research, critique, accessibility, journey mapping and more.

  • Speq audit

    marconae/speq-skill/.claude/skills/speq-audit Skill

    48★ repo

    A light-weight and straightforward system for spec-driven development with Claude Code or OpenAI Codex. Written in Rust 🦀

  • Work with design systems

    natdexterra/work-with-design-systems Skill

    48★

    Inspect, build, or extend Figma design systems from Claude Code. Read-only audits with WCAG checks and component scoring, build mode with variable bindings and slots, optional Phase 6 sync to tokens.css + AI rules.

  • Audit logging

    BagelHole/DevOps-Security-Agent-Skills/compliance/auditing/audit-logging Skill

    46★ repo

    Agent-ready DevOps, security, infrastructure, and compliance knowledge base with 80+ skills across Kubernetes, Terraform, AWS/Azure/GCP, AI platform operations, container hardening, SOC2/ISO27001, and incident response—plus ready-to-run scripts, templates, and playbooks for SRE, platform, and security teams.

  • Design red team audit

    Stanestane/game-design-skills-bundle/design-red-team-audit Skill

    no license44★ repo

    A public OpenClaw and ClawHub-ready bundle of game design skills for emotional direction, feature workflows, audits, FTUE, pitch decks, prototyping, and red-team design review.

  • Claude code

    atharvnaik1/ipaship-audit/wrappers/claude-code Skill

    43★ repo

    Let your AI Agent review your iOS/Android apps for appstore policy & security bugs with ipaShip's web app, cli, mcp or claude-skill with safety hooks layer any any llm agent you use - loopin fixes in dev stage only no more waits till submissions.

  • Nsfc benzi audit

    jiankang1991/nsfc-benzi-audit/nsfc-benzi-audit Skill

    40★ repo

    一个用于国家自然科学基金（NSFC/国自然）申请书初稿诊断的 Agent Skill

  • Manage governance

    skill-mill/agent-skill-harbor/.claude/skills/manage-governance Skill

    39★ repo

    Private skill catalog / marketplace for teams

  • Platform skills

    nitinjain999/platform-skills Skill

    36★

    A platform engineering handbook covering Kubernetes, OpenShift, Argo CD, Flux CD, AWS, Azure, Terraform, and GitHub Actions — with an optional Claude plugin layer for interactive guidance.

  • Security audit

    netresearch/security-audit-skill/skills/security-audit Skill

    no license35★ repo

    Agent Skill for PHP security audits - OWASP patterns, vulnerability detection | Claude Code compatible

  • Librecrawl — Technical SEO Audit MCP Server

    adityaarsharma/librecrawl-technical-seo-audit-mcp/io.github.adityaarsharma/librecrawl-technical-seo-audit-mcp MCP server

    34★ repo

    Self-hosted technical SEO audit MCP. 50+ checks, WAF detection, ephemeral. Built on LibreCrawl.

  • Audit

    Hainrixz/claude-seo-ai/skills/audit Skill

    33★ repo

    The SEO + AI-search (GEO/AEO) optimization toolkit for Claude Code — two-score audit + opt-in fixer. Built for 2026-2027.

  • Audit

    alirezarezvani/gaios/.claude/skills/audit Skill

    no license32★ repo

    Open-source AI Operating System (AIOS) blueprint for Claude Code & Codex — turn any agent into your personal second brain + Chief of Staff: skills, self-verifying workflows, a second-brain wiki, and deterministic tools. Fork it for any role or domain.

  • Raam audit

    geoffreycrofte/luxembourg-accessibility-skillset/raam-audit Skill

    31★ repo

    A set of skills including RAWeb, RAM, and RAPDF coverage for AI (targeting Claude Code)

  • Skill2 audit

    blackblue-labs/skill2/skills/skill2-audit Skill

    30★ repo

    Skills for your skills. Create, test, audit, package, and visualize Agent Skill libraries—locally.

  • Basic sample api auditor

    saeed-vayghan/gemini-agent-skills/.agent/skills/basic-sample-api-auditor Skill

    30★ repo

    A comprehensive collection of expert AI Agent Skills for Google Gemini, featuring a powerful CLI to convert and optimize Claude Code agents for the Gemini ecosystem.

  • Dbmcp

    haymon-ai/dbmcp/ai.haymon/dbmcp MCP server

    30★ repo

    Database MCP server for MySQL, MariaDB, PostgreSQL & SQLite with PII redaction and write-prevention

  • Iso27001 mcp

    Sushegaad/MCP-Server-for-ISO27001/io.github.Sushegaad/iso27001-mcp MCP server

    28★ repo

    ISO 27001 compliance workspace for Claude. Risks, policies, SoA, evidence, and audit workflows.

  • Audit project

    eldermoraes/quarkus-agentic-scaffolding/skills/audit-project Skill

    27★ repo

    Scaffolding skill + always-on conventions (CLAUDE.md/AGENTS.md) for Quarkus + LangChain4j agentic AI apps: AI services, multi-agent workflows, and RAG. Installable in Claude Code, Codex, Copilot, Cursor, and any Agent Skills-compatible agent.

  • Argument governance

    yha9806/academic-writing-toolkit/.claude/skills/argument-governance Skill

    27★ repo

    Local-first, evidence-controlled academic writing workflows for AI agents, with bounded revision, clean-room review, and release governance.

  • Seo audit

    wonfull888/seo-audit Skill

    25★

    SEO Audit Skill is an AI-powered SEO auditing tool based on Google Search guidelines and the Ahrefs SEO checklist. Runs in any skill-enabled CLI (Claude Code recommended). Covers 92 checks with results comparable to paid tools—using minimal tokens.

  • Aegis

    myclaude-sh/myclaude-creator-engine/.claude/skills/aegis Skill

    24★ repo

    The creation pipeline for Claude Code products — research, create, validate, publish. 13 types, 20 quality patterns, zero coding required.

All 7,541 in the catalog