Audit & compliance
7,456 rows, by stacks then stars
1,290 of these skill files have been read, by 960 distinct authors, and what they tell an agent counted. What Audit & compliance authors agree on, and what they forbid
andr-ca/agentharness/.claude/skills/audit-review-followup Skill
1★ repoUse when asked to check whether review/audit recommendations were actually implemented, whether gaps were closed, or to re-score the repo — verifies claims against repo state instead of trusting status reports.
andr-ca/agentharness/.claude/skills/dependency-audit Skill
1★ repoUse when adding dependencies, reviewing a project's dependency tree, or checking for known vulnerabilities and ownership risk — covers pip-audit, npm audit, govulncheck, lock file hygiene, update policy, and trust assessment.
Paldom/node-skills/skills/node-supply-chain Skill
1★ repoHardens the npm supply chain - lockfile discipline, Dependabot cooldown and groups, per-package-manager install-script policy, provenance verification, npm token hygiene, SHA-pinned Actions. Use when the user asks to secure dependencies, audit npm packages, respond to a compromised dependency, or pin actions. Not for repo settings like rulesets/secret scanning, or publishing.
jeremyinthebay/relay-skills/skills/llm-feature-adversarial-audit Skill
1★ repoAdversarially audit an LLM-backed product feature for the exploit classes users actually find — client-controlled conversation history injecting false facts, XSS on rendered model output or user input, cost/kill-switch adequacy under variable payload size, auth/metering bypass, and secret handling. Use before shipping or reviewing an AI chat/assistant feature, before trusting client-supplied conversation history or documents, when adding a budget cap or kill switch to an LLM feature, or when someone asks "is our AI feature safe," "can this be jailbroken," or "can a user make it say/do something it shouldn't."
Chevis-Zhou/agent-skills/skills/session-audit Skill
1★ repoEnd-of-session audit that scans for uncaptured corrections, preferences, and decisions, then proposes saving each one to the right file in the user's workspace. Trigger phrase: 'audit this session'. Also activates on 'session audit', 'what did we miss', or 'end of session check'.
dineshrevunuru/SuperSkills/audit-accessibility Skill
1★ repoRun a WCAG-grounded accessibility audit on a design, prototype, or live page, severity-rate every finding, and enforce the hard accessibility launch gate. Use when asked to 'audit accessibility', 'check a11y', 'is this accessible?', 'run the accessibility gate', 'check contrast / keyboard / screen reader / focus states / target sizes', or before ANY external-facing launch or handoff — nothing Dinesh ships skips this gate. Also use to decide whether assistive-tech user testing is needed on top of the audit.
Document and govern design system
dineshrevunuru/SuperSkills/document-and-govern-design-system Skill
1★ repoDocuments design-system components (variants, states, props, usage rules, content standards) and runs system governance — NN/g 6-dimension maturity assessment to pick the highest-leverage gap, contribution rules, review cycles with yes/no criteria, versioning and deprecation. Use when asked to 'document this component', 'write usage guidelines', 'audit our design system', 'set up a contribution process', 'people keep building one-offs', 'the system is drifting', or 'where should we invest in the design system next'. NOT for creating token values (build-token-system) or designing new component states (design-ui-states).
dineshrevunuru/SuperSkills/govern-research-ethics Skill
1★ repoThe canonical research-ethics GATE — consent, participant data/PII, retention, and compensation — loaded BEFORE you recruit or hit record, the way name-and-control-bias is loaded before trusting a finding. Sized for a solo/freelance operator, not a corporate legal department: it covers what the RESEARCHER personally owes a participant on top of whatever a client NDA already handles. Use when the ask is 'do I need consent?', 'is it okay to record?', 'how do I handle their data', 'what do I do with the recordings', 'GDPR/CCPA for research', 'how much do I pay participants', 'they told me something really personal', 'this participant seems vulnerable', 'the client wants them to sign an NDA', or before ANY session with a real person. Consent is a process, not a signature; ethics is a gate, not a footnote.
NSBen/skillfoundry/src/skillfoundry/data/starter_skills/security-audit Skill
1★ repoUse when reviewing code for common vulnerabilities (SQL injection, XSS, leaked secrets, unsafe eval) and proposing concrete fixes.
vishuwa2004/cskill-agents/agents/claude-code/skills/cli-command-surface-audit Skill
1★ repoAudit a command surface end to end so registration, discoverability, permissions, and execution all line up before shipping.
The same file is in 1 other repository
vishuwa2004/cskill-agents/agents/codex/skills/cli-command-surface-audit Skill
1★ repoAudit a command surface end to end so registration, discoverability, permissions, and execution all line up before shipping.
The same file is in 1 other repository
vishuwa2004/cskill-agents/skills/cli-command-surface-audit Skill
1★ repoAudit a command surface end to end so registration, discoverability, permissions, and execution all line up before shipping.
The same file is in 1 other repository
rrpauls/hermes-esra/optional-skills/evolutionary-self-dev/loop-auditor Skill
1★ repoActivate loop-auditor to periodically review and improve the Self-Evolution Loop itself. Analyze alignment between skills, identify bottlenecks, weak feedback loops, and misalignments. Propose structural improvements to the development system. Works with self-improver and mental-model-updater. Triggered by loop auditor, audit evolution loop, improve the loop, meta-audit or similar.
erenisci/acta/skills/legal Skill
0★ repoRegion-aware legal briefs (KVKK/GDPR/CCPA/PIPL/APPI…) — warn you, brief a lawyer; never binding legal text, always "get a lawyer". Trigger on /acta:legal, "legal docs", "privacy policy", "GDPR/KVKK".
mnox/mnox-ai/plugins/compliance-review/skills/compliance-review Skill
0★ repoUse when auditing a target for regulatory compliance against SOC 2, HIPAA Security Rule, or PCI-DSS - reviewing code/config repos, ADRs/PRDs, IaC posture, or live cloud state for control gaps. Triggers - /compliance-review, compliance audit, SOC 2 review, HIPAA review, PCI-DSS review, is this compliant, check compliance, audit against controls, PHI or CHD handling review. Auto-detects input mode, fans out parallel control-domain agents, and produces structured findings with control IDs, severity, evidence, remediation, confidence, plus an out-of-scope section for human-attestation controls.
puretechnyc/purebrain-skills/skills/marketing/google-ads-audit Skill
0★ repoWeekly Google Ads campaign health check. Pull data via API, analyze performance, generate actionable optimization recommendations with copy-paste fixes.
knckknck/skills/skills/wcag-audit-patterns Skill
0★ repoConduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.
The same file is in 44 other repositories
giovicordova/skills-gc/skills/verify Skill
no license0★ repoAudits Claude's own output against the user's original request in the current session — did Claude do exactly what was asked, no more, no less? Checks requirements, styles, constraints, and flags scope creep (extras the user never asked for). Use when the user says "verify", "check your work", "did you follow my request", "audit this", "compliance check", or questions whether Claude improvised, missed something, or added unrequested features. This is specifically about holding Claude accountable to the user's brief — NOT for reviewing other people's code, checking external systems, debugging config files, running tests, or verifying things Claude didn't create.
giovicordova/skills-gc/skills/website-audit Skill
no license0★ repoAudits any website for SEO, AEO (Answer Engine Optimization), GEO (Generative Engine Optimization), and Structured Data. Crawls with Playwright, runs Lighthouse, checks Perplexity citations, applies research-backed rules, scores deterministically, and produces a prioritised fix list with letter grades. Use this skill whenever the user mentions a domain or URL and wants to know what's wrong with it from an SEO, content, structured data, or AI-readiness perspective — even if they don't use the word 'audit'. Triggers include: auditing a website, checking SEO issues, evaluating AI-readiness or answer-engine optimisation, comparing two sites or documentation portals, reviewing structured data or JSON-LD, checking robots.txt AI crawler policy, running a website health check, assessing whether content will appear in Perplexity/ChatGPT search results, or any request for a scored website quality analysis. Also triggers on: /website-audit [domain] [categories...]
thinkyou0714/claude-lab-skills/lab-data-auth-ops/skills/audit-log-design Skill
0★ repo「誰が・いつ・何をしたか」を後から追跡できる監査ログを設計する。重要操作・権限変更・データアクセスを記録する仕組みを決める前に使う。
thinkyou0714/claude-lab-skills/lab-data-auth-ops/skills/pii-handling-review Skill
0★ repo個人情報(PII)の収集・保存・利用・開示・削除が、最小化と保護の原則に沿っているかをレビューする。PII を扱う機能の設計・公開の前に使う。
thinkyou0714/claude-lab-skills/lab-thinking-core/skills/assumption-audit Skill
0★ repo設計・仕様・計画に埋め込まれた前提を洗い出し、未検証の前提が判断を歪めていないかを確認する。設計レビュー前、ADR作成前、重要な技術選定前に使う。
Clinical-Quality-Artifical-Intelligence/nhs-clinical-safety-skills/skills/review-fhir Skill
no license0★ repoFHIR Implementation Guide and resource review — terminology, profiling, and compliance audit for UK NHS FHIR projects. Covers FHIR R4 conformance, UK SNOMED/dm+d/LOINC terminology binding, UKCore/CareConnect compatibility, nursing-specific profiling (NEWS2, Waterlow, ADPIE), and IG structure. Produces a scored compliance report.
alexe-ev/product-plugins/product-ops/skills/audit-product-process Skill
0★ repoAudit the current state of product processes to identify bottlenecks, inconsistencies, and improvement opportunities. Use this skill when a product team wants to understand where their operating model is breaking down.
alexe-ev/product-plugins/product-ops/skills/automate-workflow-governance Skill
0★ repoIdentify automation opportunities in product workflows and establish governance standards. Use this skill when a team wants to reduce manual overhead in recurring product operations.
Assess privacy security regulatory
alexe-ev/product-plugins/risk-compliance/skills/assess-privacy-security-regulatory Skill
0★ repoIdentify and assess privacy, security, and regulatory risks in product decisions and features. Use this skill when a product decision may have privacy, security, or compliance implications.
alexe-ev/product-plugins/risk-compliance/skills/conduct-ai-audit Skill
0★ repoConduct a structured audit of an AI system or feature against responsible AI standards. Use this skill when a deployed AI feature needs to be evaluated for fairness, safety, transparency, and accountability.
telefrek/vallorcine/skills/audit Skill
0★ repoRun adversarial audit pipeline against shipped code
bokuwalily/claude-code-skills/skills/claude-plugin-context-audit Skill
0★ repoセッション開始が重い/応答が直近指示を取りこぼす/context bloatが疑われるとき、SessionStartで注入される全ソース(プラグイン・rules/ecc・obsidian文脈・auto-memory・remember)のトークン内訳を測定して刈り込み候補を特定したいとき
bokuwalily/claude-code-skills/skills/excel-filtered-url-http-audit Skill
0★ repoスプレッドシート(Excel/CSV)から条件列でURLを絞り込み、並列HTTP取得でDOM内の特定要素の有無を判定し、結果をCSVに分類出力する。コンテンツ監査・CTA設置確認・SEOチェックなどに繰り返し使える。
bokuwalily/claude-code-skills/skills/wp-http-article-audit Skill
0★ repoWordPressサイトのURLリストを並列HTTPで一括取得し、記事上部エリア(article~最初のh2間)の特定CTAの設置状況を分類・CSV出力するときに使う
Saturate/skills/codebase-audit Skill
no license0★ repoPerforms comprehensive codebase audit checking architecture, tech debt, security vulnerabilities, test coverage, documentation, dependencies, and maintainability. Use when auditing a project, assessing codebase health, running security scans, checking for vulnerabilities, reviewing code quality, analyzing tech debt, or asked to audit/analyze the entire codebase.
Saturate/skills/validate-skill Skill
no license0★ repoValidates Claude Code skills against official best practices from Anthropic documentation. Fetches latest documentation dynamically to ensure current standards. Checks frontmatter, structure, line count, descriptions, references, workflows, and provides actionable recommendations. Use when asked to validate skill, check skill quality, review skill, or audit skill compliance.
kennyolofsson23-netizen/claude-code-config/skills/ai-marketing-suite/skills/market-audit Skill
no license0★ repoThe most comprehensive Claude Code setup — 29 skills, 9 plugins, 13 hooks, 8 agents, 8 commands. Self-documenting, self-improving, CLI-first. Includes self-interview prompt for personalization.
kennyolofsson23-netizen/claude-code-config/skills/audit-context-building Skill
no license0★ repoEnables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.
The same file is in 7 other repositories
kennyolofsson23-netizen/claude-code-config/skills/claude-ads/ads Skill
no license0★ repoComprehensive paid advertising audit and optimization for any business type. Performs full multi-platform audits (Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, Microsoft Ads), single-platform deep analysis, conversion tracking health checks, creative quality assessment, budget allocation optimization, bidding strategy evaluation, and compliance verification. Industry detection for SaaS, e-commerce, local service, B2B enterprise, info products, mobile app, real estate, healthcare, finance, and agency. Triggers on: ads, PPC, paid advertising, Google Ads, Meta Ads, Facebook Ads, LinkedIn Ads, TikTok Ads, Microsoft Ads, Bing Ads, ad audit, campaign audit, ROAS, conversion tracking, creative fatigue, bid strategy, brand DNA, generate ads, create campaign, product photography, ad creative generation.
kennyolofsson23-netizen/claude-code-config/skills/claude-ads/skills/ads-audit Skill
no license0★ repoFull multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads accounts. Generates health score per platform and aggregate score. Use when user says "audit", "full ad check", "analyze my ads", "account health check", or "PPC audit".
The same file is in 1 other repository
kennyolofsson23-netizen/claude-code-config/skills/claude-ads/skills/ads-creative Skill
no license0★ repoCross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative fatigue, evaluates platform-native compliance, and provides production priorities. Use when user says "creative audit", "ad creative", "creative fatigue", "ad copy", "ad design", or "creative review".
kennyolofsson23-netizen/claude-code-config/skills/geo-audit Skill
no license0★ repoFull website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.
The same file is in 1 other repository
kennyolofsson23-netizen/claude-code-config/skills/nielsen-heuristics-audit Skill
no license0★ repoEvaluate UX/UI using Jakob Nielsen's 10 usability heuristics. Comprehensive audit of visibility, control, consistency, error prevention, recognition, flexibility, aesthetics, error recovery, and documentation.
kennyolofsson23-netizen/claude-code-config/skills/security-audit Skill
no license0★ repoComprehensive security audit: detects insecure defaults, hardcoded secrets, sharp edges, supply chain risks, and OWASP vulnerabilities. Based on Trail of Bits methodology. Use when auditing security, reviewing config, or pre-deployment checks. For PR diffs, use /security-review instead.
kennyolofsson23-netizen/claude-code-config/skills/seo-audit Skill
no license0★ repoWhen the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup. For AI search optimization, see ai-seo.
The same file is in 2 other repositories
kennyolofsson23-netizen/claude-code-config/skills/ux-audit-rethink Skill
no license0★ repoComprehensive UX audit using IxDF's 7 factors, 5 usability characteristics, and 5 interaction dimensions. Holistic evaluation with redesign proposals based on user-centered design principles.
kennyolofsson23-netizen/claude-code-config/skills/wcag-accessibility-audit Skill
no license0★ repoComprehensive web accessibility audit using WCAG 2.1/2.2 guidelines. Evaluate compliance across 4 POUR principles (Perceivable, Operable, Understandable, Robust) with A, AA, AAA conformance levels.
kennyolofsson23-netizen/claude-code-config/skills/web-design-guidelines Skill
no license0★ repoReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
The same file is in 38 other repositories
kennyolofsson23-netizen/claude-code-config/skills/web-quality-audit Skill
no license0★ repoComprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".
The same file is in 4 other repositories
jimmynotjames/simple-recurring-budgets/.claude/skills/audit-translations Skill
no license0★ repoAudit the existing non-English translations in Localizable.xcstrings for quality — tone, formality register, cultural appropriateness, length/truncation risk, and accuracy — then emit a re-translation manifest for the flagged subset. Drives the scripts/translate_audit/ pipeline with parallel per-locale Opus subagents. Use to run a translation quality audit, or to re-check specific locales/keys after re-translating.
jimmynotjames/simple-recurring-budgets/.cursor/skills/audit-translations Skill
no license0★ repoAudit the existing non-English translations in Localizable.xcstrings for quality — tone, formality register, cultural appropriateness, length/truncation risk, and accuracy — then emit a re-translation manifest for the flagged subset. Drives the scripts/translate_audit/ pipeline with parallel per-locale Opus subagents. Use to run a translation quality audit, or to re-check specific locales/keys after re-translating.
hsnuhow/how-skills/plugins/ponytail/skills/ponytail-audit Skill
no license0★ repoWhole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", "ponytail-audit", or "/ponytail-audit". One-shot report, does not apply fixes.
The same file is in 3 other repositories
Chase-Key/aurelion-skills/skills/rell-domain Skill
0★ repoThe RELL compliance audit engine — architecture, philosophy, active modules, and development status.
Chase-Key/aurelion-skills/.cursor/skills/rell-domain Skill
0★ repoThe RELL compliance audit engine — architecture, philosophy, active modules, and development status.
Chase-Key/aurelion-skills/.gemini/skills/rell-domain Skill
0★ repoThe RELL compliance audit engine — architecture, philosophy, active modules, and development status.
Chase-Key/aurelion-skills/.github/skills/rell-domain Skill
0★ repoThe RELL compliance audit engine — architecture, philosophy, active modules, and development status.
Chase-Key/aurelion-skills/.windsurf/skills/rell-domain Skill
0★ repoThe RELL compliance audit engine — architecture, philosophy, active modules, and development status.
Studio-Moser/skills-n-stuff/plugins/site-capture/skills/audit Skill
0★ repoAudit existing screenshot captures for quality issues. Checks every PNG file in a directory for wrong-company content, blank sections, cookie banners, error pages, and other problems. Reports what needs recapturing. Use when screenshots look wrong or after a batch capture to verify quality. Invoke with /site-capture:audit.
Evan-Daruwalla/claude-skill-suite/cron-task-manage Skill
0★ repoWindows scheduled-task auditor, READ-ONLY execution always — the only thing it ever shells out to is `schtasks /query`. audit (default) parses the CSV task list and flags the unhealthy ones: Last Result != 0 (with the code), Disabled state, and — for an ENABLED task — a Next Run Time that is N/A or already in the past. Scope defaults to non-Microsoft tasks (--all / --like <substr> to widen or narrow). plan mode PRINTS the exact `schtasks /create` line for you to run yourself; the tool NEVER runs /create, /delete, or /change. Use when the user says "audit my scheduled tasks", "did the scheduled task run", "why did the rebalance task fail", "check the cron/scheduled job", "is that task disabled", "what's the schtasks command to create X", "cron-task-manage". --fixture parses a saved query capture offline. Deterministic, zero dependencies, no model calls.
Evan-Daruwalla/claude-skill-suite/cve-audit Skill
0★ repoDependency-vulnerability audit with a deterministic parse/report core. Runs `npm audit --json` (npm projects) and `pip-audit --format json` (Python) and turns the raw report into a severity table (critical/high/moderate/low) with package names and counts, failing the build at/above a configurable fail-level (default high). Also parses a SAVED npm-audit JSON offline (`--fixture`) for CI logs and reproducible checks. If pip-audit is not installed it says so with the install hint — it never fakes Python results. Use when the user says "audit dependencies", "cve audit", "check for vulnerable packages", "npm audit", "pip-audit", "are my deps vulnerable", "scan dependencies for CVEs", or gates a release on dependency vulnerabilities. Zero dependencies, no model calls.
Evan-Daruwalla/claude-skill-suite/data-integrity-audit Skill
0★ repoRead-only SQLite integrity audit — no dependencies, no writes, no model calls. Opens a database READ-ONLY (file: URI mode=ro) and runs three checks: PRAGMA integrity_check (structural corruption), PRAGMA foreign_key_check (SQLite's own dangling-FK sweep), and explicit orphan detection that counts child rows whose foreign-key value has no parent — catching orphans even when foreign_keys enforcement was OFF at insert time. Reports per-check PASS/FAIL with row counts and the first 5 offending rowids; exit 1 on any failure. Use when the user says "audit the database", "check DB integrity", "find orphaned rows", "foreign key check", "is the SQLite file corrupt", "data-integrity-audit", or before trusting a SQLite DB that a process may have written with FK enforcement off.
Evan-Daruwalla/claude-skill-suite/path-quirk-audit Skill
0★ repoRead-only tree scan for documented Windows path/file corruption classes — the traps that silently break a .bat parse, a shell script, a JSON file, or a Windows checkout before they cost a debugging session. Flags: .bat/.cmd holding ANY non-ASCII byte (one byte corrupts the whole batch parse — reports the offset), .sh/.bash with CRLF endings, .json with a UTF-8 BOM or invalid UTF-8, scan-root files whose name shadows a cmd builtin (echo/type/sort/find/time/date/ path/exit/set) or is purely numeric ("12"), and filename pairs colliding by case on NTFS. Use when the user says "path-quirk-audit", "scan for windows file quirks", "check for bat/encoding/case landmines", "audit the tree for corruption traps", or before shipping a repo that runs on Windows. This is the proactive sweep — pair it with your own symptom-side runbook to fix what it finds. Deterministic, zero deps.
pramodmax/openshift-ai-skills/maas-governance-expert Skill
0★ repoEnterprise specialist in implementing Models-as-a-Service (MaaS) governance with Kubernetes CRDs, Kuadrant policies, token quotas, rate limiting, and tier-based access control on OpenShift AI