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
alexpialetski/doccraft/.claude/skills/doccraft-queue-audit Skill
4★ repoReconcile the dependency graph, pick-next queue, and backlog status across docs/stories/, docs/queue.md, and docs/backlog.md. Use after adding or editing a story (especially one with depends_on), after reshuffling priorities, or when the user asks "what can I work on next", "what's unblocked", "sanity-check the queue", "check my story dependencies", "fix the queue order", or "what parallel work is ready". In Agent mode (the tool can write files), apply objective mechanical fixes in the same turn and report what changed; in Ask / read-only mode, emit a proposal instead. Stop and report — never guess — on directed cycles, unknown depends_on ids, duplicate ids, or ambiguous editorial reorders.
alexpialetski/doccraft/templates/skills/doccraft-queue-audit Skill
4★ repoReconcile the dependency graph, pick-next queue, and backlog status across {{DOCS_DIR}}/stories/, {{DOCS_DIR}}/queue.md, and {{DOCS_DIR}}/backlog.md. Use after adding or editing a story (especially one with depends_on), after reshuffling priorities, or when the user asks "what can I work on next", "what's unblocked", "sanity-check the queue", "check my story dependencies", "fix the queue order", or "what parallel work is ready". In Agent mode (the tool can write files), apply objective mechanical fixes in the same turn and report what changed; in Ask / read-only mode, emit a proposal instead. Stop and report — never guess — on directed cycles, unknown depends_on ids, duplicate ids, or ambiguous editorial reorders.
BechsteinDigital/claude-shiploop/role-auditor Skill
4★ repoUse when the overall state of the repo needs checking (not a diff) — before releases, after major rework, at milestone gates, or periodically: pattern consistency, module boundaries, security posture, rule compliance, doc drift. Not for package reviews (→ role-reviewer).
roodlicht/accans-sec-skills/skills/audit-evidence Skill
no license4★ repoEvidence collection and packaging for security audits — evidence types (inspection/observation/inquiry/re-performance/automated), cadence per control, chain of custody, period tagging, WORM storage and retention, auditor delivery. Usable for SOC 2, ISO 27001, NIS2, DORA, and internal audits.
roodlicht/accans-sec-skills/skills/gdpr-pia Skill
no license4★ repoData Protection Impact Assessment (DPIA / GEB) workflow against AVG Art 35 — trigger check (AP criteria and WP 248), systematic description, necessity, risk analysis from the data subject's perspective, measures and residual risk, prior consultation with the Autoriteit Persoonsgegevens.
roodlicht/accans-sec-skills/skills/ir-runbook Skill
no license4★ repoIncident Response runbook — NIST SP 800-61 phases (Preparation/Detection-Analysis/Containment-Eradication-Recovery/Lessons-Learned), per-scenario playbooks (ransomware, BEC, data exfil, credential compromise, cloud), regulatory reporting (NIS2 24h/72h, AVG breach 72h, DORA), comms templates, and post-incident review.
roodlicht/accans-sec-skills/skills/soc2 Skill
no license4★ repoSOC 2 Type II prep — AICPA Trust Services Criteria (Security required plus Availability/Confidentiality/Processing Integrity/Privacy), Common Criteria CC1–CC9, Type I vs Type II choice, evidence-collection rhythm, auditor-friendly packaging, Complementary User Entity Controls.
roodlicht/accans-sec-skills/skills/supply-chain Skill
no license4★ repoSoftware supply-chain defense — SBOM generation (CycloneDX/SPDX), SLSA build provenance, artifact signing with sigstore/cosign, dependency-confusion and typosquat defense, and consumer-side verification of what you pull in.
roodlicht/accans-sec-skills/skills/vendor-questionnaire Skill
no license4★ repoVendor security questionnaire workflow — vendor tiering, standardized questionnaires (CAIQ, SIG-Lite/Core, VSA), custom authoring, evidence reuse against existing attestations (SOC 2, ISO 27001), and ongoing vendor-risk monitoring.
celticht32/Couchbase-Skills-for-Claude.ai/skills/couchbase/couchbase-security-hardening Skill
4★ repoHarden and audit Couchbase security posture for production deployments. Use whenever the user asks about TLS configuration, mTLS, certificate management, LDAP integration, SAML, PAM authentication, audit logging, audit log configuration, network isolation, firewall rules for Couchbase, RBAC design, least-privilege, password policy, account lockout (8.x), encryption at rest (DARE), KMIP key management, compliance (SOC2, HIPAA, PCI-DSS, FedRAMP), security hardening checklist, admin_encryption_*, admin_kmip_*, or 'how do I secure Couchbase for production.' Distinct from couchbase-mcp (calling the tools) and couchbase-app-integration (TLS in SDK clients). Use proactively for new production deployments, compliance reviews, security audits, and pre-certification hardening.
goww7/halalterminal-claude-skills/skills/halal-portfolio-audit Skill
4★ repoAudit an existing portfolio (list of holdings with weights or values) for Shariah compliance. Produces per-stock results, aggregate compliant %, purification owed, and remediation suggestions for non-compliant names. Does NOT build new portfolios (that's halal-portfolio-builder).
goww7/halalterminal-claude-skills/skills/halal-verdict Skill
4★ repoUse when the user asks whether a specific stock is Shariah-compliant ("Is X halal?", "Screen TSLA", "Compliance of AAPL"). Produces a single-stock verdict across all 5 methodologies (AAOIFI, DJIM, FTSE, MSCI, S&P), explains any failures, and suggests a halal alternative if non-compliant. Does NOT cover ETFs (use halal-etf-analysis) or portfolios (use halal-portfolio-audit).
KhaledSaeed18/dotclaude/.claude-plugin/plugins/security/skills/dependency-audit Skill
4★ repoAudit a project's dependencies for outdated and vulnerable packages and surface breaking-change notes for upgrades. Works with any ecosystem, including npm/pnpm/yarn, pip/Poetry/uv, Cargo, Go modules, Maven/Gradle, Bundler, Composer, and others. Use when checking a project's dependency health, planning upgrades, or responding to a vulnerability report.
KhaledSaeed18/dotclaude/.claude-plugin/plugins/testing/skills/accessibility-audit Skill
4★ repoAudit UI code or a running page against WCAG 2.2 AA, covering semantics, keyboard access, focus management, labels, contrast, ARIA misuse, and motion, verifying in a real browser with axe-core when one is available and by code review when not. Produces findings ranked by user impact with concrete fixes. Use when building or reviewing UI components, before shipping user-facing pages, or when accessibility compliance is required.
KhaledSaeed18/dotclaude/skills/security/dependency-audit Skill
4★ repoAudit a project's dependencies for outdated and vulnerable packages and surface breaking-change notes for upgrades. Works with any ecosystem, including npm/pnpm/yarn, pip/Poetry/uv, Cargo, Go modules, Maven/Gradle, Bundler, Composer, and others. Use when checking a project's dependency health, planning upgrades, or responding to a vulnerability report.
KhaledSaeed18/dotclaude/skills/testing/accessibility-audit Skill
4★ repoAudit UI code or a running page against WCAG 2.2 AA, covering semantics, keyboard access, focus management, labels, contrast, ARIA misuse, and motion, verifying in a real browser with axe-core when one is available and by code review when not. Produces findings ranked by user impact with concrete fixes. Use when building or reviewing UI components, before shipping user-facing pages, or when accessibility compliance is required.
openEHR/ai-plugins/plugins/openehr-specs/skills/governance Skill
4★ repoManage the openEHR specification governance lifecycle — releases, change requests (CR/PR), and lifecycle states (DEVELOPMENT/TRIAL/STABLE…). This skill should be used when the user asks to create or tag a release, prepare a release branch, update the manifest for a release, submit or manage a CR/PR, promote a spec's status, or discuss the openEHR change process or Jira workflow. Not for clinical/archetype governance, amendment-record authoring (use amendment-record), or non-openEHR release management.
openEHR/ai-plugins/plugins/openehr-specs/skills/review Skill
4★ repoReview an openEHR specification document for quality, completeness, and convention compliance in `specifications-XX` repos. This skill should be used when the user asks to review, lint, or quality-check an openEHR spec, validate its conventions, or run a pre-release review. Not for archetype/template review (openehr-assistant plugin), the governance process (use governance), or non-openEHR documents.
akhilkannur/marketing-agent-blueprints/skills/attribution-modeler Skill
no license4★ repoFacebook says they drove the sale. Google says they did. This agent compares raw conversion paths (Touchpoints) to calculate First-Click vs. Last-Click vs. Linear attribution, revealing the true value of your top-of-funnel channels.
akhilkannur/marketing-agent-blueprints/skills/attribution-window-comparator Skill
no license4★ repoCompares revenue attributed under a 1-day click vs 7-day click window to understand ad latency.
akhilkannur/marketing-agent-blueprints/skills/canonical-tag-auditor Skill
no license4★ repoTechnical debt is invisible until traffic drops. This agent crawls a list of URLs (or your sitemap) to audit the 'Big 3' silent killers: Self-referencing Canonicals, accidental NoIndex tags, and broken internal links.
akhilkannur/marketing-agent-blueprints/skills/case-study-freshness-audit Skill
no license4★ repoFlags case studies published more than 24 months ago for retirement or refresh.
Imran-ml/claude-skills/.claude/skills/security-audit Skill
no license4★ repoUse this skill to perform a security audit, scan for vulnerabilities, check OWASP Top 10 issues, or review code for security problems. Triggered by "security audit", "check security", "find vulnerabilities".
davccavalcante/supreme-coding-guidelines-skill.ah/skills/supreme-ai-governance Skill
no license4★ repoFirst-in-the-world AI governance and compliance discipline for AI Governance Officers, Compliance Leads, Risk Managers, DPOs, Legal and Privacy Counsel, CISOs, Product and AI and ML and LLM engineers, LLM Architects, AI Researchers, internal Auditors, CTOs, and Founders who must place, operate, or certify AI systems responsibly across jurisdictions. Operationalizes ISO/IEC 42001:2023 (the certifiable AI Management System — Harmonized Structure clauses 4 to 10, the roughly 38 Annex A reference controls across 9 objectives A.2 to A.10, the Statement of Applicability, and the AI System Impact Assessment now backed by ISO/IEC 42005:2025) together with the EU AI Act (Regulation 2024/1689 — prohibited practices Art 5, high-risk Annex I and Annex III, transparency Art 50, GPAI and systemic-risk obligations, provider and deployer and importer and distributor roles, conformity assessment, CE marking, EU database registration, FRIA Art 27, post-market monitoring, serious-incident reporting, penalties up to 35M EUR or 7 percent of global turnover, and the June 2026 Digital Omnibus timeline that defers high-risk obligations toward December 2027 and August 2028 pending final adoption), the NIST AI Risk Management Framework (GOVERN MAP MEASURE MANAGE plus the Generative AI Profile NIST-AI-600-1), and the global regulatory map outside the EU (United States executive orders and Texas and Colorado and California and Utah and Illinois state laws, United Kingdom principles-based approach and the Data Use and Access Act 2025, China generative-AI and AI-content labeling rules, Canada Quebec Law 25 after AIDA lapsed, Brazil PL 2338, and the international instruments OECD UNESCO Council-of-Europe G7 and UN). Maps the sectoral overlays AI governance never escapes — GDPR Article 22 and DPIA, financial model risk, medical-device regimes, and employment bias-audit law. Integrates through the Harmonized Structure with ISO/IEC 27001 security, ISO/IEC 27701 privacy, and ISO 9001 quality (the Big-3 plus 42001 for compliant AI) and with the ISO/IEC SC42 standards family (22989 terminology, 23894 risk, 5338 life cycle, 5259 data quality, 25059 quality model, 42006 certification bodies, 38507 governance). Operates through four cognitive lenses — a First-Principle Thinker asking what governance is actually for and what would falsify a claim of responsible governance, an Expansionist surfacing ignored obligations and the market-access opportunity of certification, an Outsider taking the regulator and auditor and claimant view to find the evidence demanded on day one, and an Executor who never tries to please and reports real exposure instead of a green dashboard. Delivers a tabular gap assessment, a Statement of Applicability, a control map, an evidence register, and a remediation roadmap. Requires ah-parser. This skill is compliance-engineering structure and is not legal advice — verify current law before relying on any date or citation because regulation moves. Output mode follows user preference at parser activation; user policy, legal text, evidence, and control artifacts are preserved verbatim. Evidence over assertion, current law over stale citation, honest exposure over green dashboard.
davccavalcante/supreme-coding-guidelines-skill.ah/skills/supreme-npm-node Skill
no license4★ repoPrincipal NPM/NPX/NPMJS/Node engineering discipline for Tech Leads, DevOps, Backend Engineers, Frontend Engineers, Product Engineers, AI Engineers, ML Engineers, LLM Engineers, LLM Architects, AI Researchers, Quality Assurance Engineers, and Software Quality Engineers. Enforces a latest-version-always policy (never pin to definitive versions; always `ncu -u` before install), TypeScript strict mode with every check enabled (strict + noUncheckedIndexedAccess + exactOptionalPropertyTypes + useUnknownInCatchVariables + noImplicitOverride), `satisfies` over `as`, `unknown` over `any`, discriminated unions over optional flags, branded types for opaque identifiers. Covers Node ecosystem (current LTS or latest stable), package.json discipline (files allowlist over .npmignore, exports map with import/require/types conditional, engines node range, type:module default), publishing workflow (`npm pack --dry-run` preview, OIDC provenance attestation in GitHub Actions, semantic versioning via changesets/release-please, dist-tag next/beta/canary for previews), supply-chain reliability (npm audit gate, lockfile committed, no untrusted postinstall, attw type-correctness check), monorepo support (pnpm workspaces preferred), and continuous upgrade cadence (`ncu -u` weekly + Renovate/Dependabot + codemods on breaking upgrades). Requires ah-parser. Output mode follows the user preference set at parser activation; user package.json, lockfile, scripts, and command output are always preserved verbatim.
davccavalcante/supreme-coding-guidelines-skill.ah/skills/supreme-project-audit Skill
no license4★ repoEvidence-driven full-project audit skill for Product Engineers, AI Engineers, ML Engineers, LLM Engineers, LLM Architects, and AI Researchers. Enforces severity discipline (P0/P1/P2/P3 with objective criteria), explicit coverage maps (audited vs not-audited surface), threat modeling (STRIDE + OWASP LLM Top 10), reproducibility checks (seeds, pinned deps, versioned prompts, data snapshots), and a terse report contract (finding, location, severity, evidence, cause, fix, owner). Requires ah-parser. Output mode follows the user preference set at parser activation; user code, diffs, identifiers, and audit evidence quotes are always preserved verbatim.
nocodework/growth-os/core/skills/geo-audit Skill
4★ repoMeasure how visible a brand is inside AI assistants (ChatGPT, Gemini, Claude, Perplexity) for its ICP's real questions. Runs a repeatable protocol of ~15 natural-language queries, reads whether and how the brand shows up, and reports Visibility, Rank, Sentiment, Recommendation rate, Share of Voice, and citation domains. Use when someone runs /growth-os:geo-audit, says "am I visible in ChatGPT," "AI visibility," "do LLMs recommend us," "GEO baseline," or when the growth audit needs the GEO section.
cfregly/gpu-perf-tune/plugins/profile-and-optimize/skills/mirage-graph-coverage Skill
4★ repoRead-only coverage auditor for the mirage / MPK persistent-megakernel's GENERATED task graph: cross-references DECLARED tensors (all_tensors[...] in kernel_N.cu) against tensors CONSUMED by tasks (inputs/outputs base_ptr in task_graph_N.json) and flags any tensor declared but never consumed as an input - the "feature defined in code but never wired into the task graph" bug class (e.g. RoPE cos/sin tables allocated but consumed by 0 tasks => position-blind attention => incoherent / degenerate-repetition output). A numerics / relL2 harness silently PASSES on this class, so run THIS first when a megakernel compiles + exits 0 but emits incoherent output. Distinct from inference-graph-diff (vLLM FX / Inductor graphs). Triggers on "graph coverage", "task graph audit", "megakernel wiring", "declared but unconsumed tensor", "rope not wired", "missing task", or "megakernel / mirage / MPK / task-graph" with "coverage / wiring / unconsumed / unwired / audit".
megandmartin/agent-skills-repo/skills/research-analysis/seo-content-audit Skill
4★ repoAudit a single web page for SEO — title/meta, heading structure, search-intent match, internal links — and deliver quick wins ranked by effort vs impact. Use when the user says "audit this page", "why doesn't this page rank", "SEO check", "review my landing page for search", or pastes a URL asking how to improve its traffic. Don't use for tearing down a competitor's product and pricing — that's competitor-teardown — or for monitoring topic trends weekly — that's trend-radar.
jerseycheese/agent-skills/skills/code-health-audit Skill
4★ repoKicks off a recurring code-health audit — the "embarrassing code" / overengineering sweep that turns vague tech-debt anxiety into a short list of measurable, validated simplifications to ship. Bakes in the pre-flight discipline (sync the correct base branch, confirm the active worktree and its dev server, list files in scope) so the audit never runs against stale or wrong-worktree code. Trigger on: "embarrassing code audit", "overengineering audit", "code health audit", "find simplification candidates", "what can we simplify", "tech debt sweep", "audit the codebase", "find overengineered code", "what's embarrassing in this repo".
WilliamWJHuang/ab-test-causal-inference-skills/skills/data-quality-auditor Skill
4★ repoAudit data quality before analysis. Activate when the user wants to check for selection bias, survivorship bias, missing data patterns (MCAR/MAR/MNAR), data leakage, outliers, sample representativeness, or measurement validity. Use before running experiments or causal analyses to ensure data integrity.
ShinKev/kmp-skill-library/performance/compose-performance-audit Skill
no license4★ repoAudit and improve Compose Multiplatform (CMP) runtime performance from code review and architecture. Use when asked to diagnose slow rendering, janky scrolling, excessive recompositions, or performance issues in shared or Android Compose UI.
mhrsdev/AI-Agent-Skills-Library/organized-skills/frontend-ui-design/03-web-design-guidelines Skill
4★ 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
mhrsdev/AI-Agent-Skills-Library/organized-skills/frontend-ui-design/claude-design-auditor-skill Skill
4★ repoAudit designs against 19 rules across Figma files and code (HTML/CSS/React/Vue/Tailwind). Auto-detects framework and design system (MUI, Chakra, shadcn/ui, Ant Design, Radix, Bootstrap). Runs code superpowers across all 19 categories: aria, focus, contrast, tokens, responsive, motion, forms, navigation, spacing, states, microcopy, elevation, iconography/SVG. Flags color blindness risk. Audits dark patterns, ethical design, Nielsen's heuristics. Outputs before/after diffs, developer handoff reports, wireframe-to-spec. English and Korean. Triggers on: check my design, review my UI, audit my layout, is this accessible, design review, color contrast, WCAG, a11y, pixel perfect, Figma audit, CSS check, dark patterns, is this GDPR compliant, is this manipulative, is my form accessible, is my dark mode correct, wireframe to spec, heuristic review, Nielsen audit, usability heuristics, 디자인 검토, 접근성 확인, 색상 대비, 다크 패턴, 와이어프레임 스펙.
The same file is in 1 other repository
oleg-koval/agent-skills/packages/marketing/search-console-indexing-audit/adapters/cursor/skills/search-console-indexing-audit Skill
4★ repoAnalyze Google Search Console Coverage or indexing CSV exports and correlate them with repo and live-site SEO signals. Use for Chart.csv, Metadata.csv, Critical issues.csv, Non-critical issues.csv, sitemap/robots/canonical indexing problems, "Discovered - currently not indexed", redirect indexing buckets, or requests to fix Google indexing coverage.
oleg-koval/agent-skills/packages/marketing/search-console-indexing-audit/adapters/grok/skills/search-console-indexing-audit Skill
4★ repoAnalyze Google Search Console Coverage or indexing CSV exports and correlate them with repo and live-site SEO signals. Use for Chart.csv, Metadata.csv, Critical issues.csv, Non-critical issues.csv, sitemap/robots/canonical indexing problems, "Discovered - currently not indexed", redirect indexing buckets, or requests to fix Google indexing coverage.
oleg-koval/agent-skills/packages/software-development/skill-budget-audit Skill
4★ repoDiagnose and fix Claude Code's skill context budget overflow — identify heavy plugin bundles that exceed the 2% budget, remove domain-specific ones, deactivate rarely-used skill sets, and validate the warning clears. Use when Claude Code shows "Exceeded skills context budget" or skill descriptions are stripped.
oleg-koval/agent-skills/packages/software-development/skill-budget-audit/adapters/claude/skills/skill-budget-audit Skill
4★ repoDiagnose and fix Claude Code's skill context budget overflow — identify heavy plugin bundles that exceed the 2% budget, remove domain-specific ones, deactivate rarely-used skill sets, and validate the warning clears. Use when Claude Code shows "Exceeded skills context budget" or skill descriptions are stripped.
oleg-koval/agent-skills/packages/software-development/skill-budget-audit/adapters/grok/skills/skill-budget-audit Skill
4★ repoDiagnose and fix Claude Code's skill context budget overflow — identify heavy plugin bundles that exceed the 2% budget, remove domain-specific ones, deactivate rarely-used skill sets, and validate the warning clears. Use when Claude Code shows "Exceeded skills context budget" or skill descriptions are stripped.
vaquarkhan/compliance-agent-skills/skills/breach-incident-response Skill
4★ repoExecutes USA breach and security incident response—HIPAA Breach Notification Rule (45 CFR §164.400–414), HITECH 60-day notification, state breach laws, and SOC 2 CC7.4/CC7.5 incident management—for agent, MCP, and LLM-related events. Trigger when investigating suspected PHI/PII exposure, unauthorized MCP access, LLM data leakage, or preparing breach notifications. Do not use for preventive logging design (use audit-logging-integrity) or routine vulnerability scanning.
vaquarkhan/compliance-agent-skills/skills/ccpa-cpra-privacy-rights Skill
4★ repoImplements California Consumer Privacy Act (CCPA) as amended by the California Privacy Rights Act (CPRA)—Cal. Civ. Code §1798.100 et seq.—covering consumer rights to know, delete, correct, opt-out of sale/share, and limit use of sensitive personal information, plus DSAR workflows, privacy notices, and service provider contracts for AI/agent data handling. Trigger when processing California residents' personal information, operating DSAR programs, reviewing agent/LLM data flows for CPRA compliance, or auditing privacy notices and vendor agreements. Do not use for HIPAA-covered PHI workflows (use hipaa-privacy-minimum-necessary), PCI cardholder encryption (use pci-dss-encryption-key-management), or general vendor SOC reports without CPRA scope (use vendor-third-party-risk).
vaquarkhan/compliance-agent-skills/skills/cmmc-nist-800-171 Skill
4★ repoImplements CMMC 2.0 Level 2 assessments aligned to NIST SP 800-171 Revision 2 (110 security requirements across 14 families) for Controlled Unclassified Information (CUI) protection in the Defense Industrial Base (DIB), including SPRS score self-assessment, POA&M management, and government contract flow-down obligations under DFARS 252.204-7012/7019/7020. Trigger when preparing for CMMC Level 2 certification, calculating SPRS scores, auditing CUI enclaves, or mapping 800-171 practices to cloud and on-prem implementations. Do not use for FedRAMP Moderate federal cloud authorization (use fedramp-moderate-baseline), SOX financial ITGCs (use sox-itgc-audit), or HIPAA PHI workflows (use hipaa-technical-safeguards).
vaquarkhan/compliance-agent-skills/skills/compliance-as-code-governance Skill
4★ repoImplements policy-as-code and infrastructure compliance scanning—OPA/Rego policies, Terraform static analysis, CI gates, and drift remediation—for SOC 2, HIPAA, and PCI control enforcement. Trigger when codifying security policies, integrating Checkov/tfsec/Sentinel, or automating guardrails for agent/MCP deployments. Do not use for one-time manual audits (use framework-specific skills) or vendor BAA review (use hipaa-baa-vendor-assessment).
vaquarkhan/compliance-agent-skills/skills/fedramp-moderate-baseline Skill
4★ repoImplements FedRAMP Moderate baseline assessments using NIST SP 800-53 Revision 5 controls—authorization boundary definition, System Security Plan (SSP), Plan of Action and Milestones (POA&M), and continuous monitoring (ConMon)—with Cloud Service Provider (CSP) and agency customer responsibility matrices. Trigger when preparing FedRAMP authorization packages, assessing cloud offerings for federal customers, mapping 800-53 Rev 5 controls to CSF outcomes, or auditing ConMon deliverables (monthly POA&M, annual assessments). Do not use for CMMC/CUI defense contractor assessments (use cmmc-nist-800-171), SOX ITGC financial reporting controls (use sox-itgc-audit), or generic CSF gap analysis without FedRAMP artifacts (use nist-csf-2-assessment).
vaquarkhan/compliance-agent-skills/skills/gdpr-us-multinational Skill
4★ repoImplements GDPR compliance workflows for US-headquartered multinationals—EU/EEA/UK data subjects, Articles 5-7 lawful basis, Article 30 records of processing, Article 32 security, Articles 33-34 breach notification (72 hours), Article 35 DPIA, Standard Contractual Clauses, EU-US Data Privacy Framework adequacy, and DPA/subprocessor governance for agent/LLM cross-border transfers. Trigger when US companies process EU residents' data, deploying agents in EU regions, assessing LLM vendor international transfers, or preparing RoPA/DPIA for multinational privacy programs. Do not use for US state laws only (use us-state-privacy-laws or ccpa-cpra-privacy-rights), HIPAA PHI (use hipaa-technical-safeguards), or UK-only post-Brexit without EU scope (note UK GDPR parallels in references).
vaquarkhan/compliance-agent-skills/skills/glba-ffiec-financial-privacy Skill
4★ repoImplements Gramm-Leach-Bliley Act (GLBA) Safeguards Rule (16 CFR Part 314) and Privacy Rule (16 CFR Part 313) compliance aligned to FFIEC IT Examination Handbook modules for financial institutions—customer information protection, risk assessments, access controls, vendor oversight, and GLBA privacy notices (initial, annual, opt-out). Trigger when auditing banks, credit unions, fintech lenders, or insurance entities for GLBA Safeguards, preparing FFIEC cybersecurity examinations, reviewing customer information security programs, or harmonizing GLBA with state privacy laws. Do not use for California CPRA consumer rights alone (use ccpa-cpra-privacy-rights), PCI cardholder data controls (use pci-dss-encryption-key-management), or SOX 404 ITGC without GLBA customer information scope (use sox-itgc-audit).
vaquarkhan/compliance-agent-skills/skills/hipaa-baa-vendor-assessment Skill
4★ repoReviews Business Associate Agreements and subprocessors for LLM vendors, cloud providers, and MCP server operators under HIPAA (45 CFR §164.502(e), §164.504(e)). Trigger when onboarding OpenAI/Anthropic/Azure OpenAI, cloud hosts, observability tools, or MCP integrations that may access ePHI. Do not use for technical encryption testing (use hipaa-technical-safeguards) or general vendor SOC reports without BAA focus (use vendor-third-party-risk).
vaquarkhan/compliance-agent-skills/skills/hipaa-phi-redaction-pipeline Skill
4★ repoConfigures and validates the Presidio-based PHI redaction pipeline—DLP entity detection, reversible tokenization before LLM ingestion, and authorized deanonymization—integrated with redaction.py and the compliance agent. Trigger when ePHI may appear in prompts, implementing minimum-necessary LLM access, tuning entity types, or auditing redaction effectiveness. Do not use for HIPAA access control design (use hipaa-technical-safeguards) or legal BAA review (use hipaa-baa-vendor-assessment).
Hipaa privacy minimum necessary
vaquarkhan/compliance-agent-skills/skills/hipaa-privacy-minimum-necessary Skill
4★ repoImplements HIPAA Privacy Rule minimum necessary standard—45 CFR §164.502(b)—plus §164.514 de-identification, Limited Data Sets, and patient rights to access and amend records, with agent prompt minimization, role-based PHI exposure, and integration with the Presidio redaction pipeline. Trigger when designing LLM/agent PHI access policies, auditing disclosure practices, implementing patient rights workflows, or validating that agent prompts contain only minimum necessary ePHI. Do not use for Presidio entity tuning alone (use hipaa-phi-redaction-pipeline), Security Rule technical controls (use hipaa-technical-safeguards), or BAA legal review (use hipaa-baa-vendor-assessment).
vaquarkhan/compliance-agent-skills/skills/hipaa-technical-safeguards Skill
4★ repoImplements HIPAA Security Rule technical safeguards (45 CFR §164.312)—access control, audit controls, integrity, person/entity authentication, and transmission security—for AI agents, MCP servers, and LLM pipelines. Trigger when assessing ePHI handling in agent architectures, MCP tool authorization, encryption in transit/at rest, or mapping HIPAA controls to technical implementations. Do not use for BAA legal review (use hipaa-baa-vendor-assessment) or Presidio tokenization setup (use hipaa-phi-redaction-pipeline).
vaquarkhan/compliance-agent-skills/skills/iso27001-annex-a-controls Skill
4★ repoImplements ISO/IEC 27001:2022 Annex A control assessment—93 controls across Organizational, People, Physical, and Technological themes—covering Statement of Applicability (SoA), risk treatment, and implementation evidence. Trigger when building or auditing an ISMS, mapping Annex A to existing controls, preparing ISO 27001 certification, or assessing agent/MCP systems against ISO 27002:2022 guidance. Do not use for SOC 2 TSC mapping alone (use soc2-trust-services-criteria), IAM-only reviews (use access-control-identity-audit), or vendor SOC report review without ISO scope (use vendor-third-party-risk).
vaquarkhan/compliance-agent-skills/skills/mcp-compliance-integration Skill
4★ repoHardens Model Context Protocol (MCP) server integrations for compliance—OAuth 2.1, PKCE, scoped tool sets, transport security, and patterns for Playwright, Postgres, Slack, and Presidio MCP servers in audit workflows. Trigger when deploying, configuring, or auditing MCP servers for HIPAA, PCI, or SOC 2 agent architectures. Do not use for general IAM reviews without MCP focus (use access-control-identity-audit) or PCI script DOM audits (use pci-dss-script-audit).
vaquarkhan/compliance-agent-skills/skills/nist-ai-rmf-governance Skill
4★ repoImplements NIST AI Risk Management Framework (AI RMF 1.0, NIST AI 100-1)—GOVERN, MAP, MEASURE, and MANAGE functions—for trustworthy AI systems including LLM agents, MCP toolchains, and automated compliance workflows. Trigger when assessing AI governance, model risk, agent trustworthiness, GenAI deployment controls, or harmonizing AI RMF with NIST CSF 2.0 and ISO 42001 concepts. Do not use for general cybersecurity without AI scope (use nist-csf-2-assessment), HIPAA PHI controls alone (use hipaa-technical-safeguards), or EU AI Act (out of scope—use gdpr-us-multinational for privacy overlap only).
vaquarkhan/compliance-agent-skills/skills/nist-csf-2-assessment Skill
4★ repoPerforms NIST Cybersecurity Framework 2.0 gap assessments across six Functions—Govern, Identify, Protect, Detect, Respond, Recover—using CSF 2.0 categories, subcategories, Implementation Tiers, and Organizational Profiles. Trigger when benchmarking security posture, preparing executive risk reporting, assessing AI/agent system controls against NIST CSF, or harmonizing CSF with ISO 27001 or SOC 2 programs. Do not use for ISO 27001 SoA certification work (use iso27001-annex-a-controls), PCI CDE scoping (use pci-dss-network-segmentation), or HIPAA Privacy Rule minimum necessary (use hipaa-privacy-minimum-necessary).
Pci dss encryption key management
vaquarkhan/compliance-agent-skills/skills/pci-dss-encryption-key-management Skill
4★ repoAudits PCI-DSS v4.0 Requirement 3 (protect stored account data) and Requirement 4 (protect cardholder data with strong cryptography during transmission)—covering key management lifecycle, HSM usage, PAN masking, tokenization, and TLS 1.2+ enforcement with Terraform/Vault MCP patterns for evidence collection. Trigger when assessing encryption of CHD/SAD at rest or in transit, reviewing key rotation and split knowledge, validating tokenization scope reduction, or scanning IaC for crypto misconfigurations. Do not use for network segmentation (use pci-dss-network-segmentation), payment-page script inventory (use pci-dss-script-audit), or general IAM without crypto focus (use access-control-identity-audit).
vaquarkhan/compliance-agent-skills/skills/pci-dss-network-segmentation Skill
4★ repoValidates PCI-DSS v4.0 network segmentation and scope reduction—Requirement 1.x (firewalls, network security controls) and 2.x (secure configurations)—for Cardholder Data Environment (CDE) isolation. Trigger when scoping PCI environments, reviewing firewall rules, VLAN segmentation, agent/MCP access to CDE, or reducing assessment scope. Do not use for payment-page script audits (use pci-dss-script-audit) or general IAM reviews without CDE focus (use access-control-identity-audit).
vaquarkhan/compliance-agent-skills/skills/pci-dss-script-audit Skill
4★ repoAutomates PCI-DSS v4.0 Requirements 6.4.3 (payment-page script authorization, inventory, integrity hashes, and business justification) and 11.6.1 (weekly change/tamper detection for HTTP security headers and DOM scripts). Trigger when auditing ecommerce checkout or payment pages, validating third-party JavaScript governance, detecting unauthorized script or CSP changes, or producing PCI script inventory evidence. Do not use for backend server patching, network firewall rules, cardholder data storage encryption, or non-payment marketing pages.
Soc2 ccm continuous monitoring
vaquarkhan/compliance-agent-skills/skills/soc2-ccm-continuous-monitoring Skill
4★ repoImplements Continuous Control Monitoring (CCM) for SOC 2—automated control testing, configuration drift detection, predictive risk scoring, and alerting—for agent platforms, MCP servers, and cloud infrastructure. Trigger when building always-on compliance dashboards, detecting TSC control drift between audits, or operationalizing CC4/CC7 monitoring. Do not use for one-time evidence binders (use soc2-evidence-collection) or initial TSC mapping (use soc2-trust-services-criteria).
vaquarkhan/compliance-agent-skills/skills/soc2-evidence-collection Skill
4★ repoAutomates SOC 2 evidence gathering—screenshots, configuration exports, access reviews, log samples, and audit-trail packaging with integrity hashes—for AICPA TSC examinations. Trigger when preparing audit binders, populating Vanta/Drata-style evidence requests, or packaging agent/MCP compliance artifacts. Do not use for control mapping (use soc2-trust-services-criteria) or continuous drift monitoring (use soc2-ccm-continuous-monitoring).
vaquarkhan/compliance-agent-skills/skills/soc2-trust-services-criteria Skill
4★ repoMaps organizational controls and evidence to AICPA SOC 2 Trust Services Criteria (2017 TSC with 2022 revisions)—Security (CC), Availability (A), Confidentiality (C), Processing Integrity (PI), and Privacy (P). Trigger when scoping SOC 2 audits, gap assessments, control design reviews, or mapping agent/MCP architecture to TSC. Do not use for evidence collection mechanics (use soc2-evidence-collection) or continuous monitoring dashboards (use soc2-ccm-continuous-monitoring).