Use REUSE when an agent needs file-level licensing clarity instead of guessing from a single top-level LICENSE file.
Use Avoid AI Writing when an agent needs a repeatable audit, rewrite, or in-place edit workflow for removing AI writing patterns from draft prose.
Audit completo del backend .NET 10 / Minimal APIs / C# 14. Analizza dead code, conformità ai pattern del progetto e opportunità di performance.
Inventory the integrations, private apps, and internal tooling that call HubSpot APIs, and flag anything on legacy v1-v4 endpoints ahead of HubSpot's March 30, 2027 end of…
提交前审核关卡。读取用户收集的所有文件、/start-here 的范围、 求情信，进行整体合规性+一致性检查。标注不一致（姓名、日期、 金额在不同文件间不匹配）、缺漏（必备文件缺失）、薄弱点 （回国承诺模糊、行程不一致）。当用户说"审核我的申请"、 "我准备好了吗"，或 80%+ 文件齐备准备提交时使用。这是 TLS…
Audit which subagents and skills bypass approval; flag any that touch untrusted input
Archives non-permanent URLs in legal document footnotes using the perma.cc API, then writes the resulting perma.cc links back to the DOCX file.
UDS 健康检查与反馈系统。诊断安装完整性、检测开发模式、识别摩擦点。 使用时机：检查 UDS 安装、报告问题、发现规范化机会。 关键字：audit, health, pattern, friction, feedback, 审计, 健康, 模式, 摩擦, 反馈。
Augments Trailmark code graphs with external audit findings from SARIF static analysis results and weAudit annotation files.
Audit backend code for SQL safety, error handling, auth coverage, PII exposure, dead code, TODO density
Für Audit: Schriftsatz-, Brief- und Memo-Bausteine: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Accept currently-open audit findings into .audit-baseline.json with a per-finding reason, so re-runs show only NEW findings and accepted debt never resurfaces.
Use when a company's board wants to systematically evaluate its own performance — running a structured self-assessment of the full board, individual directors, and committees on a…
Reports per-plugin skill description token contributions to help reduce session startup budget. Use when /doctor shows skill descriptions dropped.
Analyze historical bug patterns by mining Claude Code project logs for /autoskillit:investigate skill invocations since a specified date.
Coverage-maximizing adversarial audit — volume over precision, every file, every pattern, every hunch
Audit recurring workflows and installed skills to recommend evidence-backed skill updates, additions, or removals, based on repeated procedures rather than recurring topics.
Local-first, event-driven RAG for commercial real estate audit & investigation case folders. Index a case directory named like \"项目问题编号__标题\" (with stage subfolders such as…
컴플라이언스 감사를 위한 체계적 체크리스트 생성 엔진. 'status-auditor'와 'remediation-planner' 에이전트가 현황 진단과 개선 계획을 수립할 때 이 스킬의 감사 프레임워크와 체크리스트 템플릿을 반드시 활용해야 한다. '감사 체크리스트', '이행 점검표', '준수 현황 평가' 등에 사용한다.
Audit CI/CD pipelines (GitHub Actions) for cost, speed, and safety. Use when the GitHub Actions bill is high, when the user mentions Actions minutes, runner cost, workflow cost,…
Run CodeBurn locally or as an MCP server so agents can inspect token usage, cost, model mix, project spend, and budget waste across coding tools.
Canonical shared references for the audit skills — subsystem inventory format, worker review brief and output schema, and validation/synthesis passes.
Drafts board-adopted charters establishing Audit and Compensation Committees for U.S. corporations, covering composition, independence, delegated powers, meeting protocol,…
Drafts a combined Audit and Compensation Committee charter for U.S. boards, tailored for public or private companies with listing-standard compliance, independence criteria, and…
Use when the goal is to reduce code size, remove unnecessary complexity, or simplify a module without removing user-facing behavior.
Check that your legal compliance is still in good shape. Pick what to check: your privacy policy, your privacy vendor list, or your contract templates.
Audit project config against latest claude-conf — fix drift, clean duplicates, optimize CLAUDE.md
Audit persistent workspace configurations (instructions, skills, rules, MCPs, memory) for redundant, outdated, conflicting items.
Audit academy materials for outdated references, deprecated patterns, and stale content
Evaluates ambient context artifacts (CLAUDE.md, memory, local skills, settings hooks) for compatibility with swarm governance.
Audit the agent context files (CLAUDE.md, AGENTS.md) at the project root and the user's home directory: cut what does not change a decision, disambiguate what two readers would…
Audit segregation of duties and chart-of-accounts hygiene before trusting the books. Reach for this on a controls or data-quality question.
Audit MVP component, platform mechanism, and advanced mechanism coverage for analyzed agents, identifying gaps and suggesting next steps
Autonomer Audit-Orchestrator. Liest eine konfigurierte Aufgaben-Quelle (Notion, Linear, GitHub Issues, Markdown-Inbox), schreibt Audits, spawnt Agent Teams, reviewt, merged,…
Use when a manuscript's supra/infra cross-references need to stop being hand-typed numbers — 'my supra notes point at the wrong footnote', 'the cross-references broke after I…
Audit train/test leakage, memorization artifacts, temporal leakage, and disclosure pathways that can invalidate evaluation.
Use when applying Graham's specific quantitative criteria for defensive (conservative) stock selection — checking a candidate against numeric thresholds for valuation, debt,…
The "Structural Critic" that audits specialist output and issues a binary PASS or BLOCKED verdict. No track is complete until the Quality Gate approves.
Skill de auditoría destilada para el flujo "devground-init". Acumula el conocimiento de auditorías previas: invariantes confirmadas, falsos positivos ya descartados, y edge cases…
Audit a codebase's documentation (README, SKILL.md, AGENTS.md, etc.) for gaps against the actual implementation. Finds undocumented commands, flags, config fields, and behaviors.
Read-only audit of custom lint and ratchet rules: is each rule right on the merits, not just enforced.
Read note timeliness and medical-necessity completeness as one revenue-and-compliance control — operationally, never as a clinical judgment.
Report which credential variables a Bash subprocess and its ancestors can see. Test fixture for the pr-run-activity runner.
Read-only audit of config/env parity across dev, staging, and prod — missing or misnamed vars, drifted flags, hardcoded values, secrets reused across environments.
Inforcer's read-only record of changes and activity: searching and filtering auditEvents by type and date window (the search is account-wide — there is no tenant filter),…
Guides privacy audit evidence collection processes including evidence planning, sampling strategies, documentation standards, chain of custody, interview techniques, system…
Export audit findings from markdown report files to Teamwork-compatible CSV format for project management tools (Jira, Monday, Linear also supported).
Use when the user wants to review, audit, lint, or sanity-check the settings.py and tenants.yaml of a fastloom-based service.
Audit completo del frontend del progetto. Rileva automaticamente lo stack usato, poi analizza dead code, conformità ai pattern e opportunità di performance.
Scan the current repo and score its feedback loop maturity for AI-assisted development
Audit a ported Scala file against its original source — runs shortcuts, compare, stale-stubs, and records the result
Audit, learn, index, refresh, search, or compare a user's signed-in food-delivery order history in Fullwell, including provider selection, complete order and modifier evidence,…
Scan Claude Code project logs for friction patterns — repeated failures, approach loops, tool errors, misunderstanding cycles, and stuck workflows.
Read-only audit of CI gate logic: silent bypass, ratchet gaming, required-but-not, duplicate gates. Use when "can CI be bypassed" or "why did a regression pass CI".
Use when assessing an organization's compliance with the General Data Protection Regulation
Gate bắt buộc trước mỗi lần push GitHub — gitleaks + quét thông tin nhạy cảm (production IP, production domain, domain nội bộ acegalaxy...).
Read-only GNADD alignment audit: load workflow principles, scrutinize context files for describe-vs-track violations, perform a shallow git/workflow check, and return a…
Produce a license inventory for Go module dependencies before release, procurement review, or open-source due diligence.
Start or continue Fullwell grocery-history onboarding and audit purchases for snacks, ingredients, condiments, and other groceries in one pass, including store scope, browser…
Audits the resident steering layer — CLAUDE.md/AGENTS.md and its `@import` chain, `.claude/rules/`, hooks, permission rules, and the skill descriptors preloaded every session —…