Security
ovhcloud-live-kms-key-destruction-guard
Gate and audit OVHcloud KMS key version destruction requests by enforcing five mandatory checks: confirmed key ID and KMS service URN, named approving identity, usage audit confirm…
DevOps
playbook-cli-audit
Audit all packmind-* skills for CLI compatibility issues: deprecated commands, invalid options, wrong file formats, missing flags, and version mismatches against the locally instal…
Security
defi-risk-analysis
Analyze a DeFi protocol's risk profile across smart contract, off-chain, and track-record dimensions. Use when the user wants a risk analysis of a DeFi project, to check protocol s…
Automation
goal-evidence-ledger
Maintains append-only evidence ledgers as sidecar files under `.flow/runs/<run-id>/evidence/`, storing structured metadata in `.evidence.yaml` and raw outputs in matching `.txt` fi…
Business
fz-personalkosten-und-stundennachweis
Defines eligible personnel costs for the research tax credit: gross wages plus employer contributions, 70-euro hourly flat rate for owner-managers, and 60 percent (70 percent for S…
Engineering
audit-deep
Composite skill — full project health check across testing, config, hooks, performance, security, MCP, and plugins. Runs audit skills in parallel and reconciles into one severity-r…
Productivity
utility-pm-critic
Runs adversarial review on a PM artifact via the pm-critic sub-agent. Dispatches natively on Claude Code with the pm-skills plugin; on other clients reads agents/pm-critic.md and e…
Business
pm-progress-auditor
Audit a status update, exec review, board email, all-hands talking point, or dashboard callout for credibility leaks before sending. Flags overstated claims, cherry-picked windows,…
Business
stb-drv-sozialversicherungspruefung
DRV social security audit support. Four-year review cycle under § 28p SGB IV. Focuses on status determination, managing directors, bogus self-employment, mini/midijobs, phantom wag…
Testing
agenttrace
Local-first TUI/CLI for post-run agent session audits — cost/token spikes, tool failures, retry loops, latency gaps, health scores, anomalies, session-to-session diffs. No upload, …
Business
the-support-machine
Converts The Support Machine book into an executable field guide for planning, auditing, or operating AI customer support on B2B or technical products. Diagnose friction, evaluate …
Productivity
utility-pm-skill-auditor
Runs a repo-wide governance audit via the pm-skill-auditor sub-agent. Dispatches natively on Claude Code with the pm-skills plugin; on other clients reads agents/pm-skill-auditor.m…
Engineering
entity-mapper-expert
Implement JPA Entity Long FK strategy with BaseAuditEntity/SoftDeletableEntity inheritance and EntityMapper Domain⇄Entity conversion. Prohibits JPA relationship annotations and Lom…
Security
l5-red-team-auditor
Performs an uncompromising L5 Enterprise Red Team Audit on a given plugin against the 39-point architectural maturity matrix. Trigger when the user requests a security audit, red t…
Security
owasp-mobile-security-checker
Perform security audits, vulnerability assessments, or compliance checks on Flutter or mobile applications. Covers OWASP Mobile Top 10 (2024) — hardcoded secrets, insecure storage,…
General
blog-geo
AI citation readiness audit scoring blog posts for citability in ChatGPT, Perplexity, Gemini, and Google AI Overviews. Evaluates passage-level citability, Q&A formatting, entity cl…
Security
repo-first-defense
Defensive security audit for AI-native repositories. Activate before launching, merging, updating dependencies, migrating package managers, configuring AI agents, or when supply ch…
Business
pruefer-uebergabe-paket
Assembles the complete auditor package after a Würfel run: Excel cube export, PDF report, evidence chain CSV, audit trail excerpt, prompt versions, consistency report, risk aggrega…
Research
cowork.audit_foucault
Applies Foucault-based audit filters across a Zettelkasten vault using a five-layer read pattern. Input: audit candidate. Output: audit_foucault_v1.yaml covering disciplinary power…
DevOps
openclaw-config-ops
Safely inspect, audit, and change OpenClaw configuration and model/provider setup. Use when working with `openclaw.json`, validating config hygiene, enforcing backup/change-control…
Research
referee2
Performs systematic audit and review in two modes: deck reviews for rhetoric, visual quality, and compile cleanliness; code reviews for cross-language replication and econometric a…
Documentation
os-decision
Records a new decision in DECISION_LOG.md using the canonical format: running ID, date, decision, rationale, status, plus version bump in Document Control. Invoke on phrases like "…
Web
seo-a11y-audit
Composite workflow that runs a full SEO and accessibility audit of a website or webapp. Chains multiple specialized scans into one severity-ranked report split by SEO, accessibilit…
Research
cowork.audit_freire
Runs Freire-based audit filters across a Zettelkasten vault using a five-layer read pattern. Input: audit candidate. Output: audit_freire_v1.yaml covering banking vs. problem-posin…
Automation
zapier-status
Check the health of your Zapier MCP setup. Three modes — health check (dashboard view), audit (find waste and duplicates), diagnose (systematic troubleshooting). Use when asking "i…
Security
review-security
White-box security audit with parallel isolated blue-team and red-team passes. Findings are synthesized into four buckets—anchoring-suppressed, convergent, blue-flagged-unverified,…
Business
dsa-art-34-systemische-risikobewertung
Conduct annual systemic risk assessments under DSA Article 34 for VLOP/VLOSE platforms. Document risks across illegal content, fundamental rights, civic discourse, and minor protec…
Web
raweb-audit
Audit web pages and components against RAWeb 1.1 for Luxembourg accessibility compliance. Reviews existing code, generates reports, checks conformance levels, and prepares for cert…
Business
lease-compliance
Audit commercial lease compliance systems including CAM reconciliation accuracy, lease abstraction completeness, critical date tracking, clause compliance monitoring, tenant obliga…
General
website-ai-discoverability-audit
Audits a public website for search crawlability, structured data, sitemaps, robots.txt, optional llms.txt, and major AI crawler policies. Produces an evidence-based report with ven…
DevOps
kafka-topic-audit
Audits Kafka topic configurations against production standards for replication factor, retention, partitions, compaction, naming, and metadata completeness. Use for health checks, …
Security
doncheli-security
Perform OWASP Top 10 static security audits identifying vulnerabilities in access control, cryptography, injection, configuration, and logging. Activate on mentions of "security au…
General
course-quality-review
Performs evidence-based course quality audits aligned with Quality Matters and Community of Inquiry frameworks. Evaluates structural quality, teaching/social/cognitive presence, an…
Security
loom-security-scan
Lightweight security checks for secrets, dependencies, container images, and common vulnerabilities. Suitable for pre-commit and CI scans using Semgrep, Trivy, gitleaks, cargo audi…
Productivity
minutes-lint
Health-check your meeting knowledge for contradictions, stale commitments, and decision conflicts. Use when the user asks about conflicts in meetings, stale action items, wants to …
Web
seo-metadata-audit
Perform a comprehensive SEO metadata audit on any webpage or HTML document using the 10 most important HTML meta tags. Triggers on URL shares, HTML sources, or requests about title…
Web
eds-project-health
Audit an AEM Edge Delivery Services project's codebase for best practices, boilerplate currency, CSS scoping issues, block structure quality, performance patterns, and configuratio…
Engineering
inspect
Deep audit comparing plan versus implementation. Parses plan files or descriptions, extracts requirements, and evaluates completeness, quality, and gaps across multiple dimensions.…
Business
ads-apple
Deep analysis for Apple Ads (formerly Apple Search Ads) aimed at mobile app advertisers. Reviews campaign structure, bid health, Custom Product Pages, MMP attribution, budget pacin…
Business
hochrisiko-risikomanagementsystem-art-9
Risk management system obligations for high-risk AI providers under Article 9 of the EU AI Act: continuous iterative process covering risk identification, assessment, mitigation, a…
Security
x-ray
Generates an x-ray.md pre-audit report covering overview, enhanced threat model, protocol profiling, attack surfaces, risk analysis, invariants, integrations, docs quality, and tes…
Research
ara-research-manager
Captures research provenance as a session epilogue by scanning conversation history to extract decisions, experiments, dead ends, claims, heuristics, and pivots, then writes them t…
Documentation
auto-improving-agents-md
Sets up, structures, and continuously improves AGENTS.md files: bootstraps with self-improvement rules, audits existing files against instruction budgets, performs end-of-session r…
AI / ML
aio
Agentic Implementation Optimizer audits existing agentic systems for reliability, cost, and architecture issues; scaffolds new agents from scratch or extends existing ones. Covers …
Design
deer-sense
Sense accessibility barriers with gentle awareness. Listen to the forest, scan for obstacles, test the paths, guide toward inclusion, and protect all wanderers. Use when auditing a…
Testing
gloss-review
Stage 8 interlinear evaluator — audit completeness and correctness of candidate interlinear artifacts, benchmark them against ground truth, and decide pass/block/promote. Use for e…
Security
hm-security
Deep security audit (L1/L2/L3) before external deployment, after adding auth/sensitive data/financial flows, or for periodic maintenance. Covers CIS Docker, OWASP Top 10, ASVS, com…
General
red-team
Runs adversarial course design audits across alignment, evidence, cognitive load, learner personas, and prerequisite integrity. Produces a 0-100 confidence score in a clean-context…
Engineering
code-cleanup-helper
Two-mode tool. Mode A scans codebases, SKILL.md files, and prompts for duplication, naming issues, modularity gaps, and excessive length. Mode B audits repos for private/public syn…
Security
login-forensics
Investigate Salesforce login activity with LoginHistory, IdentityVerificationHistory, and Login Forensics. Reconstruct user timelines, review failed logins and IPs, analyze verific…
Testing
mobile-sweep
Detects mobile layout issues including clipped content, undersized touch targets, text overflow, and modals exceeding viewport bounds. Captures screenshots at 360px, 390px, and 768…
Automation
ozm-record-surface-management
Keeps OZM-governed control surfaces such as task cards, receipts, ledgers, state files, evidence hashes, audit receipts, active windows, and maps synchronized with live progress to…
Productivity
phoenix-skills-audit
Audit recent changes to Phoenix user-facing surfaces and update the external agent skills for phoenix-tracing, phoenix-cli, and phoenix-evals to stay synchronized. Use when syncing…
Web
blog-locale-audit
Audit multilingual blog directories for completeness, consistency, hreflang correctness, meta-tag parity, and freshness. Builds translation coverage matrices, flags stale content, …
Engineering
logic-fix-all
Run a consent-gated repository-wide audit-and-fix pipeline covering health review, root-cause location, remediation, and diff verification until clean. Triggered by requests to res…
Testing
agent-experience
Audit developer experience of products, SDKs, docs, or SKILL.md files by deploying multiple agents with minimal prompts and real tooling. Captures traces, scores on friction and re…
Documentation
maintain-project-accessibility
Maintain canonical ACCESSIBILITY.md files with deterministic audit and bounded apply modes. Use when a project needs documented standards, implementation expectations, testing cove…
Testing
sql-plan-audit
Run EXPLAIN QUERY PLAN against every query in a sqlc-style catalog and diff the plans against a baseline. Detects new full-table SCANs and TEMP B-TREE sort scans introduced by PRs.…
Engineering
workflow-codebase-audit
Performs cold-start, time-boxed, multi-axis audits of unfamiliar codebases for assessments, due diligence, onboarding, or tech-debt reviews; dispatches sub-agents for deeper sweeps…
Productivity
pi-cli
Unified project analysis CLI with DAG scheduling, LLM batch tasks, dependency graph building, test analysis/fix, doc generation, code audit, and Web Dashboard. Matches project-inde…
Showing the top 60 of 1,388. See the full list →