Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 551 files from 1 750 authors, of which 61 898 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Analyzing dependencies, circular references, and God Classes; authoring ADRs/RFCs. Use for architecture improvement, module decomposition, and technical debt assessment.
Authoring unified specification packages across Business/Development/Design teams via staged elaboration (L0 Vision → L1 Requirements → L2 Team Detail → L3 Acceptance Criteria). No code. Use when authoring cross-team specs, building L0-L3 packages, or aligning Biz/Dev/Design on a single source of truth.
Verifying spec compliance by extracting ACs from specs, adversarially checking implementation conformance, and generating BDD scenarios, traceability matrices, and evidence-based compliance reports. No code. Use when verifying impl matches spec (PRD/SRS/AC) or producing machine-adjudicated conformance proof for a PR.
Orchestrating super-premium landing-page studio chains. Orchestrates the full LP pipeline (Discover → Audience → Strategy → Structure → Design → Build → Optimize → Verify → Launch) across 6 craft axes (Design/Animation/Branding/Marketing/SEO/IA) with explicit rubrics and quality gates. Use when a request asks for a complete, conversion-tuned, brand-defining LP. Not for single LP section (Funnel), design-only pipeline (Atelier), product-wide build (Titan), generic orchestration (Nexus), or A/B execution (Experiment).
Orchestrating design-to-implementation pipelines (code-to-visual-to-code closed loop). Persists a project design system across downstream agents. Use when a request spans design extraction, prototypes, visual assets, slides, and production together. Not for single-token tweaks (Muse), single prototype (Forge), direction only (Vision), or generic orchestration (Nexus).
Designing new skill agents via gap analysis, overlap detection, SKILL.md + reference generation, and Nexus integration. Do not use for task orchestration (Nexus), app architecture (Atlas), or format-only audits (Gauge).
Designing retention strategy, re-engagement, and churn prevention. Covers retention analysis frameworks, re-engagement trigger design, gamification elements, habit formation design, and loyalty programs. Use when engagement tactics are needed.
Engineering observability and reliability through SLO/SLI design, distributed tracing, alerting, dashboards, capacity planning, toil automation, and reliability review. Use when designing observability instrumentation, defining SLOs/SLIs, building dashboards/alerts, or reviewing reliability posture.
Optimizing frontend (re-render reduction, memoization, lazy loading) and backend (N+1 fix, indexing, caching, async) performance, including continuous auto-tuning loops (profile → parameter → optimize → verify for GC/threadpool/pool/cache/worker settings — absorbed from dial). Use when one-shot speed improvement or continuous tuning is needed.
Visualizing code/designs/context as Mermaid, ASCII, or draw.io diagrams. Reverse-generates flowcharts and sequence/state/class/ER diagrams from code or specs. Also handles Journey Maps, Emotion Score, Persona, Team Structure, DX Journey, and test telemetry visualizations (coverage heatmaps, traceability matrices, test-shape views — absorbed from vista). Use when generating diagrams from code/specs or reverse-documenting systems visually.
Implementing robust business logic, API integrations, and data models with type safety and production readiness. Use when business logic implementation or API integration is needed. Offers an interactive pair-programming mode (co-implement, confirming each increment).
Assessing standards compliance and analyzing gaps. Evaluates codebases against OWASP/WCAG/OpenAPI/ISO 25010 standards, detects violations, provides actionable remediation with citations. Use when checking industry-standard compliance (security/a11y/API/quality) or producing citation-backed audit reports.
Designing red team attack scenarios, building threat models, applying MITRE ATT&CK/OWASP frameworks, running Purple Team exercises, and performing AI/LLM red teaming. Use when adversarial security validation is needed.
Casting personas via rapid generation, persistence, lifecycle management, and inter-agent sync. Generates personas from diverse inputs, manages via a registry, evolves data-driven, and distributes in unified format. Use when creating, updating, or syncing personas across agents. Not for UI walkthroughs (Echo) or user research design (Field).
Auditing skill/plugin/MCP supply chains. Treats SKILL.md, bundled scripts, MCP server defs, hooks, and `.claude/` config as third-party software. Generates sha256 manifests, scans for Unicode Tag injection, detects curl-pipe + credential-exfil patterns, enforces third-party intake checklist, and pins MCP tool descriptions against rug-pulls. Use when auditing skill/MCP supply chain. Not for app SAST (Sentinel), CI/CD (Gear/Pipe), hook design (Latch), SKILL.md format (Gauge), or runtime exploit (Probe).
Engineering privacy and data governance via PII detection, data flow mapping, consent management patterns, GDPR/CCPA-compliant code implementation, and DPIA facilitation. Use when privacy-by-design implementation is needed.
Navigating the skill ecosystem and guiding onboarding. Lists agents, recommends best fit for tasks. Don't use for task execution (Nexus), agent design (Architect).
Reviewing legal documents for Terms of Service, Privacy Policy, and Tokushoho compliance. Detects clause gaps, flags risks, and aligns regulatory requirements. Don't use when legal advice is needed — consult a lawyer.
Researching competitors, analyzing differentiation, and shaping strategic positioning. Covers feature matrices, SWOT, benchmarking, positioning maps, battle cards, win/loss, and LLM brand visibility. Research only — no code. Use when scoping competitive landscape, building positioning artifacts, or assessing LLM brand visibility.
Designing cryptographic architecture: algorithm selection, key management, E2EE, KMS integration, signature verification, and TLS configuration. Use when designing cryptographic protocols, key rotation flows, or end-to-end encryption architectures.
Building engineer self-branding by transforming technical contributions into a professional brand. Use when GitHub/LinkedIn/blog/conference/SNS positioning, profile optimization, or content strategy is needed.
Writing video scripts, storyboards, and narration designs. Used for product videos, explainer videos, and onboarding content planning.
Scanning supply-chain malware infections via IoC-based local scan + safe eradication for npm/PyPI worm campaigns (Shai-Hulud, S1ngularity, lottie-player). Detects OS persistence (LaunchAgent/systemd), IDE-hook implants (.claude/.vscode/.github/workflows), lockfile-pinned malicious versions, and C2/exfil traces. Sequences credential rotation so revocation does not trigger `rm -rf ~/` retaliation payloads. Use when worm infection is suspected. Not for SAST (Sentinel), skill/MCP audit (Chain), Sigma/YARA (Vigil), or incident coordination (Triage).
Orchestrating ecosystem self-evolution by detecting project lifecycle phases, evaluating agent relevance, synthesizing cross-agent knowledge, and proposing evolution actions (health checks, fitness scoring, structural proposals). Use when auditing skill-ecosystem health, scoring agent fitness, or proposing structural evolution.
Simulating users (beginners, seniors, mobile users, etc.) via persona-based cognitive walkthroughs to evaluate UI flows, report confusion points, and score emotional friction. Use when usability validation or UX problem discovery is needed.
Producing automated feature demo videos via Playwright E2E tests. Covers scenario design, recording configuration, implementation patterns, and quality checklists for product demos and onboarding materials.
Designing A/B tests, documenting hypotheses, calculating sample sizes, implementing feature flags, and analyzing statistical significance. Covers CUPED variance reduction, SRM detection, and switchback experiments. Use when hypothesis validation is needed.
Refracting thinking by challenging assumptions, combining cross-domain knowledge, and shifting perspectives to reframe problems. Use when breaking through stuck situations or paradigm shifts are needed. Does not write code.
Implementing CSS/JS animations for hover effects, loading states, modal transitions, and gesture interactions. Use when adding meaningful motion, improving interaction feedback, or implementing performance-safe animations.
Conducting user research via interview guides, usability test plans, qualitative data analysis, persona creation, and journey mapping. Complements Echo's UI validation. Use when user research design or analysis is needed.
Building rapid prototypes for both frontend (UI components/pages) and backend (API mocks/simple servers). Use when validating new features or turning ideas into working demos. Prioritize working software over perfection.
Constructing landing pages end-to-end via structure design, conversion strategy, CTA optimization, and responsive design. Use when creating or improving landing pages.
Extracting and structuring design context from Figma via MCP Server for downstream implementation agents. Use when Figma-to-code bridging, Code Connect management, or design system rule extraction is needed.
Designing and reviewing APIs via OpenAPI spec generation, versioning strategy, breaking change detection, and REST/GraphQL best practices. Ensures API quality and consistency. Use when API design or OpenAPI specs are needed.
Designing regex, parsers, and DSLs for grammar authoring and ReDoS-safe regex. Not for REST APIs (Gateway) or DB schemas (Schema).
Auditing SKILL.md normalization and self-evolving compliance. Scans SKILL.md files against the 19-item checklist, classifies violations, produces fix snippets, and researches emerging best practices. No code. Use when auditing SKILL.md compliance, generating fix recommendations, or running ecosystem health dashboards.
Designing, optimizing, and auditing repository structure. Covers directory design, docs/ layout (PRD, specs, ADR), test/script organization, anti-pattern detection, and migration planning for existing repositories.
Managing dependencies, CI/CD optimization, Docker configuration, and operational observability (logging/alerting/health checks). Use when build errors, dev environment issues, or operational config fixes are needed.
Collecting GitHub PR data and generating work reports. Retrieves PR info via gh commands to auto-generate weekly/monthly reports and release notes. Use when work reporting or PR analysis is needed.
Optimizing SEO (meta/OGP/JSON-LD/heading hierarchy), SMO (social sharing), CRO (CTA/form/exit-intent), and GEO (AI citation optimization) across four pillars. Use when search ranking, conversion, or AI visibility improvement is needed.
Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy. Use when PR preparation or commit strategy is needed.
Simulating business strategy via short/mid/long-term scenario planning from financial, market, and competitive data. Applies SWOT/PESTLE/Porter analysis, KPI forecasting, and strategic roadmap generation. Does not write code.
Auditing and optimizing AI CLI configuration. Audits Codex CLI (~/.codex/), Antigravity CLI (~/.gemini/ — `agy`), and Claude Code (~/.claude/) configs (config.toml/settings.json/CLAUDE.md/hooks/MCP) and proposes Before/After diff improvements. Never edits configs directly. Use when auditing AI CLI configs, optimizing prompt cache hierarchy, or reviewing hooks/MCP/plugins security posture.
Generating, optimizing, and auditing personal development environment config files (zsh/tmux/neovim/ghostty), and automating the macOS desktop via AppleScript/JXA/osascript (Finder, Mail, Safari, Calendar, Notes, System Events). Use when dotfile management, shell/terminal/editor configuration, or Mac app automation and Apple Events scripting is needed.
Reviewing code via multi-engine orchestration. Orchestrates parallel review via subagents with grounding verification, shipping only findings worth fixing. Reviews on three axes — secure, correct, and lean. Default Claude + Codex (dual-engine); agy optional third axis. Use for PR review or pre-commit checks — detects bugs, vulnerabilities, logic errors, waste, and intent misalignment. Offers an interactive pair-review mode (fix-as-you-go). Complements Zen refactoring.
Generating SVG icons/illustrations, designing icon systems, and constructing sprite symbols. Use when vector assets are needed.
Comprehending and investigating codebases. Systematically performs structure mapping, feature discovery, and data flow tracing for "does X exist?", "how does Y work?", or "what is this module's responsibility?". Includes a conversational Q&A mode ("ask") for navigator-style, multi-turn questions about a project. Does not write code.
Deliberating decisions via multi-perspective lenses (Logos/Pathos/Sophia) for architecture arbitration, trade-offs, Go/No-Go, and strategic decisions. Does not write code. Don't use for architecture (Atlas), requirements (Accord), or implementation (Builder).
Planning, executing, and tracking releases in a unified workflow. Covers versioning strategy, CHANGELOG generation, release notes, rollback plans, and feature flag design for safe, predictable delivery.
Optimizing FinOps and cloud costs. Cost estimation from IaC, right-sizing, RI/SP recommendations, anomaly detection, budget alerts, AI/GPU workload cost analysis. Use when forecasting cloud spend, optimizing instance/reservation mix, designing budget alerts, or modeling AI/GPU economics.
Controlling combinatorial explosion across multi-dimensional axes via universal combinatorial analysis. Selects minimum coverage sets, generates execution plans, and prioritizes across test/deploy/UX/risk/compatibility. No code. Use when scoping multi-axis combinations or selecting minimum-coverage subsets under combinatorial explosion.
Designing a project's operating layer — the blueprint of which project-local skills, repo-tailored recipes (task playbooks), and skill-and-agent orchestration workflows a repository needs, designed together as a coherent system. Analyzes the repo, designs the layer, then delegates skill-body authoring to Sigil and runtime routing to Nexus. Use when a repository needs a coordinated set of project agents, recipes, and orchestration workflows designed together. Don't use for authoring a single skill body (Sigil), runtime request orchestration (Nexus), autonomous loop runners (Orbit), application or business-process workflows and code-level state machines (Weave), or ecosystem-wide global agents (Architect).
Proposing, configuring, debugging, and maintaining Claude Code hooks (PreToolUse/PostToolUse/Stop and other lifecycle events). Use when workflow automation, quality gates, or security enforcement via hooks is needed.
Curating cross-agent knowledge and guarding institutional memory. Extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices, prevents organizational forgetting. Use when consolidating cross-agent insights, curating memory, or auditing knowledge decay.
Generating test data and fixtures. Use when factory pattern design, boundary value data generation, synthetic data generation, or seed data management is needed.
Defining and managing design tokens, applying token systems to existing codebases, and building design system foundations. Covers token architecture for spacing, color, typography, dark mode, and cross-platform output.
Remediating known failure patterns automatically. Receives Triage diagnoses and Beacon alerts, executes runbooks with safety-tier classification, staged verification, and rollback. Use when automated incident remediation is needed.
Converting document formats (Markdown/Word/Excel/PDF/HTML). Converts specs from Scribe and reports from Harvest into distributable formats; generates reusable conversion scripts. Use when converting documents, building accessibility-compliant PDFs, or creating Pandoc/LibreOffice pipelines.
Orchestrating specialist AI agent teams as a meta-coordinator. Decomposes requests into minimum viable chains, spawns each as an independent session in AUTORUN modes, and drives to final output. Use when a task spans multiple specialist domains, requires parallel agent execution, or needs hub-and-spoke routing across the skill ecosystem.
Auditing regulatory compliance and mapping business requirements (SOC2/PCI-DSS/HIPAA/ISO 27001), checking control implementations, designing audit trails, and implementing Policy as Code. Use when compliance auditing is needed.
Claude Skills — questions
Answers built from the skills we actually parsed.