tech-leads-club/agent-skills

这个仓库里有 92 个技能，GitHub 星标 ★ 6,348。

• component-common-domain-detectionFinds duplicate business logic spread across multiple components and suggests co
• component-flattening-analysisDetects misplaced classes and fixes component hierarchy problems — finds code th
• component-identification-sizingMaps architectural components in a codebase and measures their size to identify
• coupling-analysisAnalyzes coupling between modules using the three-dimensional model (strength, d
• decomposition-planning-roadmapCreates step-by-step decomposition plans and migration roadmaps for breaking apa
• domain-analysisMaps business domains and suggests service boundaries in any codebase using DDD
• domain-identification-groupingGroups existing components into logical business domains to plan service-based a
• evolutionary-modular-architectureGuides design and implementation of evolutionary modular-monolith platforms with
• frontend-blueprintAI frontend specialist and design consultant that guides users through a structu
• legacy-migration-plannerUse when planning legacy system migrations, codebase modernization, monolith dec
• modular-decompositionRuns a sequenced monolith-to-modular pipeline that sizes and inventories compone
• modular-design-principles>
• react-composition-patternsReact composition patterns that scale. Use when refactoring components with bool
• tactical-dddDetects anemic domain models, validates and refactors them into rich domain mode
• aws-advisorExpert AWS Cloud Advisor for architecture design, security review, and implement
• cloudflare-deployDeploy applications and infrastructure to Cloudflare using Workers, Pages, and r
• netlify-deployDeploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when t
• render-deployDeploy applications to Render by analyzing codebases, generating render.yaml Blu
• vercel-deployDeploy applications and websites to Vercel. Use when the user requests deploymen
• create-adrCreates Architecture Decision Records (ADRs) to document significant architectur
• create-rfcCreates structured Request for Comments (RFC) documents for proposing and decidi
• technical-design-doc-creatorCreates comprehensive Technical Design Documents (TDD) with mandatory and option
• cursor-subagent-creatorCreates Cursor-specific AI subagents with isolated context for complex multi-ste
• skill-architectExpert guide for designing and building high-quality skills from scratch through
• subagent-creatorGuide for creating AI subagents with isolated context for complex multi-step wor
• the-foolUse when challenging ideas, plans, decisions, or proposals. Invoke to play devil
• the-juryUse when a question, decision, plan, tradeoff, or claim needs a rigorous verdict
• figmaUse the Figma MCP server to fetch design context, screenshots, variables, and as
• figma-implement-designTranslate Figma nodes into production-ready code with 1:1 visual fidelity using
• frontend-designCreate distinctive, production-grade frontend interfaces with high design qualit
• web-design-guidelinesReview UI code for Web Interface Guidelines compliance. Use when asked to "revie
• codenaviYour pathfinder for navigating unknown codebases. Investigates with precision, i
• coding-guidelinesBehavioral guidelines to reduce common LLM coding mistakes. Use when writing, mo
• confluence-assistantExpert in Confluence operations using Atlassian MCP. Use when the user says "sea
• docs-writerWrite, review, and edit documentation files with consistent structure, tone, and
• gh-address-commentsAddress review and issue comments on the open GitHub PR for the current branch u
• harness-evalEvaluate a repo agent harness (AGENTS.md, rules, skills, skill refs) for broken
• jira-assistantManage Jira issues via Atlassian MCP — search, create, update, transition status
• nestjs-modular-monolithSpecialist in designing and implementing scalable modular monolith architectures
• not-your-babysitterAutonomous senior-operator mode for AI agents that resolve tasks end to end with
• rails-devOpinionated Rails conventions: rich models, concerns, CRUD-everything, state-as-
• react-native-expertSenior React Native and Expo engineer for building production-ready cross-platfo
• shopify-developerComplete Shopify development reference covering Liquid templating, OS 2.0 themes
• spec-driven-evalScores how completely an implementation fulfills a PRD/spec, case by case, and p
• tlc-discoverInterviews an unshaped idea into a verdict and a design document with literal de
• tlc-implementImplement a work already planned: extracts a checklist, builds it, and proves ev
• tlc-planTurns decided work — a PRD, design doc, RFC, or thread — into tasks a builder ca
• tlc-spec-drivenFeature planning and implementation with 4 adaptive phases (Specify, Design, Tas
• tlc-spec-leanSpec-driven feature work that freezes obligations instead of the plan: one human
• ai-cold-outreachWhen the user wants to build an AI-powered outreach system, write cold emails, i
• ai-pricingWhen the user wants to price an AI product, choose a charge metric, design prici
• ai-sdrWhen the user wants to deploy AI sales development reps, automate sales qualific
• ai-seoWhen the user wants to build programmatic SEO with AI, create competitor alterna
• ai-ugc-adsWhen the user wants to create UGC ad campaigns, recruit UGC creators, generate A
• content-to-pipelineWhen the user wants to turn content into revenue, build a content-led GTM motion
• expansion-retentionWhen the user wants to reduce churn, build expansion revenue, automate customer
• gtm-engineeringWhen the user wants to build GTM automation with code, design workflow architect
• gtm-metricsWhen the user wants to define GTM metrics, build a metrics dashboard, measure pi
• lead-enrichmentWhen the user wants to build data enrichment workflows, score leads against ICP,
• multi-platform-launchWhen the user wants to launch a product across multiple platforms, plan a Produc
• paid-creative-aiWhen the user wants to create AI-generated ad creative, test performance creativ
• partner-affiliateWhen the user wants to build a partner program, launch an affiliate program, des
• positioning-icpWhen the user wants to define their ideal customer profile, position an AI produ
• sales-motion-designWhen the user wants to choose between PLG and sales-led, design a sales motion,
• social-sellingWhen the user wants to sell through social media, optimize LinkedIn for sales, b
• solo-founder-gtmWhen the user is a solo founder building their GTM motion, wants to scale withou
• video-outreachWhen the user wants to build video-first cold outreach, create personalized vide
• learning-opportunitiesFacilitates deliberate skill development during AI-assisted coding. Offers inter
• sentryInspect Sentry issues, summarize production errors, and pull health data via the
• core-web-vitalsOptimize Core Web Vitals (LCP, INP, CLS) for better page experience and search r
• perf-astroAstro-specific performance optimizations for 95+ Lighthouse scores. Covers criti
• perf-lighthouseRun Lighthouse audits locally via CLI or Node API, parse and interpret reports,
• perf-web-optimizationOptimize web performance: bundle size, images, caching, lazy loading, and overal
• react-best-practicesReact and Next.js performance optimization guidelines from Vercel Engineering. U
• seoOptimize for search engine visibility and ranking. Use when asked to "improve SE
• the-judgeEvidence-first pull request judge that reviews a PR and posts one consolidated G
• tlc-generative-engine-optimizationGenerative Engine Optimization (GEO) specialist — the technical, on-page publish
• accessibilityAudit and improve web accessibility following WCAG 2.1 guidelines. Use when aske
• best-practicesApply modern web development best practices for security, compatibility, and cod
• web-quality-auditComprehensive web quality audit covering performance, accessibility, SEO, and be
• security-best-practicesPerform language and framework specific security best-practice reviews and sugge
• security-ownership-mapAnalyze git repositories to build a security ownership topology (people-to-file)
• security-threat-modelRepository-grounded threat modeling that enumerates trust boundaries, assets, at
• chrome-devtoolsBrowser debugging, performance profiling, and automation via Chrome DevTools MCP
• excalidraw-studioGenerate Excalidraw diagrams from natural language descriptions. Outputs .excali
• gh-fix-ciUse when a user asks to debug or fix failing GitHub PR checks that run in GitHub
• mermaid-studioExpert Mermaid diagram creation, validation, and rendering with dual-engine outp
• nx-ci-monitorMonitor Nx Cloud CI pipeline status and handle self-healing fixes automatically.
• nx-generateGenerate code using Nx generators — scaffold projects, libraries, features, or r
• nx-run-tasksExecute build, test, lint, serve, and other tasks in an Nx workspace using singl
• nx-workspaceConfigure, explore, and optimize Nx monorepo workspaces. Use when setting up Nx,
• playwright-skillComplete browser automation with Playwright. Auto-detects dev servers, writes cl