Agent skills

Other skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
21,420 found
2,8812,928 · page 61 / 447
crisis-response-protocolHandle mental health crisis situations in AI coaching safely. Use when implementing crisis detection, safety protocols, emergency…majiayu000writescrispr-designerDesigns guide RNA (gRNA) sequences for CRISPR-Cas9 editing, including off-target analysis. Use when a user needs to edit a gene…majiayu000critical-argumentationPractical argument analysis and construction -- how to identify, evaluate, reconstruct, and build real arguments in natural…majiayu000Critical Peer PersonalityProfessional, skeptical communication style focused on critical thinking and coaching. Never over-enthusiastic, always verifies…majiayu000critical-perspectiveEngage in critical thinking by questioning assumptions, exploring alternative perspectives, and uncovering latent topics in…majiayu000critical-process-briefCreate critical process briefs through challenging dialogue that exposes operational blind spots and stress-tests workflows. Use…majiayu000critiqueChallenge idea assumptions with skeptical VC-style evaluation. Use when user requests critique, validation, or 'is this a good…majiayu000writescross-border-flow-trackerTrack and analyze cross-border capital flows between mainland China and Hong Kong via Stock Connect (沪港通/深港通). Monitor northbound…majiayu000cross-chainCross-chain bridge and multi-chain development expertise. Supports LayerZero, Chainlink CCIP, Wormhole, and Axelar for omnichain…a5c-aiwritescross-disciplinary-bridge-finderUse when identifying collaboration opportunities across fields, finding experts in complementary disciplines, translating…majiayu000writescross-disciplinary-ideationField connection mapping and systematic ideation for method transferbrycewang-stanfordcross-env-setupConfigure cross-env for cross-platform environment variable setting in npm scripts and CLI commands.a5c-aiwritescross-platform-path-handlerGenerate cross-platform path handling utilities for Windows, macOS, and Linux compatibility in CLI applications.a5c-aiwritescross-source-fact-verificationUse when fact-checking drafts containing dates, quantities, or causal claims against multiple independent sources.majiayu000crypto-analyzerCryptographic implementation analysis and validation for encryption algorithms, key sizes, and certificate managementa5c-aiwritescrypto-reportAnalyze cryptocurrency projects with tokenomics, on-chain metrics, and market analysis. Generate comprehensive crypto research…majiayu000crypto-ta-analyzerTechnical analysis with 29+ indicators (BB, Ichimoku, RSI, MACD). Generates 7-tier trading signals with divergence detection…majiayu000cses-trackerTrack progress through CSES Problem Set with structured learninga5c-aiwritesct-alphaCrypto Twitter intelligence and alpha research. Search X/Twitter for real-time crypto narratives, trending tokens, yield…majiayu000cublas-cudnnExpert integration with NVIDIA GPU-accelerated math libraries. Configure cuBLAS tensor core operations, generate cuBLAS GEMM…a5c-aiwritescublas-cudnnExpert integration with NVIDIA GPU-accelerated math libraries. Configure cuBLAS tensor core operations, generate cuBLAS GEMM…majiayu000writesCucumber BDD TestingCucumber/Gherkin BDD testing for behavior-driven development workflowsa5c-aiwritescuda-toolkitDeep integration with NVIDIA CUDA toolkit for kernel development, compilation, and debugging. Execute nvcc compilation with…a5c-aiwritescui-httpCUI HTTP client standards with HttpHandler, HttpResult pattern, and async-first adaptersmajiayu000writescuratorAutonomous curator for Source Library. Discover, evaluate, and import historical texts from digital archives (Archive.org…majiayu000curriculum-grade-assistAssist with grading by applying rubrics to student work, generating criterion-level feedback, and maintaining consistency across…majiayu000cursor-ai-chatManage master Cursor AI chat interface for code assistance. Triggers on "cursor chat", "cursor ai chat", "ask cursor", "cursor…majiayu000writescustomer-briefGenerate a concise, executive-ready digest of internal touchpoints and external intelligence for a named customer.majiayu000customer-feedback-analyzerAnalyzes customer feedback from surveys, reviews, support tickets, and interviews to identify themes, prioritize improvements…majiayu000customerio-reference-architectureImplement Customer.io enterprise reference architecture. Use when designing integration layers, event-driven architectures, or…jeremylongshorewritescustomerio-sdk-patternsApply production-ready Customer.io SDK patterns. Use when implementing typed clients, retry logic, event batching, or singleton…jeremylongshorewritescwicr-comparison-toolCompare cost estimates across projects, versions, and scenarios. Identify variances, benchmark against standards, and generate…majiayu000cybernetic-immuneCybernetic immune system with Varela+Friston+Powers for Self/Non-Self discrimination via reafference, GF(3) trit encoding, and…majiayu000cynefin-classifierClassify problems into Cynefin Framework domains (Clear, Complicated, Complex, Chaotic, Confusion) and recommend appropriate…majiayu000cynefin-classifierClassify problems into Cynefin Framework domains (Clear, Complicated, Complex, Chaotic, Confusion) and recommend appropriate…majiayu000cynefin-classifyUse when facing a new problem to classify its domain (Clear, Complicated, Complex, Chaotic, Confused) and select appropriate…majiayu000cynefin-classifyUse when facing a new problem to classify its domain (Clear, Complicated, Complex, Chaotic, Confused) and select appropriate…majiayu000cynefinCynefin sense-making framework categorizing problems as Simple, Complicated, Complex, Chaotic, or Confused to select the right…majiayu000daem0nmcp-protocolUse when Daem0nMCP tools are available - enforces the sacred covenant (commune at session start, seek counsel before changes…majiayu000dag-pattern-learnerLearns from DAG execution history to improve future performance. Identifies successful patterns, detects anti-patterns, and…majiayu000writescog-daily-intelligenceGenerate personalized verified news briefs with 7-day freshness and 95%+ source accuracya5c-aidan-kennedyTalk to Dan Kennedy about their expertise. Dan Kennedy provides authentic advice using their mental models, core beliefs, and…majiayu000dara-denneyTalk to Dara Denney Youtuber about their expertise. Dara Denney Youtuber provides authentic advice using their mental models…majiayu000dark-gritty-moodDark, grim, gritty, rusty, abandoned, decayed, industrial, lonely, and melancholic mood direction for Blender.arjun988dart-pub-dev-searchTo search pub.dev for relevant Dart packages, query by keywords and return download counts, topics, license, and publisher.majiayu000datalog-fixpointDatalog bottom-up fixpoint iteration for recursive queriesmajiayu000datamolPythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including…majiayu000datamolPythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including…majiayu000
← Prev61 / 447Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going