Agent skills

AI & Agents 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
4,965 found
1,3451,392 · page 29 / 104
designing-mobile-permissionsUse when designing mobile permissions is required during mobile product work, especially when the result must be traceable…casioreview20-glitchdesigning-mobile-syncUse when designing mobile sync is required during mobile product work, especially when the result must be traceable…casioreview20-glitchdesigning-model-routingUse when designing model routing is required during ai-products product work, especially when the result must be traceable…casioreview20-glitchdesigning-observabilityUse when designing observability is required during architecture work, especially when the result must be traceable…casioreview20-glitchdesigning-os-integrationsUse when designing os integrations is required during desktop product work, especially when the result must be traceable…casioreview20-glitchdesigning-plugin-architectureUse when designing plugin architecture is required during architecture work, especially when the result must be traceable…casioreview20-glitchdesigning-responsive-experiencesUse when designing responsive experiences is required during ux work, especially when the result must be traceable, independently…casioreview20-glitchdesigning-saas-billingUse when designing saas billing is required during saas product work, especially when the result must be traceable, independently…casioreview20-glitchdesigning-saas-tenancyUse when designing saas tenancy is required during saas product work, especially when the result must be traceable, independently…casioreview20-glitchdesigning-save-systemsUse when designing save systems is required during games product work, especially when the result must be traceable…casioreview20-glitchdesigning-shopping-cartUse when designing shopping cart is required during ecommerce product work, especially when the result must be traceable…casioreview20-glitchdesigning-simulation-to-reality-workflowsUse when designing simulation to reality workflows is required during physical-ai product work, especially when the result must…casioreview20-glitchdestructionDestructible environment skill for fracturing and debris systems.a5c-aiwritesdetect-trendsDetect trending topics across multiple articles by analyzing entity co-occurrence and cross-source mentions. Uses memory search…majiayu000detecting-fake-noveltyUse when detecting fake novelty is required during creativity work, especially when the result must be traceable, independently…casioreview20-glitchdetecting-skill-regressionUse when detecting skill regression is required during meta work, especially when the result must be traceable, independently…casioreview20-glitchdev-routerDeveloper agent skill router - routes to 31 dev skills by category and signal keywords, manages 5 sub-agents.majiayu000developing-agentsThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when…majiayu000developing-features-with-tddUse when developing features with tdd is required during implementation work, especially when the result must be traceable…casioreview20-glitchdf:list-objective-assumptionsSurface Claude's assumptions about an objective approach before planning. Specialized diagnostic tool for reviewing AI…majiayu000writesdf:map-codebaseAnalyze codebase with parallel mapper agents to produce .planning/codebase/ documents and CLAUDE.md. Use when the user wants to…majiayu000writesDiagnose Research AgentA comprehensive skill designed for researching on complex diagnosis problems.majiayu000dialogue-aiDialogue system skill for branching conversations and response generation.a5c-aiwritesdid-analysisEconometrics skill for Difference-in-Differences (DID) analysis. Activates when the user asks about: "difference in differences"…brycewang-stanforddiffdockPredict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) — blind diffusion…BioTender-maxdiffdockPredict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) — blind diffusion…xuzhougengdiffusion-model-patternsDiffusion model training and inference patterns including UNet/DiT architectures, noise schedules, CFG, ControlNet, and LoRA. Use…majiayu000digital-twinBuild and maintain digital twins - virtual representations of physical systems that synchronize with real-world counterparts for…majiayu000Dimensional Model ValidatorValidates dimensional models against Kimball methodology best practicesa5c-aiwritesdirector-aiAI Director skill for pacing control and dynamic difficulty.a5c-aiwritesdisbaCompute surface wave dispersion curves for layered Earth models using the Thomson-Haskell matrix method with Numba acceleration.…majiayu000discover-codebase-enhancementsUse when the user asks for a deep codebase analysis to identify and rank improvements, optimizations, architectural enhancements…majiayu000discover-mlAutomatically discover machine learning and AI skills when working with machine learning, PyTorch, training, inference, RAG…majiayu000discover-updatesDiscover Claude and Claude Code CLI updates, improvements, tools and best practices from official sources and community. Use when…majiayu000distillStrip overspecified instructions from an artifact. Trust the model's intuition — prescribe intent, not format.majiayu000distill-promptDistill a verbose developer-facing prompt into a concise, token-efficient LLM-facing prompt while retaining essential…majiayu000distill-promptCreate lean, token-efficient versions of promptsmajiayu000distribution-searchGuidance for finding probability distributions that satisfy specific statistical constraints such as KL divergence targets…majiayu000dns-protocolExpert skill for DNS protocol implementation, configuration, and service discoverya5c-aiwritesdocument-lessons-as-snippetsWhen you make a mistake or discover a better approach, immediately suggest creating an Agent Beha... Use when configuring AI…majiayu000documenting-public-interfacesUse when documenting public interfaces is required during implementation work, especially when the result must be traceable…casioreview20-glitchdomain-mlUse when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep…majiayu000domain-mlUse when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep…majiayu000domain-model-extractorExtract domain models from monolithic codebases using DDD principles for microservices decompositiona5c-aiwritesdomain-modelerDDD Strategic Patterns + Event Storming Liteを使用してドメインモデルを作成するスキル。Bounded Context識別、Ubiquitous Language定義、ドメインイベント洗い出しを行う。…majiayu000dspy-advanced-module-compositionThis skill should be used when the user asks to "compose DSPy modules", "use Ensemble optimizer", "combine multiple programs"…majiayu000writesdspy-haystack-integrationThis skill should be used when the user asks to "integrate DSPy with Haystack", "optimize Haystack prompts using DSPy", "use DSPy…majiayu000writesdspy-rag-pipelineThis skill should be used when the user asks to "build a RAG pipeline", "create retrieval augmented generation", "use ColBERTv2…majiayu000writes
← Prev29 / 104Next →
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