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
1,0091,056 · page 22 / 104
automl-pipeline-setupЭксперт AutoML. Используй для automated machine learning, hyperparameter tuning и model selection.majiayu000autonomous-agentBefore main skill execution, perform guardrail checks.majiayu000autonomous-coding-agentBuild autonomous coding agents with CLI integration. Use when creating automated coding workflows, managing multi-session…majiayu000writesautonomous-loopAutonomous development loop patterns for iterative self-improvement. Auto-triggers when implementing features autonomously…majiayu000autopilotThis skill should be used when the user asks to "run autopilot", "autopilot feature N", "implement all phases", "run all phases…majiayu000autopoiesisSelf-modifying AI agent configuration via ruler + MCP + DuckDB. All behavior mods become one-liners.majiayu000autoresearch-mlAutonomous LLM training optimization with GPU support. Runs 5-minute training experiments, measures val_bpb, keeps improvements…majiayu000autoresearchThis skill should be used when the user asks to "run autoresearch", "optimize X in a loop", "set up autonomous experiments"…majiayu000autoresearchScaffold and run Karpathy-style autoresearch loops in any git repo. This skill should be used when setting up autonomous code…majiayu000autoskillManage personal local Agent Skill files as an installable skill manager. Proactively and periodically detect reusable…ECNU-ICALKAwareness SkillProactive detection, self-correction, and epistemic vigilancemajiayu000axi-protocolExpert skill for AMBA AXI protocol implementation and verification in FPGA designsa5c-aiwritesaxiom-ios-mlUse when deploying ANY machine learning model on-device, converting models to CoreML, compressing models, or implementing…majiayu000axiom-ios-mlUse when deploying ANY machine learning model on-device, converting models to CoreML, compressing models, or implementing…majiayu000backcasting-from-the-futureUse when backcasting from the future is required during creativity work, especially when the result must be traceable…casioreview20-glitchalpaca-trading-backtestExecute deterministic, reproducible historical backtests from a start date, end date, and strategy concept using the Alpaca CLI…alpacahqbacktest-analyzer-agentBacktest results interpreter and strategy evaluator. Analyzes historical backtest performance, identifies strengths/weaknesses…majiayu000balthasar-2MAGI 2號機 - 守護者視角分析 (Gemini via MCP)。作為 MAGI 三機平行討論的一員,從品質、可維護性、最佳實踐角度分析任務。觸發條件:MAGI 系統啟動時自動平行調用。majiayu000band-advancedThis skill group covers advanced electronic band structure techniques beyond the standard k-path band calculation. These methods…majiayu000basecallingThe most comprehensive Claude Code skills registry - 50,000+ skills indexedmajiayu000batch-inference-pipelineBatch Inference Pipeline - Auto-activating skill for ML Deployment. Triggers on: batch inference pipeline, batch inference…majiayu000writesbatch-reportGenerate post-run analysis reports for batch processing jobs. Analyzes manifests, timings, and failures to produce comprehensive…majiayu000writesbazinga-db-agentsAgent logs, reasoning, and token tracking. Use when logging interactions, saving reasoning, tracking tokens, or managing events.majiayu000writesbdi-mental-statesThis skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create…majiayu000bdi-mental-statesThis skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create…majiayu000bedrock-agentsAmazon Bedrock Agents for building autonomous AI agents with foundation model orchestration, action groups, knowledge bases, and…majiayu000writesbedrock-promptsAmazon Bedrock Prompt Management for creating, versioning, and managing prompt templates with variables, multi-variant A/B…majiayu000writesbehavioral-profile-calibrationCalibrate behavioral profiles for consistent agent operation.majiayu000benchmarking-skill-utilityUse when benchmarking skill utility is required during meta work, especially when the result must be traceable, independently…casioreview20-glitchbentoml-model-packagerBentoML skill for model packaging, serving, and containerization.a5c-aiwritesbentoml-model-packagerBentoML skill for model packaging, serving, and containerization.majiayu000writesbest-practicesTransforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper…majiayu000better-prompt当用户明确要求"优化 prompt"、"改进提示词"、"润色指令"或"将简陋 prompt 转换为最佳实践版本"时使用。基于 OpenAI 和 Anthropic 官方最佳实践,对用户提供的简陋 prompt 进行结构化优化,输出符合社区标准的高质量版本。majiayu000Binary Exploitation SkillAdvanced binary exploitation and mitigation bypassa5c-aiwritesblender-integrationBlender to engine pipeline skill for GLTF/FBX export.a5c-aiwritesblind-spot-chainFive-skill sequence for 'what am I missing?' - Collide → Critique → Scale → Synthesize → Simplify. Use when you suspect you're…majiayu000blockrunBlockRun works with Claude Code and Google Antigravity.majiayu000bmad-advanced-elicitationPush the LLM to reconsider, refine, and improve its recent output.majiayu000bmad-advanced-elicitationPush the LLM to reconsider refine and improve its recent output.majiayu000bmad-advanced-elicitationPush the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known…majiayu000bmad-agent-builderBuilds, edit or validate Agent Skill through conversational discovery. Use when the user requests to "Create an Agent", "Optimize…majiayu000bmad-bmb-create-agentCreate a new BMAD agent with best practices and compliancemajiayu000bmad-bmb-create-agentCreate a new BMAD agent with best practices and compliancemajiayu000bmad-bmb-edit-agentEdit existing BMAD agents while maintaining compliancemajiayu000bmad-bmb-edit-agentEdit existing BMAD agents while maintaining compliancemajiayu000bmad-bmb-validate-agentValidate existing BMAD agents and offer to improve deficienciesmajiayu000bmad-bmb-validate-agentValidate existing BMAD agents and offer to improve deficienciesmajiayu000bmorphism-interactomeGitHub interactome explorer for bmorphism/plurigrid ecosystem. Maps collaborations across AlgebraicJulia, Topos Institute…majiayu000
← Prev22 / 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