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
2,4012,448 · page 51 / 104
shapModel interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine…majiayu000shepherdAutonomous pipeline monitor using sense-think-act loop. Watches snakemake/nextflow jobs, detects errors, applies fixes from…majiayu000writessibyl-codex-reviewerSibyl Codex 独立第三方审查 - 使用 OpenAI Codex 提供不同 AI 视角的评审majiayu000writessibyl-experiment-supervisorSibyl 后台实验监督 agent - 持续刷新 GPU 空闲状态、动态派发排队实验、处理运行时间/状态漂移majiayu000writessibyl-idea-validation-decisionSibyl pilot 验证决策 agent - 根据小实验结果决定 ADVANCE / REFINE / PIVOTmajiayu000writessibyl-latex-writerSibyl LaTeX 排版 agent - 将论文转为 NeurIPS LaTeX 格式并编译majiayu000writessibyl-literatureSibyl 文献调研 agent - 使用 arXiv + Web 双源搜索进行系统性文献调研majiayu000writessibyl-self-healerSibyl 自愈 agent - 后台自动检测修复系统错误,添加回归测试,git commit 留痕majiayu000writessignaling-kb-batchedExtract all entity types (interventions, pathways, biomarkers, conflicts) from Google Drive transcript analyses using a…majiayu000writessignaling-kb-builderBuild and maintain an entity-centric cell signaling knowledge base from lecture transcripts. Uses a three-stage LLM pipeline…majiayu000writessigning-desktop-buildsUse when signing desktop builds is required during desktop product work, especially when the result must be traceable…casioreview20-glitchSim-to-Real Transfer SkillTechniques for minimizing simulation-to-reality gap and validating transfera5c-aiwritesSim-to-Real Transfer SkillTechniques for minimizing simulation-to-reality gap and validating transfermajiayu000writessingle-cell-annotation-skills-with-omicverseGuide Claude through SCSA, MetaTiME, CellVote, CellMatch, GPTAnno, and weighted KNN transfer workflows for annotating single-cell…FreedomIntelligenceSisyphusThe Primary Orchestrator Agent for Oh My Antigravitymajiayu000alpaca-trading-exampleOne-line trigger description for when an agent should load this skill.alpacahqskill-creatorCreate, structure, and package agent skills. Use when designing new skills, updating existing skills, or helping users build…gooseworks-aiskill-installation审查、安装、配置、激活、验证、更新和回滚 AgentDock Skill 时使用;负责来源校验、安全评估、环境配置和已安装版本验收。uvwtskill-installer跨平台智能安装助手:自动检测操作系统,适配Windows/macOS/Linux命令,处理Git/网络/路径问题。当用户说"安装skill"、"帮我安装xxx"、"我下载了skill,路径是xxx"时触发。mingchen666model-routingRoute tasks to appropriate model size based on confidence estimation. Use small model by default, escalate to large model only on…majiayu000skill-neovim-researchResearch Neovim APIs, plugin patterns, and Lua development. Invoke for lua-language research tasks.majiayu000analyze-cc-featureReverse engineer and analyze a specific feature in Claude Code's source. Use when the user wants to understand how a Claude Code…majiayu000skill-python-researchResearch Python/Z3 patterns and APIs for semantic theory development. Invoke for Python-language research tasks.majiayu000writesskill-suggesterScan prompt history for recurring patterns and unmet needs, then propose new skills or command templatessickn33monad-memory-architectureMONAD-grounded cognitive architecture for AI memory as morphemic substrate navigation. Memory is not storage but substrate…majiayu000skillsUse this skill when the user asks "/think" or when you face a complex architectural challenge.majiayu000toolfsUnified virtual filesystem framework for LLM agents. Provides access to files, memory, RAG, skills, and snapshots through a…majiayu000hivemindGlobal team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling…majiayu000scikit-learnMachine learning library for classical supervised/unsupervised models, preprocessing, and model evaluation using NumPy/SciPy.majiayu000openai-chatkit-skillIntegrate OpenAI ChatKit for conversational AI interfacemajiayu000groq-inference-skillUse Groq for fast LLM inference with OpenAI-compatible clientmajiayu000sklearn-model-trainerScikit-learn model training skill with cross-validation, hyperparameter tuning, pipeline construction, and model serialization.…a5c-aiwritessklearn-model-trainerScikit-learn model training skill with cross-validation, hyperparameter tuning, pipeline construction, and model serialization.…majiayu000writessklearn-pipeline-builderBuild sklearn pipeline builder operations. Auto-activating skill for ML Training. Triggers on: sklearn pipeline builder, sklearn…majiayu000writesslack-respondProcess unhandled Slack messages as Claudicle with persistent memory. Loads user models and soul state, posts terminal-styled…majiayu000slam-algorithmsExpert skill for SLAM algorithm selection, configuration, and tuning. Configure visual SLAM (ORB-SLAM3, RTAB-Map), LiDAR SLAM…a5c-aiwritesslam-algorithmsExpert skill for SLAM algorithm selection, configuration, and tuning. Configure visual SLAM (ORB-SLAM3, RTAB-Map), LiDAR SLAM…majiayu000writesslicing-long-contextsUse when a prompt or corpus is long/dense (multi-docs, logs, codebases) and you want a reproducible map/reduce pipeline. Trigger…majiayu000slicing-vertical-incrementsUse when slicing vertical increments is required during planning work, especially when the result must be traceable…casioreview20-glitchsmart-pole-instructorUse when a user provides a vague prompt and needs structured clarification to produce a precise master prompt.majiayu000smart-ralphCore Smart Ralph skill defining common arguments, execution modes, and shared behaviors across all Ralph plugins.majiayu000sme-agent-protocolMandatory protocol for all SME (Subject Matter Expert) agents. Defines fact-finding requirements, output contracts…majiayu000smoke-testing-productionUse when smoke testing production is required during operations work, especially when the result must be traceable, independently…casioreview20-glitchsmolvlmLocal vision-language model for image analysis using SmolVLM-2Bmajiayu000sniffable-pythonStructure Python so LLMs can understand it in 50 lines.majiayu000sniffable-pythonStructure Python so LLMs can understand it in 50 lines.majiayu000soil-extractionUses a shovel tool to dig soil from the ground in outdoor environments. Execute this skill when you need to obtain soil for…zjunlpsophia-singularityComplete Sophia Catgirl Singularity architecture - Recursive self-improvement engine integrating monad-memory (288-grid, GOD…majiayu000
← Prev51 / 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