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
1,825–1,872 · page 39 / 104
metaExecute Claude Code commands in the telegram_agent project directory. Use when the user wants to work on the telegram agent…majiayu000metaxyThis skill should be used when the user asks to "define a feature", "create a BaseFeature class", "track feature versions", "set…majiayu000metaxyThis skill should be used when the user asks to "define a feature", "create a BaseFeature class", "track feature versions", "set…majiayu000metricsCollect and report metrics on agent usage from git history implementing the 8 key metrics defined in agent-metrics.md for…majiayu000migrate-to-skillsConvert legacy agent resources to the unified Agent Skills format.majiayu000milestone-zeroae-zae-limiter-0dd088e8When users mention a milestone version (e.g., "0.4.0", "v0.4.0") or ask about release status, invoke this skill to analyze GitHub…majiayu000minicoil-trainingminiCOIL v1 sparse neural retrieval model training methodology: per-word linear layer training with triplet loss, word vocabulary…majiayu000minimax-mcp-usageOptimal patterns for MiniMax MCP tools (web_search + understand_image)majiayu000minimizing-extension-permissionsUse when minimizing extension permissions is required during browser-extensions product work, especially when the result must be…casioreview20-glitchminimum-viable-agenticGuide creation of minimum viable agentic layer for a codebase. Use when starting agentic coding in a new project, bootstrapping…majiayu000mining-user-workaroundsUse when mining user workarounds is required during research work, especially when the result must be traceable, independently…casioreview20-glitchmixed-precision-trainerManage mixed precision trainer operations. Auto-activating skill for ML Training. Triggers on: mixed precision trainer, mixed…majiayu000writesmixed-precision-trainerMixed Precision Trainer - Auto-activating skill for ML Training. Triggers on: mixed precision trainer, mixed precision trainer…majiayu000writesml-causalEconometrics skill for machine learning methods in causal inference. Activates when the user asks about: "causal forest"…brycewang-stanfordml-engineerBuild production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature…majiayu000ml-engineerProduction machine learning systems and model serving infrastructure. Use when building ML pipelines, deploying models to…majiayu000ml-engineerBuild production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature…majiayu000ml-engineerBuild production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature…majiayu000ml-engineerBuild production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature…majiayu000ml-experiment-trackerGuides ML experiment logging, versioning, and reproducibility using tools like MLflow, Weights & Biases, and DVC for systematic…majiayu000ml-expertImplement machine learning solutions including model architectures, training pipelines, optimization strategies, and performance…majiayu000ml-memoryMemory systems specialist for hierarchical memory, consolidation, and outcome-based learningUse when "memory system, memory…majiayu000ml-model-deploymentServe models with A/B testing, monitoring, retraining.majiayu000ml-model-eval-benchmarkCompare model candidates using weighted metrics and deterministic ranking outputs. Use for benchmark leaderboards and model…majiayu000ml-model-explainerExplain ML model predictions using SHAP values, feature importance, and decision paths with visualizations.majiayu000ml-model-trainingTrain ML models with scikit-learn, PyTorch, TensorFlow. Use for classification/regression, neural networks, hyperparameter…majiayu000ml-model-trainingTrain ML models with scikit-learn, PyTorch, TensorFlow. Use for classification/regression, neural networks, hyperparameter…majiayu000ml-monitoringProduction-grade ML model monitoring, drift detection, and observabilitymajiayu000ml-pipelineUse when building ML pipelines, orchestrating training workflows, automating model lifecycle, implementing feature stores, or…majiayu000MLflow PatternsML experiment tracking, model registry, and deployment with MLflow for reproducible machine learning workflows.majiayu000mlflow-tracking-setupMlflow Tracking Setup - Auto-activating skill for ML Training. Triggers on: mlflow tracking setup, mlflow tracking setup Part of…majiayu000writesmlflow-tracking-setupConfigure mlflow tracking setup operations. Auto-activating skill for ML Training. Triggers on: mlflow tracking setup, mlflow…majiayu000writesmlip-guideUniversal and specialized machine learning interatomic potentials for rapid atomistic simulation without DFT. Covers model…majiayu000mlops-engineerBuild comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools.…majiayu000mlops-engineerML infrastructure automation and production ML lifecycle management. Use when building ML pipelines, setting up experiment…majiayu000mlops-engineerBuild comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools.majiayu000mlops-engineerBuild comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools.…majiayu000mlopsImplement MLOps practices for ML lifecycle management. Use for CI/CD pipelines, model versioning, experiment tracking, automated…majiayu000moai-alfred-expertise-detectionEnterprise AI-powered user expertise detection with behavioral analysis, communication pattern recognition, code complexity…majiayu000moai-foundation-claudeCanonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing…majiayu000writesmoai-foundation-claudeCanonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing…majiayu000writesmoai-foundation-claudeCanonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing…majiayu000writesmoai-ml-llm-fine-tuningEnterprise LLM Fine-Tuning with LoRA, QLoRA, and PEFT techniquesmajiayu000writesmoai-ml-ragRetrieval-Augmented Generation systems, vector databases, embedding strategies, and production RAG architectures for enterprise…majiayu000writesmobile-optimizationMobile GPU optimization skill for thermal management.a5c-aiwritesmodelInspect or change Babysitter model-routing policy by phase.majiayu000Model Bias FairnessModel Bias occurs when an AI system produces results that are systematically prejudiced against certain individuals or groups.…majiayu000Model Bias and FairnessIdentifying, measuring, and mitigating algorithmic bias to ensure equitable outcomes in AI systems.majiayu000
← Prev39 / 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
Collections, ranked →
Which skill collections are moving this week, from our own snapshots.
Open Source Radar →
The repositories behind these skills, watched daily.
The makers →
Who publishes the skills you install.
Startup rankings →
The companies building in the same ecosystem.