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
2,3052,352 · page 49 / 104
retellai-reference-architectureRetell AI reference architecture \u2014 AI voice agent and phone call\ \ automation.\nUse when working with Retell AI for voice…jeremylongshorewritesretellai-reliability-patternsRetell AI reliability patterns \u2014 AI voice agent and phone call\ \ automation.\nUse when working with Retell AI for voice…jeremylongshorewritesretellai-sdk-patternsProduction-ready Retell AI SDK patterns for voice agent applications. Use when building production voice agents, implementing…jeremylongshorewritesretellai-webhooks-eventsRetell AI webhooks events \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents…jeremylongshorewritesreviewing-architecture-risksUse when reviewing architecture risks is required during architecture work, especially when the result must be traceable…casioreview20-glitchreviewing-code-diffsUse when reviewing code diffs is required during implementation work, especially when the result must be traceable, independently…casioreview20-glitchreviewing-critical-code-line-by-lineUse when reviewing critical code line by line is required during implementation work, especially when the result must be…casioreview20-glitchreviewing-visual-regressionsUse when reviewing visual regressions is required during ux work, especially when the result must be traceable, independently…casioreview20-glitchrisk-agentRisk management and constitutional compliance specialist. Ensures all trading decisions comply with constitutional limits and…majiayu000Reinforcement Learning SkillRL training for robot control using simulation with sim-to-real transfera5c-aiwritesReinforcement Learning SkillRL training for robot control using simulation with sim-to-real transfermajiayu000writesrlhf-feedbackAutonomous RLHF feedback capture - Claude self-captures mistakes and successesmajiayu000rlmRun a Recursive Language Model-style loop for long-context tasks. Uses a persistent local Python REPL and an rlm-subcall subagent…majiayu000writesrlmProcess large codebases (>100 files) using the Recursive Language Model pattern. Treats code as an external environment, using…majiayu000roc-curve-plotterRoc Curve Plotter - Auto-activating skill for ML Training. Triggers on: roc curve plotter, roc curve plotter Part of the ML…majiayu000writesroc-curve-plotterManage roc curve plotter operations. Auto-activating skill for ML Training. Triggers on: roc curve plotter, roc curve plotter…majiayu000writesrollback-automation-skillAutomate rollback procedures with state snapshots, rollback scripts, and verification automationa5c-aiwritesroot-cause-analysis-and-fixThis skill is for debugging failed Bauplan runs. It assumes a failure has already occurred and prioritizes evidence collection…majiayu000ros2_control SkillHardware abstraction and controller management using ros2_control frameworka5c-aiwritesrouteManually route a query to the optimal Claude model (Haiku/Sonnet/Opus)majiayu000route-legal-researchPick the right LLM for LEGAL RESEARCH & ANALYSIS — issue-spotting, rule application, case/statute analysis, memos, and multi-step…lawve-airouter-statsDisplay Claude Router usage statistics and cost savingsmajiayu000routing-skill-graphUse when routing skill graph is required during kernel work, especially when the result must be traceable, independently…casioreview20-glitchRubber Duck Debugging SkillBe a thinking partner. The answer often emerges when explaining the problem.majiayu000running-canary-releaseUse when running canary release is required during operations work, especially when the result must be traceable, independently…casioreview20-glitchrunning-placebo-analysisPerforms placebo-in-time sensitivity analysis with hierarchical null model and optional Bayesian assurance. Use when checking…brycewang-stanfordrunning-placebo-analysisPerforms placebo-in-time sensitivity analysis to validate causal claims. Use when checking model robustness, verifying lack of…majiayu000running-product-go-no-goUse when running product go no go is required during product work, especially when the result must be traceable, independently…casioreview20-glitchruntime-skillsUniversal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving. Covers device management, model…majiayu000RViz Visualization SkillRViz configuration and custom visualization for robot development and debugginga5c-aiwritesrwd-editor-in-chiefRWD研究の企画から完成までを統括する編集長Skill。他のSkillを適切な順序で呼び出し、 研究案Top3の選定、スコアリング、感度分析計画、次アクションを統合出力する。majiayu000safe-agent-selectiveAgent with selective Gemini safety settings for specific categoriesmajiayu000sam-altmanAgente que simula Sam Altman — CEO da OpenAI, ex-presidente da Y Combinator, arquiteto da era AGI.majiayu000sample-pluginPhase 1 sample plugin synthesizing a SKILL.md frontmatter for backwards-compat tests.nexu-iosample-skillA sample skill for testing the validator. Helps with greeting generation.dotnetsanctions-screening-legal-analysis-skill-english-gillan-salehSanctions and export control analysis tool for Claude Desktop. Real-time individual screening across 30+ official lists (UN, EU…lawve-aisandboxing-desktop-featuresUse when sandboxing desktop features is required during desktop product work, especially when the result must be traceable…casioreview20-glitchsay-narrationUse macOS text-to-speech for agent narration and announcements. Sub-agents announce themselves using different language voices…majiayu000scale-checkThis skill supports three modes: Create, Update, and Find.majiayu000scenario-plannerWhat-if analysis for construction projects: model different scenarios and their cost/schedule/resource impacts. Compare…majiayu000scienceworld-animal-identifierUse when the agent needs to locate, identify, and focus on a specific animal or biological entity in the ScienceWorld…zjunlpscienceworld-container-inspectorInspects the contents of a container or device using the 'look at' action. Use this skill when you need to verify what is inside…zjunlpscienceworld-container-item-retrieverThis skill retrieves a specified item from a container by using the 'pick up' action. It should be triggered when the agent has…zjunlpscienceworld-container-transferMoves a substance or object from one container to another (e.g., moving lead to a metal pot). Use this skill when you need to…zjunlpscienceworld-device-activatorActivates a device (e.g., blast furnace, stove) to initiate a process like heating. Use this skill when you have placed materials…zjunlpscienceworld-liquid-pourerTransfers the contents of a source liquid container into a target container for mixing or preparation. Use this skill when you…zjunlpscienceworld-planting-coordinatorThis skill plants a seed or small plant into a suitable growth container (e.g., a flower pot with soil and water). It should be…zjunlpscienceworld-pot-preparerPrepares a planting pot by moving soil from inventory into an empty or water-filled pot. Use this when setting up a growth…zjunlp
← Prev49 / 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