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
1,5851,632 · page 34 / 104
hyperparameter-tunerManage hyperparameter tuner operations. Auto-activating skill for ML Training. Triggers on: hyperparameter tuner, hyperparameter…majiayu000writeshyperparameter-tunerHyperparameter Tuner - Auto-activating skill for ML Training. Triggers on: hyperparameter tuner, hyperparameter tuner Part of the…majiayu000writesiapIn-app purchases skill for receipt validation.a5c-aiwritesIcelandic Company FormationUse this skill when asked about forming, registering, or structuring a company in Iceland. Triggers on questions about Icelandic…lawve-aiIcelandic Court Case FinderUse this skill when asked to find, cite, analyze, or summarize Icelandic court decisions. Triggers on requests involving…lawve-aiIcelandic EEA Gap AnalysisUse this skill when asked to analyze how Iceland has implemented an EU directive or regulation into national law, identify gaps…lawve-aiIcelandic Labour LawUse this skill when asked about Icelandic employment law, labour relations, workplace rights, or collective agreements. Triggers…lawve-aiIcelandic Legal TerminologyUse this skill when asked to translate, explain, or map Icelandic legal terms to English (or vice versa). Triggers on requests…lawve-aiidentify-architectureAnalyze ML model architecture from papers and code. Use when understanding model structure for implementation.majiayu000identifying-market-shiftsUse when identifying market shifts is required during research work, especially when the result must be traceable, independently…casioreview20-glitchilya-sutskeverAgente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas…majiayu000image-generationAI-powered image generation and editing using Gemini. Use when Claude needs to: (1) Generate images from text descriptions, (2)…majiayu000impact-analysis-helperConfigure with impact analysis helper operations. Auto-activating skill for Enterprise Workflows. Triggers on: impact analysis…majiayu000writesimpact-analysisImpact analysis for understanding how code changes affect the system. Covers git diff analysis, entity mapping, flow…majiayu000implementing-contract-firstUse when implementing contract first is required during implementation work, especially when the result must be traceable…casioreview20-glitchimplementing-mlopsStrategic guidance for operationalizing machine learning models from experimentation to production. Covers experiment tracking…majiayu000inboxAgent Mail inbox monitoring. Check pending messages, HELP_REQUESTs, and recent completions. Triggers: "inbox", "check mail", "any…majiayu000writesincident-forensicsDigital forensics and incident response capabilities. Analyze memory dumps with Volatility, parse filesystem artifacts, extract…a5c-aiwritesincognito-mode-patternsIncognito mode patterns for ephemeral conversations with blank slate option. Controls tool access (write tools always disabled…majiayu000incremental-commitsCommit code after each logical unit of work is complete Use when configuring AI agent workflows and patterns. Agent Behavior…majiayu000Incremental Model Strategy SelectorSelects and configures optimal incremental model strategiesa5c-aiwritesIndustry VerticalsSpecialized agent configurations for specific industriesmajiayu000AI Inference & Model ServingAI model inference and serving. Activate when: (1) Setting up LocalAI or vLLM, (2) Configuring model serving, (3) Working with…majiayu000infinite-gratitudeMulti-agent research skill for parallel research execution (10 agents, battle-tested with real case studies).majiayu000init-first-agentWalk the operator through creating the first NanoClaw agent for a DM channel — resolve the operator's channel identity, wire the…majiayu000init-first-agentWalk the operator through creating the first NanoClaw agent for a DM channel — resolve the operator's channel identity, wire the…majiayu000inquirer-prompt-generatorGenerate interactive command-line prompts using Inquirer.js with validation, conditional logic, and custom renderers. Creates…a5c-aiwritesinstruction-improverSearch memex for user feedback patterns (frustration, corrections, praise, successful outcomes) to identify recurring mistakes…majiayu000instruction-optimizerUse when instruction files (skills, prompts, CLAUDE.md) are too long or need token reduction while preserving capability.majiayu000integrating-enterprise-ssoUse when integrating enterprise sso is required during enterprise product work, especially when the result must be traceable…casioreview20-glitchintegrating-payment-providersUse when integrating payment providers is required during ecommerce product work, especially when the result must be traceable…casioreview20-glitchinternal-comms-communityTo write internal communications, use this skill for:sickn33introspectionAnalyze and explain Claude's reasoning, decision patterns, and problem-solving approaches. Use when user requests "explain your…majiayu000investigateUse when user asks 'what is X', 'how does X work', 'find out about', 'analyze', 'explain the code', or needs quick codebase…majiayu000writesirac-prompt-stephane-boghossianRestructure any rough build, research, or legal-drafting request into an IRAC-shaped prompt — Issue, Rule, Analysis, Conclusion —…lawve-aiisolating-development-workUse when isolating development work is required during planning work, especially when the result must be traceable, independently…casioreview20-glitchjina-aiUse Jina AI APIs for converting URLs to LLM-friendly Markdown (Reader) and searching the web (Search).majiayu000jira-assistantManage Jira issues via Atlassian MCP — search, create, update, transition status, and handle sprint tasks. Auto-detects workspace…tech-leads-clubJIT CompilationExpert skill for just-in-time compilation including profiling, tiered compilation, and deoptimizationa5c-aiwritesJudicial First ImpressionAssesses a legal argument, submission, or piece of structured reasoning from the perspective of a judge reading it cold under…lawve-aijules-cliInteract with the Jules CLI to manage asynchronous coding sessions. Use this skill to assign tasks, monitor progress, and pull…majiayu000jupyter-notebook-executorJupyter notebook execution skill for running notebooks programmatically and extracting outputs.a5c-aiwritesjustice-matrix-researchRalph research agent for discovering global youth justice cases and advocacy campaignsmajiayu000keine-chatUse this skill whenever the user wants to discuss, explore, or ask questions about a topic using the local knowledge base as…majiayu000keyword-based-llm-evalUse when evaluating LLM-generated structured output against expected results using keyword matching and F1 metrics.majiayu000Kinematics/Dynamics SkillRobot kinematics and dynamics computation including forward/inverse kinematics and dynamicsa5c-aiwritesKinematics/Dynamics SkillRobot kinematics and dynamics computation including forward/inverse kinematics and dynamicsmajiayu000writeskinfer-runtimeK-Scale kinfer model inference engine for deploying trained RL policies to real robots via ONNX Runtime in Rustmajiayu000
← Prev34 / 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