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
9611,008 · page 21 / 104
prompt-cachingCaching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use…majiayu000rag-implementationRetrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag…majiayu000tool-use-guardianFREE — Intelligent tool-call reliability wrapper. Monitors, retries, fixes, and learns from tool failures. Auto-recovers from…majiayu000yann-lecun-tecnicoSub-skill técnica de Yann LeCun. Cobre CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machinery of…majiayu000antseed-connectConnect coding agents, AI SDKs, and LLM tools to the AntSeed buyer proxy. Use when configuring Claude Code, Codex, OpenCode, Pi…internet-courtaomi-transactBuild natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into…majiayu000applefoundationmodels- On-Device Foundation Model: Apple''s Foundation Models frameworkmajiayu000apply-prompt-feedbackApplies user feedback to prompts with precision - incorporates feedback intent without over-fitting, maintains information…majiayu000applying-cross-domain-analogiesUse when applying cross domain analogies is required during creativity work, especially when the result must be traceable…casioreview20-glitchAppropriate Reliance Skill (v2.0)Calibrated human-AI collaboration with creative latitude — trust calibrated to reliability, creativity preserved with validation.majiayu000arcanea-coding-agentArcanea creative agent integration for opencodemajiayu000arch-viewThis skill should be used when the user asks to "generate architecture view", "show service dependency graph", "map request…majiayu000architecture-healthDiagnose cognitive architecture health — synapse integrity, memory balance, connection density, and drift detectionmajiayu000architecture-introspectorIntrospect and analyze software architectures using first principles thinking, SpaceX's 5-step engineering methodology (Question…majiayu000arize-experimentINVOKE THIS SKILL when creating, running, or analyzing Arize experiments. Covers experiment CRUD, exporting runs, comparing…majiayu000arize-instrumentationAdds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase…githubarize-instrumentationINVOKE THIS SKILL when adding Arize AX tracing to an application. Follow the Agent-Assisted Tracing two-phase flow: analyze the…majiayu000arize-observabilityArize AI skill for production ML monitoring, embedding drift, and performance analysis.a5c-aiwritesarize-observabilityArize AI skill for production ML monitoring, embedding drift, and performance analysis.majiayu000writesarize-traceINVOKE THIS SKILL when downloading or exporting Arize traces and spans. Covers exporting traces by ID, sessions by ID, and…majiayu000arxivSearch arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.majiayu000writesarxivSearch arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.majiayu000writesarxiv-learnINTERNAL MODULE - Use `arxiv learn` instead. This module provides the learn pipeline implementation for the arxiv skill.majiayu000arxivSearch arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.majiayu000writesase-meta-chatQuery foreign LLM for chat. Use this skill if a foreign LLM like OpenAI ChatGPT, Google Gemini, DeepSeek or xAI Grok should be…majiayu000ask-aiUse external AI assistants (ChatGPT, Claude, Gemini, DeepSeek) when agent encounters difficult problems. Trigger when: (1) User…majiayu000ask-before-assumingIf requirements are unclear or ambiguous, ask clarifying questions before proceeding Use when configuring AI agent workflows and…majiayu000ask-councilMulti-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.majiayu000askAsk Claude, Codex, or Gemini via local CLI and capture a reusable artifactmajiayu000assemble-agentsFetch specialized agents from the VoltAgent repository. Searches across categories, presents top 5 matches, and waits for user…majiayu000assemble-pluginsSearch the official Claude Code marketplace (claude-plugins-official) for plugins matching capability gaps. Uses plugin CLI to…majiayu000asset-optimizationAsset optimization skill for mesh and texture budgets.a5c-aiwritesasset-optimizationValidates and optimizes Blender assets for polycount, topology, UV efficiency, material count, naming, collections, and…arjun988assigning-agent-workUse when assigning agent work is required during planning work, especially when the result must be traceable, independently…casioreview20-glitchastarA* pathfinding skill for heuristics and optimization.a5c-aiwritesasyncopenai-concurrency-httpx-poolRaise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers…kennethkhoocyatlas-agent-developerImplementation and troubleshooting agent - builds features and fixes bugsmajiayu000atlas-reportRender agent findings as a styled HTML report in the browser. Use when asked for "full report", "detailed report", "show in…jeremylongshorewritesatomic-agentsThis skill should be used when the user asks to "create an agent", "configure AtomicAgent", "set up agent", "agent…majiayu000auditing-agent-actionsUse when auditing agent actions is required during kernel work, especially when the result must be traceable, independently…casioreview20-glitchauraConfigure AI personality using the AURA protocol (HEXACO-based). Use when user wants to customize agent personality, reduce…majiayu000auto-analysis-219c9431a85d⚡ This skill was automatically created after detecting a repetitive pattern.majiayu000auto-coder-enzannometsuke-lynyx-claude-3Autonomous multi-session feature development framework. Use when the user wants to systematically implement features from a…majiayu000auto-coherenceThe skill you cannot invoke. It invokes itself.majiayu000auto-skill-lifecycle-handling自动处理 Agent Skill 的全生命周期:在用户反馈中识别稳定约束以触发技能抽取;合并新增偏好实现版本演进(如 v0.1.0 → v0.1.1);并在后续相似任务中精准检索并注入对应技能。majiayu000autogen-setupMicrosoft AutoGen multi-agent configuration for conversational AI systemsa5c-aiwritesautogen-setupMicrosoft AutoGen multi-agent configuration for conversational AI systemsmajiayu000writesautoml-optimizerAutomated machine learning with hyperparameter optimization using Optuna, Hyperopt, or AutoML libraries. Activates for "automl"…majiayu000
← Prev21 / 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