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
3,2173,264 · page 68 / 104
constraint-satisfaction-solverConstraint programming skill for scheduling, configuration, and assignment problemsa5c-aiwritesconsultCross-tool AI consultation. Use when user asks to 'consult gemini', 'ask codex', 'get second opinion', 'cross-check with claude'…agent-shcontact-angle-analyzerWettability analysis skill for surface energy characterization and hydrophobicity/hydrophilicity assessmenta5c-aiwritescontext-budgetAudits OpenAI Codex context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant…mturaccontext-compressionWhen agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approach is…sickn33context-fundamentalsContext is the complete state available to a language model at inference time. It includes everything the model can attend to…sickn33context-kitEvaluate, adapt, and safely install Context Kit personal context artifacts for Claude Code or adjacent agent workflows.sickn33context-managerElite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent…sickn33context-window-managementStrategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rotsickn33continual-learningGuide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when setting up…microsoftcontract-analyzerContract analysis and negotiation support skill with clause extraction and risk identificationa5c-aiwritescontrol-chart-analyzerStatistical process control chart creation and analysis skill with control limit calculation and special cause detection.a5c-aiwritescontrol-d-automationAutomate Control D tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQconversation_evidence_sopSOP for extracting evidence from offline OpenAI-format conversations, distinguishing primary user questions from secondary…ECNU-ICALKconversation-memoryPersistent memory systems for LLM conversations including short-term, long-term, and entity-based memorysickn33conversion-tools-automationAutomate Conversion Tools tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQconvert-plaintext-to-mdConvert a text-based document to markdown following instructions from prompt, or if a documented option is passed, follow the…githubConvert Python Event Camera Algorithm to Optimized C++Converts Python event-camera processing code (involving window creation, scatter operations, and aggregation methods like…ECNU-ICALKconvertapi-automationAutomate Convertapi tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQconvertkit-automationAutomate ConvertKit (Kit) tasks via Rube MCP (Composio): manage subscribers, tags, broadcasts, and broadcast stats. Always search…davepoonconvertkit-automationAutomate ConvertKit (Kit) tasks via Rube MCP (Composio): manage subscribers, tags, broadcasts, and broadcast stats. Always search…sickn33conveyor-automationAutomate Conveyor tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQconvolo-ai-automationAutomate Convolo AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcorl-related-workUse when positioning a CoRL paper against the literature — the robot-learning lineage across CoRL/RSS/ICRA, the ML-methods stream…brycewang-stanfordcorrently-automationAutomate Corrently tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcorrosion-materials-selectorMaterials selection skill for corrosion resistance based on process conditions and industry standardsa5c-aiwritescortexML/AI engineer — LLM integrations, prompt engineering, model pipelines, evals, RAG.jeremylongshorewritescosmosis-parameter-estimatorCosmoSIS cosmological parameter estimation skill for MCMC sampling and likelihood analysisa5c-aiwritescost-booster-editApply a simple code transform via agent-booster's WASM engine — sub-millisecond, deterministic, $0 (no LLM call). Companion to…ruvnetwritescost-booster-routeRoute tasks through hooks_route, partition by Agent Booster availability, and report Tier 1 bypass utilization with $0 costruvnetwritescost-conversationPer-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total costruvnetwritescost-reportGenerate a cost report showing token usage and USD costs by agent and modelruvnetwritescost-sessionPer-message cost breakdown within a single session. The drill-down companion to cost-anomaly — when an outlier session is…ruvnetwritescost-to-serve-analyzerSupply chain cost-to-serve analysis skill by customer, product, or channela5c-aiwritescost-trackAuto-capture per-session token usage from the Claude Code session jsonl and persist to the cost-tracking namespaceruvnetwritescost-trendRead every docs/benchmarks/runs/*.json and surface drift in win rate, latency, escalation rate, and LLM-baseline cost over timeruvnetwritescoupa-automationAutomate Coupa tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcpm-schedule-generatorCritical Path Method scheduling skill for construction schedule development and analysisa5c-aiwritescpu-profiler-configConfigure cpu profiler config operations. Auto-activating skill for Performance Testing. Triggers on: cpu profiler config, cpu…jeremylongshorewritescraftmypdf-automationAutomate Craftmypdf tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcreate-agentCreates and configures agent.yaml files, writes SOUL.md personality definitions, and sets up agent directory structures with…open-gitagentcreate-agentsmdPrompt for generating an AGENTS.md file for a repositorygithubcreate-custom-agentCreates VS Code custom agent files (.agent.md) for specialized AI personas with tools, instructions, and handoffs. Use when…dotnetcreate-pluginScaffold a new Claude Code plugin with proper directory structure, plugin.json, skills, commands, and agentsruvnetwritescreate-prThis skill should be used when user asks to "create a PR", "make a pull request", "open PR for this branch", "submit changes as…fcakyoncreating-agent-skills-skillUse when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io…AgentWorkforcecreating-claude-agentsUse when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool…AgentWorkforcecreating-claude-rulesUse when creating or fixing .claude/rules/ files - provides correct paths frontmatter (not globs), glob patterns, and avoids…AgentWorkforce
← Prev68 / 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