Agent skills

Skills matching “agent”

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
1,221 found
289336 · page 7 / 26
agent-mlopsProduction deployment and operationalization of AI agents on Databricks. Use when deploying agents to Model Serving, setting up…majiayu000agent-native-architectureBuild applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools…majiayu000agent-native-architectureThis skill should be used when building AI agents using prompt-native architecture where features are defined in prompts, not…majiayu000agent-nativeMake an out-of-session Claude (Managed Agent or Agent SDK loop) AgentOps-native — via skills + the ao CLI + CI, not hooks.majiayu000agent-nlp-engineerExpert NLP engineer specializing in natural language processing, understanding, and generation. Masters transformer models, text…majiayu000agent-o-ramaLayer 4: Learning and Pattern Extraction for Cognitive Surrogate Systemsmajiayu000agent-o-ramaLayer 4 Learning and Pattern Extraction for Cognitive Surrogate Systemsmajiayu000agent-onboardingComprehensive framework for effective gptme agent onboarding that builds user trust, communicates capabilities clearly, and…majiayu000agent-ops-article-verificationSystematically deconstruct written content into verifiable claims, validate each using search/documentation, and facilitate…majiayu000agent-ops-constitutionCreate/update .agent/constitution.md. Use when commands/boundaries/constraints must be confirmed before baseline or code changes.…majiayu000agent-ops-context-mapAnalyze the codebase to create a concise, LLM-optimized structured overview in .agent/map.md.majiayu000agent-ops-docker-reviewDocker image reviews, optimization, and step-building guidance. Analyzes Dockerfiles for best practices, security issues, and…majiayu000agent-ops-dogfoodDogfooding discovery agent — establish human-approved project baseline from public docs without code inspectionmajiayu000agent-ops-git-analysisAnalyze git repository for insights: contributor stats, commit patterns, branch health, and change analysis. Outputs actionable…majiayu000agent-ops-git-storyGenerate narrative summaries from git history for onboarding, retrospectives, changelogs, and exploration. LLM-enhanced when…majiayu000agent-ops-improvement-discoveryIdentifies concrete justified improvements aligned with project goalsmajiayu000agent-ops-interviewConduct structured interviews with the user. Use when multiple decisions need user input: ask ONE question at a time, wait for…majiayu000agent-ops-potential-discoveryAnalyze incoming content (text, files, folders, URLs) to extract purpose, create summaries, and identify potential value for the…majiayu000agent-ops-project-sectionsIdentify and map different sections of a software project (API, frontend, database, CLI, domain). Use for context scoping and…majiayu000agent-ops-reality-auditAggressive evidence-based audit to verify project claims match implementation realitymajiayu000agent-ops-reportGenerate markdown reports from issues. Filter by type, priority, epic, date range. Supports summary, detailed, progress…majiayu000agent-ops-researchConduct structured research on topics, technologies, libraries, patterns, or any subject requiring investigation. Produces…majiayu000agent-ops-specManage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature…majiayu000agent-ops-stateMaintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update…majiayu000agent-ops-toolsDetect available development tools at session start. Saves to .agent/tools.json and warns about missing required tools. Works…majiayu000agent-optimizationImprove an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.Prism-Shadowagent-orchestrationThis skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents.…majiayu000agent-orchestrationAI DevKit · Supervise multi-agent workflows over repeated passes: poll progress, unblock waiting agents, coordinate dependencies…codeaholicguyAgent Orchestration PatternsMulti-agent coordination patterns for building effective AI teamsmajiayu000agent-orchestration-improve-agentSystematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.majiayu000agent-orchestration-multi-agent-optimizeOptimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving…majiayu000agent-organizerExpert in designing, orchestrating, and managing multi-agent systems (MAS). Specializes in agent collaboration patterns…majiayu000agent-os-frameworkGenerate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision…majiayu000agent-output-formatsStandardized output formats for research, planning, implementation, and review agents. Use when generating agent outputs or…majiayu000agent-patternsExecute this skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination"…majiayu000agent-performanceTrack and report agent invocation metrics including usage counts, success/failure rates, and completion times. Use for…majiayu000agent-prompt-behaviorDesign agent system prompts with explicit behavior rules and cognitive control. This skill should be used when users need to…majiayu000agent-prompt-designCreate well-structured prompts for AI agents using proven architecture patterns. Use when users ask to write agent prompts…majiayu000agent-prompt-engineerExpert prompt engineer specializing in designing, optimizing, and managing prompts for large language models. Masters prompt…majiayu000agent-promptsThis skill should be used when the user asks to "generate tasks", "create implementation plan", "break down feature", "write…majiayu000agent-protocolInter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and…alirezarezvaniagent-provisionerMANDATORY workflow for creating new agents. Enforces -01-agent-formatting standards from inception, ensuring every new agent is…majiayu000agent-quant-analystExpert quantitative analyst specializing in financial modeling, algorithmic trading, and risk analytics. Masters statistical…majiayu000Agent Reasoning & Decision-MakingDesign effective reasoning processes for AI agents and optimize decision-making strategies. Use when designing agent prompts…majiayu000agent-registryGuide for managing the Agent Registry - database-backed agent configuration system. Use when asked to "configure agents", "manage…majiayu000Agent Reliability & SafetyDesign reliable, safe, and trustworthy agent systems that fail gracefully and operate within bounds. Use when building…majiayu000agent-repairA two-phase repair skill that analyzes errors and suggests fixes before executing repairs. Phase one: user describes error, agent…majiayu000agent-research-analystExpert research analyst specializing in comprehensive information gathering, synthesis, and insight generation. Masters research…majiayu000
← Prev7 / 26Next →
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