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
1,1531,200 · page 25 / 26
nested-subagentsSpawn nested sub-agents (agents that spawn sub-agents, up to depth=5) via Claude Code's native Task tool — for context-managed…ruvnetwritesobserval-agentsCreate, update, version, and manage Observal agents. Use when the user wants to create a new agent, update an existing one…Observalontario_witty_real_estate_agentA charismatic real estate assistant for Ontario that autonomously classifies user intent (buyer/seller/investor) and transaction…ECNU-ICALKoptim-agentUse when optimizing configurable system parameters against a measurable scalar objective.Optim-Agentoptim-agentGuide agent-driven parameter optimization for configurable systems with measurable objectives. Use for HPO, inference tuning…sickn33options-analytics-agent-guideAI agent for options pricing, Greeks, and strategy analysisbrycewang-stanfordorquestracao-kanban-humano-agenteOrquestrar projetos com Kanban humano + agentes de IA.Hermes-brasilpaper-to-agent-guideTransform research papers into interactive AI agents for explorationbrycewang-stanfordparallel-agentsMulti-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when…sickn33patent-agent-patentportfolioWenn es um Patent Agent Patentportfolio in Berufsrecht Patentanwälte geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und…Klotzkettepatent-agent-prior-art-sanktionenWenn es um Patent Agent Prior Art Sanktionen in Berufsrecht Patentanwälte geht: klärt Rolle, Ziel, Frist, Unterlagen und den…Klotzkettepatent-agent-title-und-werbung-kammerantwortWenn es um Patent Agent Title Und Werbung Kammerantwort in Berufsrecht Patentanwälte geht: ordnet Akteninhalt, Belege, Lücken und…Klotzkettepatent-agent-title-und-werbung-rechtsprechungscheckWenn es um Patent Agent Title Und Werbung Rechtsprechungscheck in Berufsrecht Patentanwälte geht: zerlegt Ergebnis, Frist…Klotzketteperformance-testing-review-multi-agent-reviewUse when working with performance testing review multi agent reviewsickn33Persona Agent InterviewerConducts a structured two-phase interview to build a user persona agent, asking 20 questions about background/skills followed by…ECNU-ICALKpkv-basistarif-standardtarif-notlagentarifWenn es um PKV: Basistarif, Standardtarif und Notlagentarif in Krankenkassenrecht und Krankenversicherung geht: prüft Frist…Klotzketteplan-agentPlanning agent that creates implementation plans and handoffs from conversation contextvibeevalpolis-protocol-a-self-optimizing-city-of-agentsPolis Protocol: A Self-Optimizing City of Agentssickn33PPO Agent for Multi-Parameter Tuning with Discrete ActionsImplements a PPO (Proximal Policy Optimization) agent and environment for tuning multiple continuous parameters using a…ECNU-ICALKppo_gnn_multitask_stability_agentImplements a PPO agent for continuous action spaces using Graph Neural Networks (GNN). The Actor features a multi-task head…ECNU-ICALKPPO Multi-Parameter Optimization AgentImplements a PPO agent and environment for optimizing multiple parameters where each parameter has three discrete actions…ECNU-ICALKrd-agent-guideMicrosoft AI-driven R&D agent for automated data and model developmentbrycewang-stanfordReasoningBank with AgentDBImplement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict…ruvnetreinforcement-learning-agentsDesign and train reinforcement learning agents — environment setup, reward shaping, policy gradient methods, and evaluation.a5c-aiwritesrepairing-workspaces-agentsRepairs and upgrades existing Friday workspaces, jobs, user agents, and generated agents to current runtime contracts. Use when a…friday-platformresearch-agentResearch agent for external documentation, best practices, and library APIs via MCP toolsparcadeireview-agent-setupConfigure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may…wshobsonrun-agentConfigures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Supports local…open-gitagentself-evolving-single-agentUse when generating a single installable agent that should keep learning, track sources, refresh research, propose repairs, or…agentlas-aiself-improving-agentRepo-local meta-skill for improving Xiaobai Skills over time. Use after significant project changes, user feedback, install…TyutsSolve Principal-Agent Incentive ContractsSolves for optimal incentive contracts in a basic principal-agent model with binary effort and profit levels. The skill involves…ECNU-ICALKsub-agentDelegate a self-contained task to a sub-Agent (Codex, Claude Code, or Pi via background process). The original use case was…opensquillasub-agentsCreate and configure Claude Code sub-agents with custom prompts, tools, and modelsparcadeiwritessubagent-creatorGuide for creating AI subagents with isolated context for complex multi-step workflows. Use when users want to create a subagent…tech-leads-clubsubagent-driven-developmentExecute plans task-by-task with two-stage review.HezaoHezaowritesSubagent-Driven Literature ReviewUse parallel subagents for large-scale paper screening and deep dive analysisbrycewang-stanfordsubagentRun a one-shot or flat parallel batch of provider LLM subagents (headless `cc-fleet subagent`) that return a result. Use when…ethanhqsubagentProtocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's…evo-hqsubagent-orchestrationDecompose work across parallel subagents properly — task slicing that avoids collisions, briefs that stand alone, and result…mohitagw15856submit-to-agentlaunchSubmit an AI agent to agentlaunch (a Product Hunt-style directory for AI agents) and read the directory via a public, no-auth…davepoonsuggest-awesome-github-copilot-agentsSuggest relevant GitHub Copilot Custom Agents files from the awesome-copilot repository based on current repository context and…githubtaetigkeit-fristennotiz-agentische-datenbankWenn es um Taetigkeit: Fristennotiz und nächster Schritt in patentrecherche geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und…Klotzkettetalivia-agent-kitSet up and verify Talivia revenue analytics through MCP, with explicit confirmation for website changes and payment attribution.sickn33tesla / agent / euGeneral SOP for common requests related to tesla, agent, eu.ECNU-ICALK使用TF-Agents和LSTM构建多股票强化学习训练流程指导用户使用TensorFlow的TF-Agents库构建针对多只股票的强化学习训练代码。该技能涵盖自定义LSTM Q网络、使用BatchedPyEnvironment批量处理多股票环境、配置DQN代理、设置Replay…ECNU-ICALKtf_agents_lstm_multi_stock_training配置TF-Agents的DQN代理使用自定义LSTM网络处理多只股票的时间序列数据,涵盖环境批量打包、维度适配、网络初始化避坑以及完整的训练与评估循环,兼容TensorFlow 2.10.1。ECNU-ICALKTranslate React/ApexCharts components to ClojureScript/ReagentTranslates React class-based ApexCharts components into ClojureScript Reagent components, mapping React state to atoms and JSX to…ECNU-ICALKtravel-agent-skill私人旅行管家 — 从出发地到目的地的完整行程规划+攻略导出。 输入出发地、目的地、天数、预算、风格偏好,自动输出闭环行程, 包含交通推荐、酒店推荐、美食路线、每日预算,并可选生成攻略。 当用户提到「做攻略」「旅行规划」「旅游计划」「行程安排」时使用。davepoon
← Prev25 / 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