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
2,6892,736 · page 57 / 104
workshop-facilitationFacilitate workshop sessions in a one-step, multi-turn flow. Use when an interactive skill needs consistent pacing, options, and…deanpetersworld-compositionLarge world streaming skill for world partition.a5c-aiwritesworld-memory-worldingWorld memory is world remembering is world worlding - the autopoietic loop where memory enables remembering enables worlding…majiayu000xbox-gdkXbox GDK skill for achievements and certification.a5c-aiwritesxenodium-elispXenodium's Emacs packages: chatgpt-shell, agent-shell, dwim-shell-command, and ACP integration for modern Emacs development.majiayu000xiaohongshu-netfeel-guardian当用户用 Claude 写小红书、公众号、视频脚本等内容时,输出出现翻译腔、英文思考、西式框架,导致“像外国人假装写中文”时使用。 典型触发语句: - “Claude写小红书翻译腔太重”“英文思考输出灾难” -…majiayu000xml-standardsXML tag structure patterns for Claude Code agents and commands. Use when designing or implementing agents to ensure proper XML…majiayu000subagent-prompt-constructionSystematic methodology for constructing compact (<150 lines), expressive, Claude Code-integrated subagent prompts using lambda…majiayu000yann-lecun-debateSub-skill de debates e posições de Yann LeCun. Cobre críticas técnicas detalhadas aos LLMs, rivalidades intelectuais (LeCun vs…majiayu000yann-lecun-filosofiaSub-skill filosófica e pedagógica de Yann LeCun.majiayu000yann-lecun-tecnicoSub-skill técnica de Yann LeCun. Cobre CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machinery of…majiayu000zbrushZBrush skill for decimation and normal map baking.a5c-aiwriteszephyr-rtosSpecialized skill for Zephyr RTOS development and configurationa5c-aiwriteszhimeng-agentzhimeng's Agent 智能助手操作技能。 触发场景:用户提到"问知识库"、"发日报"、"检查Agent"、"重建索引"、"知识问答"等。majiayu000zipai-optimizerAdaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware, MCP-aware.majiayu000zoom-outStep up one layer of abstraction and surface a map of relevant modules and callers when the local view is too narrow. Trigger…majiayu00010-andruia-skill-smithIngeniero de Sistemas de Andru.ia. Diseña, redacta y despliega nuevas habilidades (skills) dentro del repositorio siguiendo el…sickn3318-referral-programKhi nguoi dung can thiet ke chuong trinh gioi thieu bạn be (referral program), affiliate, hoac word-of-mouth. Cung dung khi nguoi…minhnv0807-21risk-automationAutomate 21risk tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQ-2chat-automationAutomate 2chat tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQa3-problem-solverA3 problem-solving and status reporting skill with structured thinking and coaching supporta5c-aiwritesaamas-experimentsUse when designing or auditing AAMAS experiments - self-play and population-based training, opponent selection, equilibrium and…brycewang-stanfordabc-xyz-classifierMulti-dimensional inventory classification skill combining value (ABC) and demand variability (XYZ) analysis for differentiated…a5c-aiwritesably-automationAutomate Ably tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQabstract-automationAutomate Abstract tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQabuselpdb-automationAutomate Abuselpdb tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQabyssale-automationAutomate Abyssale tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQAcademic Competitive Strategy Analysis using T3 Model and Economic TheoriesAnalyzes competitive interactions between two entities using Transaction Cost Economics and Game Theory, structured via the T3…ECNU-ICALKacademic-research-hubUse this skill when users need to search academic papers, download research documents, extract citations, or gather scholarly…BioTender-maxaccelo-automationAutomate Accelo tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQacceptance-criteria-creatorCreate acceptance criteria creator operations. Auto-activating skill for Enterprise Workflows. Triggers on: acceptance criteria…jeremylongshorewritesaccint-solveRoute a goal through acc's scored-memory loop via acc_act(runtime="solve"); deliberate any returned brain_frame and submit via…sickn33account-reconciliation-automatorAutomated account reconciliation skill with matching algorithms and exception handlinga5c-aiwritesaccredible-certificates-automationAutomate Accredible Certificates tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQacculynx-automationAutomate Acculynx tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQacl-related-workUse when positioning an ACL submission against the NLP literature, covering ACL Anthology citation practice…brycewang-stanfordacm-ieee-international-conference-on-model-driven-engineering-languages-and-systemsUse when targeting ACM/IEEE International Conference on Model Driven Engineering Languages and Systems (MODELS) or deciding…brycewang-stanfordacmg-variant-classifierACMG/AMP variant classification skill for systematic pathogenicity assessmenta5c-aiwritesacp-routerRoute plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw ACP…SafeAI-Lab-Xacreadiness-generate-instructionsGenerate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default…githubactive-campaign-automationAutomate ActiveCampaign tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQactivecampaign-automationAutomate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and…davepoonactivecampaign-automationAutomate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and…sickn33a-different-nameValidate a skill. Don't use for unrelated docs.luongnv89ada-compliance-checkerADA accessibility compliance checking skill for routes, slopes, and pedestrian facilitiesa5c-aiwritesAdaptive PPO Exploration via Reward HistoryImplements a dynamic exploration mechanism for a PPO agent that adjusts action variance based on reward trends. It compares…ECNU-ICALKadd-educational-commentsAdd educational comments to the file specified, or prompt asking for file to comment if one is not provided.githubadd-memory-kindAdd a new business memory kind end-to-end. Pick the storage combination (Markdown / SQLite / LanceDB), pick the markdown strategy…EverMind-AI
← Prev57 / 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