Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Discover and install related skills from inference.sh skill registry. Helps find complementary skills for your AI workflow. Use for: skill discovery, workflow expansion, capability exploration. Triggers: related skills, find skills, skill discovery, complementary skills, expand workflow, more capabilities, similar skills, skill suggestions
Enforcing Ring's orchestrator protocol every conversation: dispatch specialist/Explore agents instead of operating tools directly, honor the >3-file hard gate, and run skill discovery before any task. Use at conversation start, before any task, when a request matches auto-trigger phrases (fix issues, refactor, find where, visualize), or when tempted to read/edit files directly. Never skip — mandatory.
Create and manage scheduled tasks, with support for viewing, modifying, enabling/disabling, deleting and creating scheduled tasks. Use when the user wants to set up, modify or manage tasks that run automatically on a schedule. Create and manage scheduled tasks for recurring or one-time automated execution.
This skill should be used when users want guidance on Spec-Driven Development methodology using GitHub's Spec-Kit. Guide users through executable specification workflows for both new projects (greenfield) and existing codebases (brownfield). After any SDD command generates artifacts, automatically provide structured 10-point summaries with feature status tracking, enabling natural language feature management and keeping users engaged throughout the process.
在專案中建立並維護 Zeabur 部署規範，會在專案根目錄的 AGENTS.md 寫入一段部署約束（Zeabur 只支援 Dockerfile、不支援 docker-compose；compose 僅供本地開發測試）。僅在使用者明確指定專案要部署到 Zeabur 時才使用 — 例如使用者明說「這個專案要部署到 Zeabur」「要上 Zeabur」「設定 Zeabur 部署」，或直接呼叫此 skill。不要在僅僅提到 Docker、寫 Dockerfile、討論部署平台、或泛泛談到 Zeabur 時觸發；必須有明確的「部署到 Zeabur」意圖。This skill MUST be used only when the user explicitly states the project deploys to Zeabur, and MUST NOT be triggered by Docker usage, Dockerfile work, or general deployment talk.
Conduct a complete feature pipeline from idea to PR — interactive framing, specification, and task planning up front, then autonomous design-gated, test-driven, reviewed delivery per task. Use when the user says ship this, ship it, run the full pipeline, build this feature end to end, take this from idea to PR, or wants autonomous execution after an approved plan. Do not use for single small edits, pure reviews, or pure diagnosis — invoke the specific skill instead.
Search, discover, and install OpenClaw agent skills from multiple registries. Use when: user asks "find a skill for X", "is there a skill that can...", "how do I do X" (where X might have an existing skill), wants to browse available skills, or asks to install/add a skill. Also triggers on "search skills", "explore skills", "what skills exist for...", or "extend capabilities".
Ultimate Claude Code skill creator and architect. Designs, scaffolds, builds, reviews, evolves, and publishes production-grade Claude Code skills following the Agent Skills open standard and 3-layer architecture (directive, orchestration, execution). Handles single-file skills, multi-skill orchestrators with sub-skills and subagents, MCP-enhanced workflows, and full skill ecosystems. Industry detection for skill domain. Triggers on: "create skill", "build skill", "new skill", "skill creator", "skill builder", "skill-forge", "design skill", "scaffold skill", "review skill", "improve skill", "publish skill", "skill architecture", "convert skill", "port skill", "multi-platform", "cross-platform", "eval skill", "test skill", "benchmark skill", "skill evals", "measure skill", "skill performance", "skill A/B test".
Single entry point to install, update, delete, or check the status of any supported CodeArts skill/tool installer. Consolidates four installers behind one skill: superpowers, office-mcp, playwright-cli, and openspec. OpenSpec and other tools don't natively support CodeArts; this meta-installer bridges them. Specify the target via --target <name> (or positionally). Use whenever the user wants to install/update/delete any of these targets, or to list what's supported. Triggers on: install superpowers, install office-mcp, install playwright-cli, install openspec, 一键安装技能, 安装技能, skill installer, update skills, uninstall skills, 安装openspec, 安装office文档工具, 安装浏览器自动化工具.
This skill should be used after creating or modifying skills to update the main README.md file. It scans all skills in ~/.claude/skills/, extracts metadata from SKILL.md files, and regenerates the README with categorized skill listings. Triggers on requests mentioning "update skills readme", "refresh skills list", or after adding new skills.
After an agent answers, trace the original basis and sources of that answer. Use when the user says "查出处", "show sources", "原始依据在哪", "这条回答的来源是什么", or wants to verify the URLs/documents that support an answer; first list the sources the agent actually read in the conversation, then check primary sources for claims that lack citations, and write it up as a Markdown file.
Conversational design workshop for substantial work. Interviews the human one question at a time, explores 2-3 approaches with trade-offs, and presents the design section by section for approval before writing only design.md, then stops. Combines requirements discovery with codebase research and architecture design. Use when the user explicitly requests a spec or when atelier-orchestrator selects a Spec-backed Plan. Ambiguous design or discovery requests route through atelier-orchestrator.
Enforces spec-before-code workflow for AI-driven development. Automatically selects Spec-Kit or OpenSpec mode, triages complexity (quick/standard/thorough), recovers session context, and applies quality gates (G0-G4) with inline self-review at every stage. Use this skill whenever the user says "/super-spec", "spec first", "规范先行", or starts any feature, bugfix, or refactor — especially in projects with .spec-mode, .specify/, or openspec/ directories. Even if the user doesn't explicitly ask for spec-driven workflow, activate this skill for any non-trivial code change to prevent skipping the design phase. Orchestrates: Spec-Kit (v0.7.1, Workflow Engine) / OpenSpec (OPSX v1.2.0) + planning-with-files (v2.30.0) + ui-ux-pro-max (v2.5.0, 67 styles, 161 palettes, 14 stacks, 6 specialist skills) + Superpowers (v5.0.7, inline self-review, subagent model selection) + MemPalace (v3.3.0, 29 MCP tools, cross-session memory, knowledge graph).
Development workflow generator — Generate issue-to-pr-workflow.md for your project. Creates a project-specific development workflow through interactive dialogue, covering branch strategy, quality gates, development style, and optional sub-agent definitions. English triggers: "Generate workflow", "Create development workflow", "Setup issue-to-PR flow" 日本語トリガー: 「ワークフローを生成」「開発フローを作成」「Issue-to-PRフローを設定」
(NS) Transform atomic implementation work into rich task markdown files for backend and frontend layers with dependencies, estimates, and layer-specific checklists. Use during SDD planning when generating task-NNN-*.md from requirements features — not for E2E or unit test tasks (use specialized generators). Requires requirements.md. Output English task files under version tasks folder.
Break a ready feature specification into small, implementation-ready vertical-slice tasks with complete acceptance-criteria coverage, explicit dependencies, session-ready context, and concrete verification. Use when a ready spec is too broad for one focused implementation session or needs durable work items for implementation and review.
Use this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery. This skill provides access to 600+ scientific tools including machine learning models, datasets, APIs, and analysis packages. Use when searching for scientific tools, executing computational biology workflows, composing multi-step research pipelines, accessing databases like OpenTargets/PubChem/UniProt/PDB/ChEMBL, performing tool discovery for research tasks, or integrating scientific computational resources into LLM workflows.
Use when you are a registered relay agent (a spawned worker, or a lead that called register_agent) coordinating with peers in real time over current Agent Relay MCP tools - messaging, channels, threads, reactions, search, inbox, actions, and worker spawn/release. For role selection and orchestrator startup instructions, use https://agentrelay.com/skill and the orchestrating-agent-relay skill.
Route a prompt to the right Venice text model based on privacy tier (anonymized / private / TEE / E2EE), modality (vision / audio / video input), capability (reasoning, reasoning effort, code, function calling, X search, large context, structured output), uncensored needs, and cost. Use when a local agent (Claude Code, Hermes, NanoClaw, Codex CLI, etc.) needs to decide whether to handle a prompt locally or escalate to Venice, and if escalating, which Venice text model to call. Sits one level above venice-models (model discovery) and before venice-chat (the call surface).
Orchestrate AI coding with Vibe Kanban: tasks, review, sessions, workspaces, and isolated git worktrees. Use when managing AI-generated code in isolated environments, planning coding tasks, reviewing AI output, or configuring Vibe Kanban workspaces and agents. Keywords: Vibe Kanban, AI orchestration, worktrees.
Enforces a test-driven approach to skill authoring — defining what a skill must achieve before writing content to prevent hallucinated utility or ungrounded advice. Use when creating new skills, editing existing ones, or verifying skill quality before deployment.
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.
Drive external CLI coding agents (Claude Code, Codex, OpenCode) as first-class AG2 Agents over the Agent Client Protocol (ACP): point an Agent at a ClaudeCodeConfig / CodexConfig / OpenCodeConfig preset from ag2.acp and ask()/run() it like any agent, with its thinking, tool calls, plans and permission prompts externalized onto AG2's event stream. Use when orchestrating, observing, or gating CLI coding agents from Python — permission_policy ask/auto/deny HITL gating, fs_root confinement, turn timeouts, in-process testing via fake_acp_config. To expose an AG2 agent to other systems instead, see ag2-a2a or ag2-mcp; for approval plumbing see ag2-hitl.
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video
Bootstrap and manage the .ai/ shared context directory for multi-agent projects. Use when initializing agent handoff, bootstrapping .ai/ files, refreshing stale handoff state, creating or repairing session files, or when the user says "agent handoff", "bootstrap", "initialize", "set up handoff", "what did the last agent do", "continue where X left off", or "resume".
Add persistent memory to AI coding agents — file-based, vector, and semantic search memory systems that survive between sessions. Use when a user asks to "remember this", "add memory to my agent", "persist context between sessions", "build a knowledge base for my agent", "set up agent memory", or "make my AI remember things". Covers file-based memory (MEMORY.md), SQLite with embeddings, vector databases (ChromaDB, Pinecone), semantic search, memory consolidation, and automatic context injection.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.