通用开发任务编排器。将复杂开发任务拆解为专业 agent 角色并协调协作。当需要'组建团队'、'任务分解'、'多 agent 协作'、'组队开发'、'并行开发'、'团队协作'时使用。后续任务支持：'修改团队'、'调整分工'、'重新执行'、'更新计划'、'仅重新执行某阶段'。对于简单任务或单文件改动，直接完成，仅在复杂度确实需要多角色协作时启用。
Connect your OpenClaw agent to the EvoMate Evolution Lab. Create or join a private evolution room using a Room Code, then breed a next-generation child agent through real-time genetic fusion with a partner agent.
Use this skill when you need to discover remote agents, fetch their capabilities via A2A Agent Cards, or invoke tasks on remote A2A-compatible agents. Triggers include "discover agent", "find agent", "agent card", "invoke remote agent", "send task to agent", "A2A", or any reference to inter-agent communication beyond simple messaging.
Help developers design or review useful, controllable, extensible agentic systems and products. Use when the user is designing an agent architecture, harness, tool system, memory strategy, permission model, interaction loop, recovery plan, or evaluation strategy, or when they want to turn a vague vibe-coded agent idea into a disciplined product plan. Do not use for simple code generation, generic brainstorming, or purely cosmetic UI critique.
Persistent memory and evolving identity for AI agents. Gives your agent a knowledge graph, session continuity, persona management, and adaptive retrieval that survives across sessions. Boot at session start, ingest every turn. Your agent remembers everything.
Generates Claude Code plugin agent .md files: writes YAML frontmatter (name, model, color, tools, hooks, disallowedTools), crafts system prompts, and creates triggering example blocks with context and commentary. Validates agent structure against naming, length, and format constraints. Use when the user asks to create an agent, add an agent, write a subagent, configure agent frontmatter, design agent system prompts, set agent tools or colors, build an autonomous agent, or add agent hooks. --- # Agent Development for Claude Code Plugins Agents are autonomous markdown files with YAML frontmatter that handle multi-step tasks independently. Agents are for autonomous work; commands are for user-initiated actions. ## Workflow 1. Define agent purpose and triggering conditions 2. Create `agents/agent-name.md` with frontmatter + system prompt body 3. Include 2-4 `<example>` blocks in description 4. Validate structure (see constraints below) 5. Test triggering with real scenarios 6. If validation fails: check error recovery table, fix, re-validate ## Agent File Template ```markdown ---
百度地图Map Agent Plan，官方为 Agent专属AI地图技能，直连 place、direction、geocoding、reverse_geocoding、weather 五大核心能力，大模型一键调用地图服务。
Use this skill when an agent is managing its own micro.blog identity with mb. It covers autonomous posting, voice consistency, disclosure, and how an agent should participate as itself rather than impersonating a human user.
Initialize a multi-agent development team for any project. Use this skill whenever the user wants to set up, bootstrap, create, or design specialized agents for their codebase — including requests to "set up agents", "create a team", "organize work into agents", "bootstrap cadre", or "generate agent configuration". Also triggers for requests to scope agents to project directories (monorepo packages, microservices, frontend/backend splits). Handles both existing projects (analyzes codebase structure) and greenfield projects (interviews user first). Generates .claude/agents/*.md files, config.yaml, routing rules, and a local /cadre coordinator skill.
Use this skill when the user wants to manage AI agent knowledge, organize agent configurations, or set up post-session learning systems. Triggers include: organizing agent skills or knowledge into a structured shelf, extracting insights from conversation transcripts, splitting monolithic agent config files into modular pieces, managing memory files, searching indexed knowledge, or diagnosing shelf health. Use ShelfAI whenever a user mentions managing agent context, chunking configs, learning from sessions, compacting memory, or organizing reusable agent knowledge pieces.
Use when working in a repo that uses Codaph and you need shared agent history, a fresh context block before starting Claude or Codex, a checkpoint before risky edits, diagnostics for agent loops, or explicit handoffs between agents.
Governance framework for deciding whether a new capability should be an agent, a skill, or handled by the main agent directly. Use this skill BEFORE creating any new agent or skill. Triggers on: "I need the system to do X", "should this be an agent?", "add capability for X", "create an agent for X", "we need a new agent", "should I make a skill for this?". Also activates when the skill-creator skill is about to be used — architect runs first as a gatekeeper to prevent agent/skill sprawl. Use proactively whenever you're about to create something new in .claude/agents/ or .claude/skills/. --- # Architect — Capability Design Framework You're about to add a new capability to AOS. Before writing any code or creating any files, run through this framework to determine the right form factor: **agent**, **skill**, **main agent**, or **extend existing**. ## The Company Model
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
