- Documentation: https://agentskills.io/
- Repository: https://github.com/agentskills/agentskills
- The Open Agent Skills Ecosystem: https://www.skills.sh/
- https://platform.claude.com/docs/zh-CN/agents-and-tools/agent-skills/overview
- https://learn.chatgpt.com/docs/customization/overview#skills
- https://code.claude.com/docs/zh-CN/skills
What are Agent Skills?
Agent Skills are a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows.
my-skill/
├── SKILL.md # Required: metadata + instructions
├── scripts/ # Optional: executable code
├── references/ # Optional: documentation
├── assets/ # Optional: templates, resources
└── ... # Any additional files or directories
Why Agent Skills?
Skills provide procedural knowledge and company-, team-, and user-specific context into portable, version-controlled folders that agents load on demand. This gives agents:
- Domain expertise: Capture specialized knowledge — from legal review processes to data analysis pipelines to presentation formatting — as reusable instructions and resources.
- Repeatable workflows: Turn multi-step tasks into consistent, auditable procedures.
- Cross-product reuse: Build a skill once and use it across any skills-compatible agent.
How do Agent Skills work?
Agents load skills through progressive disclosure, in three stages:
- Discovery: At startup, agents load only the name and description of each available skill, just enough to know when it might be relevant.
- Activation: When a task matches a skill's description, the agent reads the full SKILL.md instructions into context.
- Execution: The agent follows the instructions, optionally executing bundled code or loading referenced files as needed.
Directory structure
skill-name/
├── SKILL.md # Required: metadata + instructions
├── scripts/ # Optional: executable code
├── references/ # Optional: documentation
├── assets/ # Optional: templates, resources
└── ... # Any additional files or directories
SKILL.md format
Frontmatter
---
name: skill-name
description: A description of what this skill does and when to use it.
---
Body content
Recommended sections:
- Step-by-step instructions
- Examples of inputs and outputs
- Common edge cases
Optional directories
scripts/: Executable code that the agent can run to perform tasks.references/: Documentation or reference materials that the agent can consult.assets/: Templates, resources, or other files that the agent can use.
Progressive disclosure
- Metadata (~100 tokens): The name and description fields are loaded at startup for all skills
- Instructions (< 5000 tokens recommended): The full SKILL.md body is loaded when the skill is activated
- Resources (as needed): Files (e.g. those in scripts/, references/, or assets/) are loaded only when required
Validation
https://github.com/agentskills/agentskills/tree/main/skills-ref
skills-ref validate ./my-skill
skills CLI
npx skills add vercel-labs/agent-skills
awesome skills
- https://github.com/anthropics/skills
- https://github.com/vercel-labs/agent-skills
- https://github.com/jimliu/baoyu-skills
- https://github.com/alchaincyf/huashu-design
- https://github.com/nextlevelbuilder/ui-ux-pro-max-skill
- https://github.com/joeseesun/qiaomu-knowledge-site-creator 可以一句话生成任何领域的知识型网站
- https://github.com/xiaohuailabs/xiaohu-wechat-format
- https://github.com/op7418/Humanizer-zh
- https://github.com/kostja94/marketing-skills
- https://github.com/AAAAAAAJ/infographic-skill
- https://github.com/mvanhorn/last30days-skill
- https://github.com/op7418/Claude-to-IM-skill
- https://github.com/Ceeon/remotion-skill
- https://github.com/AAAAAAAJ/infographic-skill 高密度信息大图生成专家 Skill
- https://github.com/AAAAAAAJ/slides 总结ppt