← 返回
未分类 中文

Agent Skills

Agent Skills standard reference guide. Covers SKILL.md specification format, progressive disclosure mechanism, skill discovery and activation, frontmatter me...
Agent技能标准参考指南,涵盖SKILL.md规范格式、渐进加载、技能发现与激活、创作最佳实践、质量评估和描述优化。
openlark openlark 来源
未分类 clawhub v1.0.1 2 版本 100000 Key: 无需
★ 0
Stars
📥 352
下载
💾 0
安装
2
版本
#latest

概述

Agent Skills Standard

> A standardized way to equip AI Agents with new capabilities and domain expertise. Adopted by 35+ Agent products.

Use Cases

Use when creating new skills, validating skill formats, optimizing existing skills, or learning about standardized skill system design.

Reference File Routing

NeedRead
------------
Quick skill creation (5-step guide)quick-start.md
SKILL.md format spec + Agent integrationspec.md
Authoring best practices + quality eval + description optimizationauthoring.md
Common anti-patterns and fixesanti-patterns.md
Script binding and designusing-scripts.md
Supported product listproducts.md

Minimal Example

---
name: pdf-processing
description: Extract PDF text, fill forms, merge files. Use when handling PDFs.
---

## Workflow
1. Extract: `python scripts/extract.py input.pdf`
2. Fill: `python scripts/fill.py template.pdf data.json`

## Gotchas
- Scanned PDFs need OCR first — use `scripts/ocr.py`

Validation

skills-ref validate ./my-skill

版本历史

共 2 个版本

  • v1.0.1 当前
    2026-06-30 16:35
  • v1.0.0
    2026-05-29 21:36 安全 安全

安全检测

腾讯云安全 (Keen)

队列中

腾讯云安全 (Sanbu)

队列中

🔗 相关推荐

content-creation

Toutiao Graphic Publisher

openlark
通过浏览器自动化在头条发布图文内容,支持智能排版、自动生成热门标签等功能。
★ 2 📥 1,094
ai-agent

Find Skills

root
帮助用户发现和安装智能体技能,当用户询问如「如何做X」、「找X的技能」、「有能做...的吗」等问题时
★ 1,546 📥 592,942
ai-agent

self-improving agent

pskoett
记录自身发现以实现自我改进的技能
★ 4,189 📥 959,753