Menu
Claude Skills 创建指南与最佳实践
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
研究一个**已知的** GitHub 项目/repo，判断它对 LiYe Systems 的进化有没有可借鉴之处，产出定型的 evolution-recon 报告并归档到 recon-log。Use whenever the user gives a specific GitHub repo URL and asks to 研究/研读/消化/digest/study it, wants to know whether a project 对 LiYe / AGE / loamwise 有没有帮助/可借鉴/值得参考, asks "这个项目对我们有没有用", floats "看看 <repo> 有没有能学的", or types /github-digest — even if they never name the report format. This is the KNOWN-repo research step that sits UPSTREAM of github-scout (which DISCOVERS unknown repos) and source-intake (which INGESTS a chosen repo). Reach for it when the repo is already chosen and the real question is "is it worth our attention / what can LiYe learn". Do NOT use it to search/discover repos (that is github-scout) or to actually vendor/ingest a repo (that is source-intake).
Use when testing SFC v0.2 frontmatter compatibility.
SFC patched skill. Use when "ui-ux" is relevant.
内容研究与写作助手
视觉设计与艺术创作工具
主题样式工厂 - 统一视觉风格应用
| name | skill-creator |
| description | Claude Skills 创建指南与最佳实践 |
| domain | 00_Core_Utilities |
| category | meta |
| version | 1.0.0 |
| status | active |
| source | awesome-claude-skills |
| source_url | https://github.com/ComposioHQ/awesome-claude-skills |
| license | Apache-2.0 |
| skeleton | reference |
| triggers | {"commands":["/skill-creator","/create-skill"],"patterns":["create skill","new skill","build skill"]} |
| inputs | {"required":[],"optional":["name","description","skeleton","source_url"]} |
| outputs | {"artifacts":["SKILL.md","scripts/","references/"]} |
| failure_modes | [{"symptom":"Missing source materials","recovery":"Provide valid URL or local path"},{"symptom":"Invalid skeleton selection","recovery":"Choose from: workflow | task | reference | capabilities"}] |
| verification | {"evidence_required":true,"how_to_verify":["node .claude/scripts/sfc_lint.mjs <skill_dir>"]} |
| governance | {"constitution":"_meta/governance/SKILL_CONSTITUTION_v0.1.md","policy":"_meta/policies/DEFAULT_SKILL_POLICY.md"} |
来源: ComposioHQ/awesome-claude-skills 适配: LiYe OS 三层架构
提供创建 Claude Skills 的完整指导，包括专业知识封装、工作流设计、工具集成等。
当需要创建新的 Claude 技能时：
标准目录结构：
skill-name/
├── SKILL.md # 必须：技能定义文件
├── scripts/ # 可选：辅助脚本
├── templates/ # 可选：文档模板
└── references/ # 可选：参考资料
必须包含的 Frontmatter：
---
name: skill-name
description: 清晰描述技能功能
domain: 所属域
version: 1.0.0
status: active | draft | deprecated
---
必须包含的章节：
在 LiYe OS 中创建技能需要考虑三层架构：
L1 方法论层 (docs/methodology/):
# skill_definition.md - 10 模块结构
1. Skill Identity
2. Capability Model
3. Mental Models
4. Methods & SOPs
5. Execution Protocols
6. Output Structure
7. Templates
8. Tools Access
9. Evaluation
10. Evolution
L2 可执行层 (src/skill/atomic/):
// index.ts
export const skill: Skill = {
id: 'skill-name',
name: 'Skill Name',
execute: async (input) => { ... }
};
// spec.yaml
id: skill-name
type: atomic
input: { ... }
output: { ... }
L3 指令层 (.claude/skills/):
# SKILL.md - 简洁的使用指导
针对 Claude 的操作指令
用户: 帮我创建一个 Amazon 广告分析技能
Claude: [使用 skill-creator 技能设计结构、生成模板文件]
用户: 把这个 API 文档转换成 Claude 技能
Claude: [使用 skill-creator 技能提取关键信息、生成 SKILL.md]
用户: 检查这个技能是否符合规范
Claude: [使用 skill-creator 技能对照最佳实践进行评审]
无外部依赖，纯知识型技能。
此技能被以下业务域引用：
/docs/architecture/SKILL_SPEC.md/_meta/skill_template/Created: 2025-12-28 | Adapted for LiYe OS