技能创作
- 作者仓库星标 205
- 许可证 MIT
- 作者仓库 GitHub-Copilot-for-Azure
- 领域
- 写作
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 94 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @microsoft · MIT
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- macOS · Linux · Windows
- 运行环境要求
- 未检出明确要求
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 命令执行
- 网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
# Skill Authoring Guide
This skill provides guidance for writing Agent Skills that comply with the [agentskills.io specification](https://agentskills.io/specification).
## When to Use
- Creating a new skill for this repository
- Reviewing a skill PR for compliance
- Checking if an existing skill follows best practices
- Understanding token budgets and progressive disclosure
## Constraints
- `name`: 1-64 chars, lowercase + hyphens, match directory
- `description`: 1-1024 chars, ≤60 words, explain WHAT and WHEN
- Use `WHEN:` with quoted trigger phrases (preferred over `USE FOR:`)
- Avoid `DO NOT USE FOR:` unless the skill has trigger overlap with a broader skill (see [frontmatter guidelines](references/guidelines/frontmatter.md))
- Use inline double-quoted strings (not `>-` folded scalars)
- SKILL.md: <500 tokens (soft), <5000 (hard)
- references/*.md: <1000 tokens each
## Structure
- `SKILL.md` (required) - Instructions
- `references/` (optional) - Detailed docs
- `scripts/` (optional) - Executable code
Frontmatter: `name` (lowercase-hyphens), `description` (WHAT + WHEN)
## Progressive Disclosure
Metadata (~100 tokens) loads at startup. SKILL.md (<5000 tokens) loads on activation. References load **only when explicitly linked** (not on activation). Keep SKILL.md lean.
## Reference Loading
References are JIT (just-in-time) loaded:
- Only files explicitly linked via `[text](references/file.md)` load
- **Link to files, not folders** - `[Recipes](references/recipes/README.md)` not `[Recipes](references/recipes/)`
- Each file loads in full (not sections)
- No caching between requests - write self-contained files
- Use recipes/services patterns for multi-option skills
See [REFERENCE-LOADING.md](references/REFERENCE-LOADING.md) for details.
## Validation
```bash
# Run from the scripts directory
cd scripts
npm run references # Validate all skill links
npm run tokens -- check # Check token limits
```
### Integrity Checks
When reviewing or authoring skills, verify:
1. **No broken links** - All referenced files exist
2. **No orphaned references** - All reference files are linked
3. **Token budgets** - References under 1000 tokens (split if exceeded)
4. **No duplicates** - Consolidate repeated content
5. **No out-of-place guidance** - Service-specific content belongs in service-specific references
See [Validation](references/validation/README.md) for detailed procedures.
## Reference Documentation
- [Guidelines](references/guidelines/README.md) - Detailed writing guidelines
- [Token Budgets](references/token-budgets.md) - Limits and splitting guidance
- [Reference Loading](references/REFERENCE-LOADING.md) - How references load
- [Checklist](references/CHECKLIST.md) - Pre-submission checklist
- [Validation](references/validation/README.md) - Link and reference validation
- [agentskills.io/specification](https://agentskills.io/specification) - Official spec
章节与文件索引
按说明文件中的顺序排列。
何时使用
约束条件
结构
渐进式披露
参考加载
文件/命令 -> name · description · WHEN: · USE FOR: · DO NOT USE FOR: · references/ · scripts/ · [text](references/file.md)
内容校验值 -> 32e398562805
当前原文的自动摘译,尚未人工审校。
何时使用
为此存储库创建新技能 审查技能 PR 的合规性 检查现有技能是否遵循最佳实践 了解代币预算和渐进式披露
约束条件
name:1-64 个字符,小写 + 连字符,匹配目录description:1-1024 个字符,≤60 个单词,解释什么和何时 将WHEN:与引用的触发短语一起使用(优于USE FOR:) 避免使用DO NOT USE FOR:,除非该技能与更广泛的技能有触发重叠(请参阅frontmatter 指南)使用内联双引号字符串(不是>-折叠标量)结构
SKILL.md(必填) - 说明references/(可选) - 详细文档scripts/(可选) - 可执行代码 Frontmatter:name(小写连字符),description(内容 + 时间)渐进式披露
元数据(约 100 个令牌)在启动时加载。 SKILL.md(<5000 个令牌)在激活时加载。引用仅在显式链接时加载(而不是在激活时加载)。保持 SKILL.md 的精益。
参考加载
引用是 JIT(即时)加载的:仅通过
textload 显式链接的文件链接到文件,而不是文件夹 -Recipes不是Recipes每个文件完整加载(而不是部分) 请求之间没有缓存 - 写入独立文件