技能模板
- 作者仓库星标 15,902
- 作者仓库 Agent-Skills-for-Context-Engineering
- 领域
- 人工智能
- 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
- 88 / 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
- @muratcankoylan · 未声明许可证
- 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
- 未声明(默认跨平台)
- 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。
Input: [describe input]
Output: [show expected output]
# Skill Name
Provide a clear, concise description of what this skill covers and when to use it. This description appears in skill discovery and should help agents (and humans) determine when this skill is relevant.
**Important**: Keep the total SKILL.md body under 500 lines for optimal performance. Move detailed reference material to separate files in the `references/` directory.
Every skill body must make its ownership boundary explicit. The description and `When to Activate` section should say what the skill owns and which adjacent skills own nearby work. This prevents broad skills from stealing activation from narrower skills.
## When to Activate
Describe specific situations, tasks, or contexts where this skill should be activated. Include both direct triggers (specific keywords or task types) and indirect signals (broader patterns that indicate skill relevance).
Write in third person. The description is injected into the system prompt, and inconsistent point-of-view can cause discovery problems.
- Good: "Processes Excel files and generates reports"
- Avoid: "I can help you process Excel files"
Include a short "Do not activate" block for adjacent skills. Example:
- Do not activate for project-level pipeline shape: `project-development`.
- Do not activate for individual tool schema design: `tool-design`.
## Core Concepts
Explain the fundamental concepts covered by this skill. These are the mental models, principles, or frameworks that the skill teaches.
Default assumption: Claude is already very smart. Only add context Claude does not already have. Challenge each piece of information:
- "Does Claude really need this explanation?"
- "Can I assume Claude knows this?"
- "Does this paragraph justify its token cost?"
Prefer behavior-changing mechanisms over general background. If a concept should be reusable across the corpus, add or update a record in `researcher/mechanisms/registry.jsonl`.
## Detailed Topics
### Topic 1
Provide detailed explanation of the first major topic. Include specific techniques, patterns, or approaches. Use examples to illustrate concepts.
### Topic 2
Provide detailed explanation of the second major topic. Continue with additional topics as needed.
For longer topics, consider moving content to `references/` and linking:
- See [detailed reference](./references/topic-details.md) for complete implementation
## Practical Guidance
Provide actionable guidance for applying the skill. Include common patterns, anti-patterns to avoid, and decision frameworks for choosing between approaches.
Match the level of specificity to the task's fragility:
- **High freedom**: Multiple approaches are valid, decisions depend on context
- **Medium freedom**: Preferred pattern exists, some variation acceptable
- **Low freedom**: Operations are fragile, specific sequence must be followed
Practical guidance should be executable by an agent: a workflow, checklist, decision table, or concrete operating rule. If a section only explains history or motivation, move it to `references/`.
## Examples
Provide concrete examples that illustrate skill application. Examples should show before/after comparisons, demonstrate correct usage, or show how to handle edge cases.
Use input/output pairs for clarity:
**Example:**
```
Input: [describe input]
Output: [show expected output]
```
## Guidelines
List specific guidelines to follow when applying this skill. These should be actionable rules that can be checked or verified.
1. Guideline one with specific, verifiable criteria
2. Guideline two with clear success conditions
3. Continue as needed
## Gotchas
List experience-derived failure modes, common mistakes, and counterintuitive behaviors. These are the highest-signal content in any skill. Each gotcha should be specific, actionable, and non-overlapping with guidance already in the skill body. Use numbered format:
1. **Short descriptive title**: One to two sentences explaining what goes wrong and how to prevent it.
2. **Another gotcha title**: Description of the failure mode and what to do instead.
## Integration
Explain how this skill integrates with other skills in the collection. List related skills as plain text (not links) to avoid cross-directory reference issues:
- skill-name-one - Brief description of relationship
- skill-name-two - Brief description of relationship
## References
Internal reference (use relative path to skill's own reference files):
- [Reference Name](./references/reference-file.md) - Description
Related skills in this collection:
- skill-name - Relationship description
External resources:
- Research papers, documentation, or guides
Numeric, benchmark, volatile, or vendor-performance claims need an inline `claim-*` ID backed by `researcher/claims/index.jsonl`, or they should be softened and moved to dated reference material.
---
## Skill Metadata
**Created**: [Date]
**Last Updated**: [Date]
**Author**: [Author or Attribution]
**Version**: [Version number]
章节与文件索引
按说明文件中的顺序排列。
何时激活
核心概念
主题1
主题2
实用指导
文件/命令 -> references/ · When to Activate · project-development · tool-design · researcher/mechanisms/registry.jsonl · claim-* · researcher/claims/index.jsonl
内容校验值 -> 5ca8c3588594
当前原文的自动摘译,尚未人工审校。
何时激活
描述应激活此技能的特定情况、任务或上下文。包括直接触发因素(特定关键字或任务类型)和间接信号(表明技能相关性的更广泛模式)。用第三人称写。描述被注入到系统提示中,不一致的观点会导致发现问题。好:“处理 Excel 文件并生成报告”
核心概念
解释该技能涵盖的基本概念。这些是技能所教授的心理模型、原则或框架。默认假设:克劳德已经非常聪明了。仅添加克劳德尚未拥有的上下文。挑战每一条信息:“克劳德真的需要这个解释吗?” “我可以假设克劳德知道这一点吗?” “这一段是否证明其代币成本合理?”
主题1
提供第一个主要主题的详细解释。包括具体的技术、模式或方法。使用示例来说明概念。
主题2
提供第二个主要主题的详细解释。根据需要继续其他主题。对于较长的主题,请考虑将内容移至
references/并链接:请参阅完整实施的详细参考实用指导
为应用该技能提供可行的指导。包括常见模式、要避免的反模式以及用于在方法之间进行选择的决策框架。将特异性水平与任务的脆弱性相匹配: 高自由度:多种方法有效,决策取决于上下文 中等自由度:存在首选模式,可接受一些变化 低自由度:操作脆弱,必须遵循特定顺序