intent-layer

分类: 工具与效率 | 上传者: crafter-station | 下载: 0 | 版本: v1.0（最新）

为代码库设置分层意图层（AGENTS.md 文件）。在初始化新项目、向现有存储库添加上下文基础设施、用户要求设置 AGENTS.md、添加意图层、使代理理解代码库或构建 AI 友好的项目文档时使用。 --- # Intent Layer 分层 AGENTS.md 基础设施，使代理可以像高级工程师一样导航代码库。 ## 核心原则 **只有一个根上下文文件。** CLAUDE.md 和 AGENTS.md 不应在项目根目录共存。对于复杂的子系统，鼓励在子目录中使用子 AGENTS.md。 ## 工作流程 ``` 1. 检测状态脚本/detect_state.sh /path/to/project → 返回：无 |部分 |完成 2. 无/部分布线 → 初始设置（步骤 3-5）完成 → 维护（步骤 6） 3. 测量 [gate - 首先显示表] scripts/analyze_struct.sh /path/to/project scripts/estimate_tokens.sh /path/to/each/source/dir 4. 决定没有根文件 → 问：CLAUDE.md 还是 AGENTS.md？具有根文件 → 如果需要，添加意图层部分 + 子节点 5. 执行使用references/templates.md 进行结构使用references/node-examples.md 进行实际模式

更新日志: Source: GitHub https://github.com/crafter-station/skills

目录结构

当前层级: tree/main/context-engineering/intent-layer/

📁 references/
- 📄 capture-protocol.md 2.2 KB
- 📄 node-examples.md 2.9 KB
- 📄 templates.md 1.6 KB
📁 scripts/
- 📄 analyze_structure.sh 1.6 KB
- 📄 detect_state.sh 1.3 KB
- 📄 estimate_tokens.sh 2.5 KB
📄 README.md 2.6 KB
📄 SKILL.md 2.5 KB

SKILL.md

---
name: intent-layer
description: >
  Set up hierarchical Intent Layer (AGENTS.md files) for codebases.
  Use when initializing a new project, adding context infrastructure to an existing repo,
  user asks to set up AGENTS.md, add intent layer, make agents understand the codebase,
  or scaffolding AI-friendly project documentation.
---

# Intent Layer

Hierarchical AGENTS.md infrastructure so agents navigate codebases like senior engineers.

## Core Principle

**Only ONE root context file.** CLAUDE.md and AGENTS.md should NOT coexist at project root. Child AGENTS.md in subdirectories are encouraged for complex subsystems.

## Workflow

```
1. Detect state
   scripts/detect_state.sh /path/to/project
   → Returns: none | partial | complete

2. Route
   none/partial → Initial setup (steps 3-5)
   complete     → Maintenance (step 6)

3. Measure [gate - show table first]
   scripts/analyze_structure.sh /path/to/project
   scripts/estimate_tokens.sh /path/to/each/source/dir

4. Decide
   No root file  → Ask: CLAUDE.md or AGENTS.md?
   Has root file → Add Intent Layer section + child nodes if needed

5. Execute
   Use references/templates.md for structure
   Use references/node-examples.md for real-world patterns
   Validate: one root, READ-FIRST directive, <4k tokens per node

6. Maintenance mode (when state=complete)
   Ask user:
   a) Audit nodes     → Use references/capture-protocol.md for SME questions
   b) Find candidates → Re-measure tokens, suggest new nodes
   c) Both
```

## When to Create Child Nodes

| Signal | Action |
|--------|--------|
| >20k tokens in directory | Create AGENTS.md |
| Responsibility shift | Create AGENTS.md |
| Hidden contracts/invariants | Document in nearest ancestor |
| Cross-cutting concern | Place at LCA |

Do NOT create for: every directory, simple utilities, test folders (unless complex).

## Capture Questions

When documenting existing code, ask:
1. What does this area own? What's out of scope?
2. What invariants must never be violated?
3. What repeatedly confuses new engineers?
4. What patterns should always be followed?

## Resources

**Scripts:**
- `scripts/detect_state.sh` - Check Intent Layer state (none/partial/complete)
- `scripts/analyze_structure.sh` - Find semantic boundaries
- `scripts/estimate_tokens.sh` - Measure directory complexity

**References:**
- `references/templates.md` - Root and child node templates
- `references/node-examples.md` - Real-world examples
- `references/capture-protocol.md` - SME interview protocol

登录后下载/点赞/收藏 ❤ 37 | ★ 0

intent-layer

目录结构

SKILL.md

举报内容

提示