Token导航 LogoToken导航TokenDH.com
研究检索只读clawhub未标认证来源可访问clear审计通过

code-doc-guid代码文档指南

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

9,072

周安装

367

GitHub Stars

公开资料未说明

下载量

2,848
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:code-doc-guid(代码文档指南)
来源仓库:https://github.com/omeletee/code-doc-guid
安装命令:
openclaw skills install code-doc-guid
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install code-doc-guid

简介

code-doc-guid 辅助代码库导航与文档一致性维护。

  • 帮助定位代码定义与理解依赖关系。
  • 通过 clawhub 安装,安装命令为 openclaw skills install code-doc-guid。
  • 使用前需确认权限范围、维护状态及是否涉及联网、命令执行或文件读写操作。
  • 适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

SKILL.md

name
code-doc-guid
description
Codebase navigation and documentation assistant. Helps AI locate code definitions, understand dependencies, and maintain documentation consistency. BLOCKING REQUIREMENT: Use this skill BEFORE any file modification/move/delete operation to check dependencies, and AFTER modifications to update the index.

Code Documentation & Navigation Guide

This skill provides a Codebase Knowledge Graph to help you navigate complex projects without reading thousands of files. It uses a local SQLite database to store file relationships, dependency layers, and symbol definitions.

⚠️ CRITICAL: BLOCKING REQUIREMENTS (触发条件)

STOP! READ THIS BEFORE PROCEEDING.

You MUST invoke this skill (code-doc-guid) as a BLOCKING STEP before performing any of the following actions. Failure to do so is a violation of protocol.

🔴 Mandatory Pre-Action Check (Recon Phase)

Trigger: You are about to:

  • Modify any code file (Write, SearchReplace).
  • Rename or move files (RunCommand: mv/ren).
  • Delete files (DeleteFile).
  • Refactor a class, function, or variable.

Action: You MUST run python ... codebase_manager.py inspect/search FIRST. Reason: You cannot safely modify code without knowing who depends on it. "Guessing" is strictly prohibited.

🟢 Mandatory Post-Action Sync (Archive Phase)

Trigger: You have just finished a set of file modifications. Action: You MUST run python ... codebase_manager.py update. Reason: The knowledge graph must remain consistent with the disk state for the next turn.


Workflow & Commands

All commands are run via python scripts/codebase_manager.py <command> [args]. *(Note: If running manually, adjust the path to where you saved the script)*

1. search - Find Symbols & Concepts

Use this to locate code by name or intent (docstring).

  • Command: search <query>
  • Example: search "UserAuth"
  • Output: JSONL format containing file paths, symbol names, and docstrings.
  • Action: Use this to find the *exact file path* before reading it.

2. inspect - Analyze Dependencies & Risk

Use this to understand the impact of a change.

  • Command: inspect <filename_fragment>
  • Example: inspect "auth_service"
  • Output (JSON):

* risk_score: HIGH / MEDIUM / LOW. * doc_file: Path to the detailed report (e.g., .trae/codeguiddoc.md).

  • Action Guidelines:

1. Read the JSON summary first. 2. IF RISK IS HIGH: * STOP. Do not modify code yet. * READ the generated markdown file (doc_file). It contains a Mermaid Graph and full dependency list. * SHOW the Mermaid graph to the user (if possible) or summarize the impact: "This change affects 25 files, including core modules A and B." * ASK for confirmation.

3. update - Refresh Index

Use this after ANY file modification.

  • Command: update
  • Output: "Processing X changed files..."
  • Note: It is incremental and very fast (<1s usually). Always run this before finishing your turn.

4. graph - Export Visuals (Optional)

Use this only when the user explicitly asks for an architecture overview.

  • Command: graph
  • Output: Generates .trae/architecture_layers.md (Human readable) and .trae/dependency_graph.json (Machine readable).

Token Economy Strategy

To save tokens and time:

  1. Don't read whole files to find one function. Use search -> Read(limit=20, offset=N).
  2. Don't guess dependencies. Use inspect to see the exact relationship graph.
  3. Trust the Layering. If you are modifying a Layer 0 file, be extremely careful—it breaks everything. If modifying Layer 5, it's likely safe.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

80.98%
按下载量换算2,306

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills