← 返回 Skills 市场
96
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install code-explore
功能描述
Analyze local codebase to explain directory structure, entrypoints, dependencies, call chains, and data flow without modifying code.
使用说明 (SKILL.md)
项目探索
先把代码库看清楚，再谈修改。
工作流
- 先看与需求相关的目录结构、依赖文件、配置文件和构建入口。
- 确认运行时、框架、主入口和关键启动路径。
- 只基于已经读过的文件梳理 import、export、调用链或事件流。
- 找出状态、模型、存储、外部服务和配置边界。
- 结论必须有代码依据；没读到的部分就明确写“不确定”。
- 使用本技能时不改代码，只做分析。
关注点
- 与当前问题直接相关的目录结构
- 入口文件和关键配置
- 核心模块及其职责
- 关键函数、处理器与调用关系
- 从输入到副作用或输出的数据流
输出
- 相关目录结构
- 入口与配置摘要
- 核心模块说明
- 关键函数和调用关系
- 简短的数据流说明
- 未确认项与假设
安全使用建议
This skill appears coherent and only asks the agent to read and analyze code; it does not request credentials or install software. Before enabling: (1) confirm the agent will only have read access to the target repository and not broader host files, (2) avoid running it on repos that contain secrets or credentials (remove or mask sensitive files first), and (3) review any analysis outputs before sharing them, since they could include snippets from the codebase. If you need stricter controls, run the skill against a sanitized copy of the project or restrict the agent's file access scope.
功能分析
Type: OpenClaw Skill
Name: code-explore
Version: 0.1.0
The 'code-explore' skill bundle is designed for static codebase analysis, focusing on directory structures, dependencies, and data flow. The instructions in SKILL.md explicitly restrict the agent to analysis only, forbidding code modifications or PR operations, and there are no indicators of malicious execution, data exfiltration, or prompt injection.
能力评估
Purpose & Capability
Name and description match the SKILL.md: the skill's goal is to inspect a local codebase and explain structure, entry points, dependencies, call paths, and data flow. It does not declare unrelated binaries, env vars, or install steps.
Instruction Scope
SKILL.md explicitly limits actions to reading/analyzing code and states 'do not change code.' It focuses on reading repo files (directory structure, imports/exports, call chains) and marking unknowns. It does not instruct the agent to read unrelated system files, credentials, or to transmit data externally.
Install Mechanism
This is an instruction-only skill with no install spec and no code files to execute. Nothing is written to disk or downloaded by the skill itself.
Credentials
The skill requests no environment variables, credentials, or config paths. Its requested access (read-only access to the repository files) is proportionate to its stated purpose. Note: while the skill itself doesn't request secrets, analysis of a repo that contains secrets could reveal them in outputs.
Persistence & Privilege
always is false and there are no install hooks or behavior that would modify agent/system configuration. The skill does not request permanent presence or permissions beyond runtime read access to the codebase.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install code-explore - 安装完成后，直接呼叫该 Skill 的名称或使用
/code-explore触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.0
initial release
元数据
常见问题
Code Explore 是什么？
Analyze local codebase to explain directory structure, entrypoints, dependencies, call chains, and data flow without modifying code. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 96 次。
如何安装 Code Explore？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install code-explore」即可一键安装，无需额外配置。
Code Explore 是免费的吗？
是的，Code Explore 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Code Explore 支持哪些平台？
Code Explore 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Code Explore？
由 sf0799（@sf0799）开发并维护，当前版本 v0.1.0。
推荐 Skills