← 返回 Skills 市场
g30tr1x

Project Analyzer

作者 Gavriel Donovan · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
80
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install pal
功能描述
Analyze any project directory and produce a detailed report covering what the project does, its tech stack, folder structure, entry points, how to run it, an...
使用说明 (SKILL.md)

Project Scout

Use this skill whenever the user wants to understand, explore, or get oriented inside a codebase or project folder. Trigger phrases include:

  • "analyze this project"
  • "what does this project do"
  • "I'm new to this codebase, where do I start"
  • "give me an overview of [directory]"
  • "explain the structure of my project"
  • "scan the project"
  • "project report"
  • /scout (slash command)

What you must do

When this skill is triggered:

  1. Identify the target directory. Use the path the user mentions. If none is given, use the current working directory (run pwd to confirm it).

  2. Run the scout script using the exec tool:

python3 {baseDir}/scout.py --path \x3CDIRECTORY>

Replace \x3CDIRECTORY> with the resolved absolute path. Always use --path explicitly.

  1. Present the output as a clean, readable message to the user. Structure it with clear sections. Do not just dump raw text — format it nicely for the chat channel being used.

  2. Offer next steps. After presenting the report, ask if the user wants to:

    • Dive deeper into any specific file or module
    • Get a dependency graph
    • Find the entry point and trace the execution flow
    • Generate a CLAUDE.md / README for the project

Handling errors

  • If python3 is not found: tell the user to install Python 3 and point them to https://www.python.org/downloads/
  • If the path doesn't exist: ask the user to double-check the path and try again
  • If the directory is empty or has very few files: report what was found and note it may be a new/empty project
  • If the output is very long: summarize the key sections and offer to elaborate on any part

Slash command

This skill is available as /scout [path]. Examples:

  • /scout — analyzes current working directory
  • /scout ~/projects/my-app — analyzes a specific path
  • /scout . — explicit current directory

Output format

Structure your reply like this:

🔍 **Project Scout Report**
📁 *\x3Cproject name> — \x3Cone-line summary>*

**What it does**
\x3Cplain English explanation>

**Tech stack**
\x3Clanguages, frameworks, key libraries>

**Structure**
\x3Cbrief tour of the important folders and files>

**Where to start**
\x3Cthe 2-3 files a new dev should read first>

**How to run it**
\x3Cinstall/build/run commands if found>

**Notes**
\x3Canything unusual, TODOs, missing docs, etc.>

Keep it conversational and useful. This is meant to orient a developer, not just dump data.

安全使用建议
This skill looks coherent and purpose-aligned. Before installing or running it, choose a specific project directory and avoid folders containing secrets, credentials, or unrelated private files; review the generated report before sharing it elsewhere.
功能分析
Type: OpenClaw Skill Name: pal Version: 1.0.0 The skill bundle is a legitimate project analysis tool designed to provide an overview of a codebase. The core logic in 'scout.py' performs read-only filesystem operations to identify tech stacks, directory structures, and entry points without any network activity or data exfiltration. The 'SKILL.md' instructions are well-defined and align with the stated purpose of assisting a developer with project orientation.
能力评估
Purpose & Capability
The stated purpose and visible behavior are coherent: the skill analyzes a project directory and produces an orientation report. That purpose necessarily involves reading local project files.
Instruction Scope
The skill is user-triggered and explicitly passes a target path, but if no path is provided it defaults to the current working directory, which could analyze more than the user intended.
Install Mechanism
The install requirements are limited to Python 3, with no hidden package installs, remote scripts, or unexpected dependencies evidenced.
Credentials
Reading local project structure, configs, and source samples is proportionate for a project analyzer, but users should avoid running it on directories containing secrets or unrelated private material.
Persistence & Privilege
No credentials, persistent storage, background execution, network exfiltration, or elevated privileges are evidenced in the supplied artifacts.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install pal
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /pal 触发
  4. 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
v1.0.0
Initial skill release. Major simplification and refocus: - Replaces complex SDD document generator with a streamlined project analysis tool. - Single script (scout.py) now generates comprehensive project overviews. - Obsolete files, templates, and configuration removed (20 files deleted). - New simple interface: `/scout [path]` slash command or direct query support. - Output now directly answers "what is this project, how does it work, and where do I start".
元数据
Slug pal
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Project Analyzer 是什么?

Analyze any project directory and produce a detailed report covering what the project does, its tech stack, folder structure, entry points, how to run it, an... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 80 次。

如何安装 Project Analyzer?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install pal」即可一键安装,无需额外配置。

Project Analyzer 是免费的吗?

是的,Project Analyzer 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Project Analyzer 支持哪些平台?

Project Analyzer 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 Project Analyzer?

由 Gavriel Donovan(@g30tr1x)开发并维护,当前版本 v1.0.0。

💬 留言讨论