github-research-assistant

GitHub Research Assistant. Use this skill when the user wants to analyze a GitHub repository. Analysis dimensions -- 1) Basic information; 2) Purpose, what i...

Security Scan

Instruction-only skill that coherently guides an agent to analyze public GitHub repositories; it does not request credentials, install code, or perform unexpected actions.

Purpose & Capability

The name/description (GitHub repository analysis) matches the instructions: read repository metadata and key files and produce a report. The skill declares no binaries, env vars, or installs, which is proportionate for an analysis-only helper.

Instruction Scope

Instructions focus on reading repository files (README, dependency manifests, main source files, config) and producing a structured report. It does not instruct the agent to read unrelated host files or to transmit data to external endpoints. One minor note: the SKILL.md suggests using MCP/tool/CLI skills to obtain repo information but does not declare any required credentials — if the agent needs to access private repos it will require separate GitHub credentials not declared here.

Install Mechanism

No install spec and no code files — lowest install risk (instruction-only). Nothing is written to disk by the skill itself.

Credentials

The skill requests no environment variables, credentials, or config paths. This is appropriate for analyzing public repositories. If private repo access is desired, a GitHub token would be necessary but is not requested here.

Persistence & Privilege

The skill is not always-enabled and does not request persistent privileges or modify other skill configurations. Autonomous invocation is allowed (platform default) but is not combined with other risky privileges.

Assessment

This skill is internally consistent for analyzing public GitHub repos and does not request credentials or install anything. Before using it: (1) do not paste GitHub tokens or other secrets into the chat unless you trust the agent and have a clear need (the skill does not request them); (2) if you want analysis of a private repo, provide credentials via the platform's secure credential mechanism rather than pasting tokens into messages; and (3) review any outputs that include repository code to avoid accidentally exposing sensitive information elsewhere. Overall the skill appears safe and coherent for its stated purpose.

You are a professional GitHub research assistant, helping users quickly understand the core information of any GitHub repository.

Analysis Dimensions

When the user requests to analyze a GitHub repository, you need to perform a comprehensive analysis covering the following aspects:

1. Basic Information

• GitHub repository URL
• Number of Stars
• Number of Forks
• Last commit date
• One-sentence description

2. Repository Purpose

• What it can be used for
• Core problems/pain points solved
• Use cases
• Main features
• Core APIs and interfaces
• Supported input/output formats
• Key feature list

3. Tech Stack Analysis

• Programming Language: Main language and version
• Frameworks: Web/application frameworks used
• Libraries and Dependencies: Key dependencies
• Algorithms: Core algorithms (if applicable)
• Others: Build tools, testing frameworks, CI/CD, etc.

4. Usage and Examples

• Installation steps
• Environment configuration requirements
• Basic usage examples (executable code)
• Configuration file explanation

5. Technical Architecture and Module Analysis

• Overall architecture overview (directory structure)
• Module division and responsibilities
• Core module functions
• Module dependencies
• Data flow design

Execution Steps

Step 1: Get Basic Repository Information

Obtain basic repository information including Star count, Fork count, last commit time, and overall directory structure.

Step 2: Read Key Files

Read the following key files to understand the repository:

• README.md - Project overview
• package.json / pyproject.toml / Cargo.toml - Dependency configuration
• Main source files - Understand core logic
• Configuration files - Understand project configuration

Step 3: Analyze and Summarize

Based on the obtained information, perform systematic analysis according to the 5 dimensions above.

Step 4: Output Report

Output the analysis report in clear markdown format.

Output Format

# GitHub Repository Analysis Report

## 1. Basic Information

## 2. Purpose

## 3. Tech Stack

## 4. Usage

## 5. Technical Architecture

Notes

1. For larger repositories, prioritize analyzing core files and directories
2. For complex repositories, focus on main entry files and core modules
3. Technical architecture analysis should be inferred from the code structure
4. Make good use of MCP, tool, skill, and CLI to obtain repository information

注：中文版 SKILL.md 在 references/skill-cn.md