GitHub Skill Forge

Core Features

1. Automated Scaffolding

• One-click GitHub repository cloning
• Automatically creates standard skill directory structure
• Automatically generates context aggregation files

2. Lite-RAG Context Aggregation

• Automatically extracts project file tree structure
• Automatically parses README and documentation
• Automatically collects dependency information (requirements.txt, package.json, pyproject.toml)
• Generates a single context file for quick Agent understanding

3. Intelligent Error Handling

• Automatic proxy mode switching
• Directory existence detection
• Automatic retry on Git clone failure

4. Standardized Output

• Automatically generates compliant skill structure
• Unified directory layout (scripts/, references/, context_bundle.md)
• Pre-configured SKILL.md template

Quick Start

Installation Requirements

# Basic dependencies
Python 3.7+
Git

Basic Usage

# Syntax: python scripts/forge.py <URL> [SKILL_NAME]
python3 .trae/skills/github-skill-forge/scripts/forge.py "https://github.com/username/repo"

Use Cases

• When you want to use a tool found on GitHub
• When a user sends a GitHub link and says "I want to use this"
• When you need to "install" new features into the

  .trae/skills

  library
• When you need to quickly integrate open-source tools into workflows
• When you need to standardize team tool usage specifications

Workflow

Step 1: Forge Framework

# Basic usage
python3 .trae/skills/github-skill-forge/scripts/forge.py "https://github.com/username/repo"

# Specify skill name
python3 .trae/skills/github-skill-forge/scripts/forge.py "https://github.com/username/repo" "my-custom-skill"

Step 2: Analysis and Finalization (AI Task)

context_bundle.md

1. Read Context Bundle: View

   context_bundle.md

   • This file contains the file tree, README, and dependencies
   • No need to manually search for files
   • It is recommended to limit reading to the first 500 lines
2. Update SKILL.md: Rewrite the draft in the new skill directory
   • Description: Summarize the tool's functionality
   • Prerequisites: List installation commands (e.g.,

     pip install -r src/requirements.txt

     )
   • Usage: Provide clear examples of running the tool using

     src/...

3. Create Wrapper Scripts (Optional):
   • If the tool requires complex parameters, write simplified Python/Shell scripts in

     .trae/skills/<new_skill>/scripts/

Step 3: Verification

python3 .trae/skills/<new_skill>/src/<main_script>.py --help

Usage Examples

Example 1: Basic Usage

1. Run the forge script

   python3 .trae/skills/github-skill-forge/scripts/forge.py https://github.com/sqlmapproject/sqlmap

2. Agent reads the context bundle

   read .trae/skills/sqlmap/context_bundle.md

3. Agent edits SKILL.md

   edit .trae/skills/sqlmap/SKILL.md

4. Agent runs verification

   python3 .trae/skills/sqlmap/src/sqlmap.py --help

Example 2: Specify Skill Name

python3 .trae/skills/github-skill-forge/scripts/forge.py "https://github.com/requests/requests" "http-requests-lib"

http-requests-lib

Example 3: Complex Project

1. Run the forge script
2. Read

   context_bundle.md

   to understand seaborn's API
3. Identify dependencies (numpy, pandas, matplotlib)
4. Write simplified usage scripts to the

   scripts/

   directory
5. Update SKILL.md with usage examples

Example 4: CLI Tool Installation

1. Run the forge script
2. Analyze fzf's functionality:
   • Read context_bundle.md to understand core features
   • Identify dependencies (Go environment)
   • Understand installation methods (multi-platform support)
3. Create simplified usage scripts:

   • scripts/fuzzy-search.py

     - Simplified file search

   • scripts/history-search.py

     - Command history search
4. Update SKILL.md:
   markdown

   ## Usage
   
   ### Basic File Search
   ```bash
   python3 scripts/fuzzy-search.py

   Command History Search

   bash

   python3 scripts/history-search.py

   Dependencies

   • Go 1.22+ (compile from source)
   • Or use precompiled binaries

   Installation Commands

   bash

   # macOS
   brew install fzf
   
   # Linux
   sudo apt install fzf
   
   # Windows
   choco install fzf

   undefined

Example 5: Data Processing Tool

1. Run the forge script
2. Read context_bundle.md
3. Create simplified wrapper scripts:

   • scripts/json-format.py

     - JSON formatting

   • scripts/json-query.py

     - JSON query tool
4. Update SKILL.md:
   markdown

   ## Usage Examples
   
   ### Format JSON
   ```bash
   cat data.json | python3 scripts/json-format.py

   Query JSON Path

   bash

   python3 scripts/json-query.py "data.json" ".users[0].name"

   undefined

Advanced Usage

Manually Create Context Bundle

from forge import create_context_bundle
create_context_bundle("./src", "./context_bundle.md")

Custom File Tree Limits

limit

forge.py

def get_file_tree(start_path, limit=100):  # Increase limit to 100 files
    ...

Batch Install Multiple Skills

# Create a batch installation script
for url in "https://github.com/fzf" "https://github.com/jqlang/jq" "https://github.com/sharkdp/bat"; do
    python3 .trae/skills/github-skill-forge/scripts/forge.py "$url"
done

Custom Templates

# Custom default skill name
export SKILL_FORCE_NAME="custom-skill"

# Custom file limit
export SKILL_FILE_LIMIT=100

# Custom document truncation size
export SKILL_DOC_TRUNCATE=20000

Troubleshooting

Issue 1: Clone Failure

❌ Git clone failed: fatal: Could not read from remote repository.

1. Check if the URL is correct
2. Ensure network connectivity is normal
3. Try using proxy mode (handled automatically by the script)
4. Verify Git authentication (if required)
   bash

   git config --global credential.helper store

Issue 2: Directory Already Exists

⚠️  Warning: Skill directory 'xxx' already exists.
❌ Aborting: Directory exists.

1. Use a different skill name
   bash

   python3 forge.py <URL> new_skill_name

2. Or manually delete the existing directory and retry
   bash

   rm -rf .trae/skills/xxx

Issue 3: Missing Dependencies

ModuleNotFoundError: No module named 'xxx'

1. Clearly list dependencies in SKILL.md
2. Provide installation commands
3. Create requirements.txt (if not present in the original project)
4. Check Python version compatibility

Issue 4: Oversized Context Bundle

context_bundle.md

Issue 5: Permission Error

Permission denied: '.trae/skills/xxx'

1. Check directory permissions
   bash

   ls -la .trae/skills/

2. Fix permissions
   bash

   chmod -R 755 .trae/skills/

Issue 6: Git LFS Files

Git LFS: (1 of 1 files) 0 B / 100.00 MB

1. Install Git LFS
   bash

   git lfs install

2. Manually pull LFS files
   bash

   git lfs pull

Best Practices

1. Skill Naming Conventions

• Use lowercase letters and hyphens
• Keep length between 3-50 characters
• Avoid reserved words

2. SKILL.md Writing Guidelines

• Keep it concise, only include necessary information
• Place detailed content in

  context_bundle.md

• Use Chinese titles and English commands
• Provide executable example code

3. Wrapper Script Creation

• Simplify complex command-line interfaces
• Provide default parameters
• Add error handling
• Support

  -h/--help

  parameters

4. Dependency Management

• Clearly list all dependencies
• Specify version ranges
• Provide multi-platform installation methods

5. Verification Testing

• Run all examples before release
• Test on different operating systems
• Verify dependency installation correctness

Skill Structure Specifications

Standard Directory Structure

.trae/skills/
└── <skill-name>/
    ├── SKILL.md           # Skill documentation
    ├── context_bundle.md  # Context aggregation (auto-generated)
    ├── requirements.txt   # Dependencies (optional)
    ├── src/              # Source code
    │   └── <main-script>
    ├── scripts/          # Wrapper scripts (optional)
    │   └── <helper-scripts>
    └── references/       # Reference documents (optional)
        └── <documentation>

SKILL.md Template

---
name: <skill-name>
description: <brief description>
---

# <Skill Name>

## Features
- <Feature 1>
- <Feature 2>

## Requirements
- <Dependency 1>
- <Dependency 2>

## Installation
```bash
<installation command>

Usage

Basic Usage

<basic command>

Advanced Usage

<Advanced Feature>

<advanced command>

Troubleshooting

Issue

Changelog

• <Version>: <Update Content>

## Performance Optimization

### 1. Reduce Clone Depth
```bash
# Use shallow clone
git clone --depth 1 <url>

2. Skip Unnecessary Files

# Add in forge.py
SKIP_DIRS = ['.git', '.github', 'docs', 'test']
SKIP_FILES = ['*.md', '*.txt']

3. Parallel Processing

# Use multi-threading for multiple tasks
import concurrent.futures

with concurrent.futures.ThreadPoolExecutor() as executor:
    executor.submit(process_file, file1)
    executor.submit(process_file, file2)

Security Considerations

1. Verify Repository Source

• Check the number of stars and forks of the repository
• View recent commit records
• Check maintainer activity

2. Dependency Security

• Check for known vulnerabilities
• Use dependency scanning tools
• Update dependencies regularly

3. Code Execution Security

• Test in an isolated environment
• Restrict file system access
• Log all operations

Integration Recommendations

1. CI/CD Integration

# .github/workflows/skill-test.yml
name: Test Skills
on: [push]
jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - name: Install dependencies
        run: pip install -r requirements.txt
      - name: Test skill
        run: python3 src/main.py --help

2. Automated Updates

# Regularly update skill scripts
0 0 * * 0 cd /path/to/skills && python3 github-skill-forge/scripts/forge.py <url>

Related Resources

• fzf - Command-line Fuzzy Finder
• awesome-cli-apps - Curated CLI Applications
• GitHub CLI Official Documentation

Notes

• The script will delete the

  .git

  folder in the cloned repository to reduce size
• Proxy mode uses gitclone.com as the proxy service
• It is recommended to confirm the correctness of the URL before running
• Large repositories may take longer to clone
• It is recommended to update github-skill-forge itself regularly
• Test before using in a production environment