Add: - scripts/bootstrap_skill.sh - Main script (uv sync, analyze) - scripts/skill_header.md - Operational instructions header - tests/test_bootstrap_skill.py - Pytest tests The header contains manual instructions that can't be auto-extracted: - Prerequisites (pip install) - Command reference table - Quick start examples The script prepends this header to the auto-generated SKILL.md which contains patterns, examples, and API docs from code analysis. Usage: ./scripts/bootstrap_skill.sh cp -r output/skill-seekers ~/.claude/skills/ Output: output/skill-seekers/ (directory with SKILL.md) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
45 lines
965 B
Markdown
45 lines
965 B
Markdown
---
|
|
name: skill-seekers
|
|
description: Generate LLM skills from documentation, codebases, and GitHub repositories
|
|
---
|
|
|
|
# Skill Seekers
|
|
|
|
## Prerequisites
|
|
|
|
```bash
|
|
pip install skill-seekers
|
|
# Or: uv pip install skill-seekers
|
|
```
|
|
|
|
## Commands
|
|
|
|
| Source | Command |
|
|
|--------|---------|
|
|
| Local code | `skill-seekers-codebase --directory ./path` |
|
|
| Docs URL | `skill-seekers scrape --url https://...` |
|
|
| GitHub | `skill-seekers github --repo owner/repo` |
|
|
| PDF | `skill-seekers pdf --file doc.pdf` |
|
|
|
|
## Quick Start
|
|
|
|
```bash
|
|
# Analyze local codebase
|
|
skill-seekers-codebase --directory /path/to/project --output output/my-skill/
|
|
|
|
# Package for Claude
|
|
yes | skill-seekers package output/my-skill/ --no-open
|
|
```
|
|
|
|
## Options
|
|
|
|
| Flag | Description |
|
|
|------|-------------|
|
|
| `--depth surface/deep/full` | Analysis depth |
|
|
| `--skip-patterns` | Skip pattern detection |
|
|
| `--skip-test-examples` | Skip test extraction |
|
|
| `--ai-mode none/api/local` | AI enhancement |
|
|
|
|
---
|
|
|