📄 skillActivePromisingmedium

haiku.rag

by ggozad

Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling

Supported Platforms

🤖 Claude Code

Stars

538

Skill Type

📖 Library & API Reference

Quality Score

90/200

License

MIT

Forks

36

Last Updated

Jun 11, 2026

Discovered

Apr 17, 2026

Validation

Passed

github.com/ggozad/haiku.rag

Quality Breakdown

90/ 200

Content Signals

â—‹Gotchas/Edge Cases+40
✓Progressive Disclosure+30
â—‹Trigger Description+20
â—‹Verification/Safety+20
✓Code Examples+15
â—‹Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Repository contains Docker files and CI/CD workflows that could execute arbitrary code during builds
  • Backend application (Python FastAPI) with file upload endpoints and document processing capabilities
  • Analysis agent feature mentions 'sandboxed Python code execution' which could be a sandbox escape vector
  • Multiple third-party API integrations (OpenAI, Cohere, VoyageAI, LM Studio, vLLM) with credential configuration
  • File monitoring and auto-indexing features that automatically process directory contents
  • Docker Compose files for local deployment suggest direct system interaction