v0.3.1 — Novelty Extractor skill, google-genai migration, examples index

Skillware v0.3.1

Added

• data_engineering/novelty_extractor skill (#116, fixes #24), local semantic novelty filtering via fastembed (BAAI/bge-small-en-v1.5); multi-turn distillation via baseline_chunks; catalog page, tests, and runnable examples (novelty_extractor_demo.py, gemini_novelty_extractor.py, ollama_novelty_extractor.py).
• examples/README.md, canonical index of runnable provider scripts (#107).

Changed

• Gemini SDK migration, moved from deprecated google-generativeai to google-genai (#97); usage docs and snippets updated (#92).
• Documentation, README navigation and skill catalog discoverability (#98); runnable examples cross-linked on skill catalog pages (#121); agent_loops.md matrix synced with the examples index (#122).

Notes

• novelty_extractor requires pip install fastembed numpy (manifest deps; not bundled in base install).
• First run downloads the embedding model (~50 MB) to local cache.
• Tag v0.3.1 when ready, version bump is on main at 60021d9.

Contributors

Thanks to everyone who shipped between v0.2.9 and v0.3.1:

• @rizzoMartin — data_engineering/novelty_extractor (#116)
• @CleanDev-Fix — examples index (#107)
• @narutamaaurum — skill catalog runnable examples (#121)
• @choucaleb602-commits — examples index follow-up (#122)
• @kunal-9090 — Gemini docs snippets (#92)
• @rosspeili — google-genai migration (#97), README navigation (#98)