New open skill turns folders of PDFs into clean Markdown with an agent swarm
doodlestein · x · 2026-09-09
A new skill converts huge folders of PDFs (mixed digital and scanned, e.g. legal docs) into accurate, well-formatted GitHub-Flavored Markdown economically: it extracts text mechanically when possible and falls back to OCR only if needed, orchestrates a swarm of agents via the author's ntm tool, prefers Gemini 3.8 Flash with Antigravity (falling back to Codex with Terra/Luna workers), and ships validation scripts to catch errors. Open-sourced for high-quality output without wasting tokens.
More from coding & agent
- Meta details Muse agent safety: sandboxed harness, Sentinel gatekeeper, user-held encryption — unixterminal · 2026-09-09
- SREGym benchmark launches: GPT-5.6 leads agents at fixing real production SRE failures — tianyin_xu · 2026-09-09
- Waqi: an MCP proxy that redacts PII from tool responses before the model sees them — AggressiveAnxiety481 · 2026-09-09
- Local academic literature pipeline makes fabricated citations structurally impossible — Waste_Public_2985 · 2026-09-09
- OpenAI Solved a Millennium Prize Problem — So Why Is Software Still Buggy? — ziv_ravid · 2026-09-09
- OpenContext gives coding agents persistent memory across repos, already at 757 GitHub stars — tom_doerr · 2026-09-09