{"id":22325,"plugin_id":"plugins_6ab0220f392881919c67600b8d04305d","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:17:13.280Z","digest":"1d59234124fe703263461028fa2cca94d2ae37e62e49d82a33ec9b869f14b8c7","against":null,"payload":{"description":"Use when a software project or workspace needs a Markdown research note grounded in high-trust primary technical sources, documentation, or API facts.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":226}],"name":"research","skill_md_contents":"---\nname: research\ndescription: Use when a software project or workspace needs a Markdown research note grounded in high-trust primary technical\n  sources, documentation, or API facts.\n---\n\nSpin up a **background agent** to do the research, so you keep working while it reads.\n\nIts job:\n\n1. Investigate the question against **primary sources** — official docs, source code, specs, first-party APIs — not a secondary write-up of them. Follow every claim back to the source that owns it.\n2. Write the findings to a single Markdown file, citing each claim's source.\n3. Save it where the repo already keeps such notes; match the existing convention, and if there is none, put it somewhere sensible and say where.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}