research: create the findings file first, update it after each source

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Matt PocockandClaude Opus 5.5 committed 2026-10-30 14:00:19 +00:00
1 parent a496f5513d
commit 00b200f95f
2 files changed
+6 -1

No files matched your search

@@ -0,0 +1,5 @@
---
"mattpocock-skills": patch
---
`research` now creates its findings file at the start and updates it after each source, so an interrupted agent leaves its partial findings on disk.
+1 -1
View File
@@ -8,5 +8,5 @@ Spin up a **background agent** to do the research, so you keep working while it
Its job:
1. 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.
2. Write the findings to a single Markdown file, citing each claim's source.
2. Write the findings to a single Markdown file, citing each claim's source. Create it in your first tool calls and update it after each source, so an interruption doesn't lose what you've found.
3. 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.