feat(self-improvement): use the self-review workflow to improve .blender/ agent instructions
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 6
- Forks
- 2
- Avg merge
- 1d 11h
- Merged PRs (30d)
- 17
Description
The self-review job of the auto-engineer workflow should generate valuable learnings & knowledge about how the CODEOWNER reviewers prefer BLEnder (and presumably other agents) to work in the code-base.
So, when create the self-review comment on an auto-engineered PR, also create an updated to the target repo's .blender/ agent instructions files, to improve future BLEnder work too. Only suggest updates to the .blender/ agent instructions files for significant improvements. Not every self-review should turn into improvements, or that will bloat and pollute the agent instructions context.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the self-review job in the auto-engineer workflow and inspect how it creates the self-review comment and accesses the target repository's .blender/ instruction files. Define what qualifies as a significant improvement, then verify that ordinary self-reviews do not alter instructions and qualifying reviews produce the intended update.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- devops, tooling
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100