docs(skills): improve agent-memory skill guidelines#1087
Conversation
Add guidance that summaries are the decision point for agents scanning memories. Since agents use `rg "^summary:"` to list all summaries before deciding which to read in full, the summary needs to contain enough context for that decision.
Add "Write for resumption" as the first guideline to emphasize that memories should capture all key points needed to continue work later without losing context.
Summary of ChangesHello @yamadashy, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request enhances the documentation for the agent-memory skill by providing clearer and more effective guidelines for writing memories. The primary goal is to improve how agents interact with and utilize these memories, ensuring they can make informed decisions based on summaries and efficiently resume tasks by having all necessary context readily available. Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
📝 WalkthroughWalkthroughUpdates documentation in Claude's agent memory skill file to clarify that summaries serve as decision points for memory retrieval, introduces a new guideline about writing for resumption, and reorganizes the guidelines list accordingly. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~5 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches🧪 Generate unit tests (beta)
📜 Recent review detailsConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro 📒 Files selected for processing (1)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (11)
🔇 Additional comments (2)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request improves the agent-memory skill documentation by clarifying the purpose of the summary field and adding a new guideline about writing for resumption. The changes are clear and valuable. I've added one suggestion to improve the formatting of a shell command in the documentation for better readability.
Deploying repomix with
|
| Latest commit: |
ebea28f
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://93b3f1f9.repomix.pages.dev |
| Branch Preview URL: | https://docs-improve-agent-memory-su.repomix.pages.dev |
PR Review SummaryOverall Assessment: ✅ LGTM This is a clean documentation-only PR that improves the agent-memory skill guidelines. The changes are well-thought-out and add practical value. What Changed
Code QualityThe markdown is well-formatted and follows the existing style. The additions integrate seamlessly with the current documentation structure. Review of ChangesDetailsSummary field clarification (line 56)
"Write for resumption" guideline (line 140)
Minor Suggestions (Optional)None - the changes are clear and well-documented. Premortem AnalysisPotential Risks & Mitigations
No deployment risks since this is documentation-only. Checklist
🤖 Reviewed by Claude |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #1087 +/- ##
=======================================
Coverage 87.16% 87.16%
=======================================
Files 116 116
Lines 4379 4379
Branches 1019 1019
=======================================
Hits 3817 3817
Misses 562 562 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
1 participant
Improve the agent-memory skill documentation with clearer guidance on how to write effective memories.
Changes
Clarify summary field purpose: Added explanation that summaries are the decision point for agents scanning memories via
rg "^summary:". This helps agents understand they need to include enough context in summaries for the decision of whether to read the full content.Add resumption guideline: Added "Write for resumption" as the first guideline to emphasize that memories exist to resume work later and should capture all key points needed to continue without losing context.
Checklist
npm run test- N/A (docs only)npm run lint- N/A (docs only)