docs(claude): Improve agent-memory skill guidelines#1068
Conversation
|
Important Review skippedAuto incremental reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the Note Other AI code review bot(s) detectedCodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review. 📝 WalkthroughWalkthroughExpanded documentation for the agent-memory skill to include status tracking in frontmatter (in-progress, resolved, blocked, abandoned) and introduced a new Content Reference section with guidelines for writing self-contained, structured memory notes with context, state, details, and next steps. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes Possibly related PRs
Pre-merge checks and finishing touches✅ Passed checks (3 passed)
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 |
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 refines the 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
|
![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 significantly improves the guidelines for the agent-memory skill by making them more practical for resuming work across conversations. The introduction of a status field, clearer instructions on writing self-contained notes, and a new content reference checklist are all valuable additions. My review includes a couple of suggestions to enhance the consistency and completeness of the documentation related to the new status field. Overall, these are great improvements to the skill's documentation.
.claude/skills/agent-memory/SKILL.md
Outdated
| Organize memories when needed: | ||
| - Consolidate scattered memories on the same topic | ||
| - Remove outdated or superseded information | ||
| - Update status field when work completes or gets blocked |
There was a problem hiding this comment.
To make this guideline more complete, consider also mentioning the abandoned state, which is another possible final state for a task besides resolved (completes) and blocked.
| - Update status field when work completes or gets blocked | |
| - Update status field when work completes, gets blocked, or is abandoned |
|
|
||
| When writing detailed memories, consider including: | ||
| - **Context**: Goal, background, constraints | ||
| - **State**: What's done, in progress, or blocked |
There was a problem hiding this comment.
The states mentioned here (done, in progress, blocked) are slightly different from the values defined for the status frontmatter field (in-progress, resolved, blocked, abandoned). To improve consistency and avoid potential confusion, it would be better to use the same terminology and values. This also adds the missing abandoned state.
| - **State**: What's done, in progress, or blocked | |
| - **State**: Current status of the work (e.g., `in-progress`, `resolved`, `blocked`, `abandoned`) |
Deploying repomix with
|
| Latest commit: |
5039ccf
|
| Status: | ⚡️ Build in progress... |
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #1068 +/- ##
=======================================
Coverage 87.19% 87.19%
=======================================
Files 116 116
Lines 4350 4350
Branches 1011 1011
=======================================
Hits 3793 3793
Misses 557 557 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
.claude/skills/agent-memory/SKILL.md (1)
143-151: Consider adding a brief example to the Content Reference section.While the current guidance is clear and the disclaimer ("not all memories need all sections") appropriately keeps the approach flexible, a short, concrete example showing how one of these sections might be applied could help readers understand the intent—especially for the
StateandNext stepsfields, which are most useful for in-progress work.This is optional and could be added as a follow-up if user feedback suggests it would be helpful.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
.claude/skills/agent-memory/SKILL.md
🧰 Additional context used
🧠 Learnings (1)
📓 Common learnings
Learnt from: CR
Repo: yamadashy/repomix PR: 0
File: .cursorrules:0-0
Timestamp: 2025-06-30T16:07:18.316Z
Learning: Applies to .agents/rules/base.md : Check the rules written in `.agents/rules/base.md` as they contain important project-specific guidelines and instructions.
⏰ 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). (14)
- GitHub Check: Build and run (macos-latest, 25.x)
- GitHub Check: Build and run (windows-latest, 22.x)
- GitHub Check: Test (ubuntu-latest, 24.x)
- GitHub Check: Test (windows-latest, 22.x)
- GitHub Check: Test (windows-latest, 20.x)
- GitHub Check: Build and run (windows-latest, 24.x)
- GitHub Check: Test (ubuntu-latest, 22.x)
- GitHub Check: Test (windows-latest, 24.x)
- GitHub Check: Build and run (windows-latest, 25.x)
- GitHub Check: Build and run (windows-latest, 20.x)
- GitHub Check: Test (windows-latest, 25.x)
- GitHub Check: Test with Bun (windows-latest, latest)
- GitHub Check: claude-review
- GitHub Check: Cloudflare Pages
🔇 Additional comments (1)
.claude/skills/agent-memory/SKILL.md (1)
1-151: Documentation improvements are well-structured and achieve the stated objectives.The updates effectively support resuming work from fresh conversations by introducing the
statusfield and expanding the Content Reference section. The phrasing change from "Write for your future self" to "Write self-contained notes" (line 138) is more explicit about including full context, and the optional nature of both the status field and Content Reference sections is clearly communicated (line 70, line 151).The additions to Proactive Usage (lines 19, 24, 29) naturally extend the guidance to cover in-progress work and resumption workflows without adding unnecessary complexity.
PR Review: docs(claude): Improve agent-memory skill guidelinesSummaryThis documentation PR enhances the agent-memory skill to better support resuming work from fresh conversations. The changes are well-structured and thoughtful. EvaluationCode Quality & Best Practices: ✅ Excellent
Changes Analysis:
Potential ImprovementsMinor Suggestions (Optional)
Premortem Analysis
VerdictLGTM ✅ This is a well-crafted documentation improvement. The changes enhance usability for AI agents resuming work across conversations while maintaining simplicity. The optional nature of new features (status field, Content Reference) ensures backward compatibility. No issues found. Ready to merge. Reviewed by Claude |
Enhance agent-memory skill to better support resuming work from scratch: - Change "Write for your future self" to "Write self-contained notes" to emphasize including full context for zero-prior-knowledge readers - Add status field to frontmatter (in-progress/resolved/blocked/abandoned) for tracking work state - Add Content Reference section with checklist for detailed memories - Update Proactive Usage to include in-progress work and conversation breaks
yamadashy
force-pushed
the
docs/improve-agent-memory-skill-guidelines
branch
from
b3aced8 to
5039ccf
Compare
PR Review: docs(claude): Improve agent-memory skill guidelinesOverviewThis is a well-crafted documentation-only PR that enhances the agent-memory skill to better support resuming work from fresh conversations. I've reviewed the changes and found them to be thoughtful and well-structured. Changes Review
Quality Assessment
Premortem Analysis
Minor Observations (Non-blocking)
VerdictLGTM ✅ This documentation improvement is ready to merge. The changes effectively support the stated goal of better resuming work from fresh conversations while maintaining simplicity and backward compatibility. Reviewed by Claude |
1 participant
Enhance agent-memory skill to better support resuming work from a fresh conversation.
Changes
statusfield (in-progress/resolved/blocked/abandoned) for tracking work stateDesign Intent
Checklist
npm run test(N/A - documentation only)npm run lint(N/A - documentation only)