docs: update review workflow skills and Gemini style guide

[apstndb]

Summary

• Improve review cycle and review respond skills based on learnings from PR feat(fuzzy-finder): statement name + argument completion framework #507 review cycles
• Add Gemini style guide rule to suppress praise-only review comments

Key Changes

• .claude/commands/review-cycle.md: Expanded from simple delegation (/project:review-respond) to a fully autonomous workflow — detect thread type, fix/explain/acknowledge, commit & push, request re-review, loop until clean
• .claude/commands/review-respond.md: Added reply content guidelines (no bare commit hashes), improved examples with explanation-first format, fixed arguments field typo
• .gemini/styleguide.md: Added "Avoid Praise-Only Comments" section — every review comment should contain actionable feedback

Context

In PR #507's review cycles, ~30% of threads were praise-only ("This is a good improvement") requiring manual resolution. This adds guidance to reduce that noise.

Test Plan

• Skills render correctly (verified via /review-cycle and /review-respond invocations)
• Gemini styleguide is valid Markdown

[gemini-code-assist]

Summary of Changes

Hello @apstndb, 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 automated review processes and guidelines to enhance the efficiency and quality of code reviews. It introduces a more robust and autonomous review cycle workflow, improves the clarity and substance of automated review responses, and establishes a new style guide rule to minimize non-actionable 'praise-only' comments, all aimed at streamlining the feedback loop based on past learnings.

Highlights

• Enhanced Review Cycle Workflow: The automated review cycle workflow in .claude/commands/review-cycle.md has been significantly expanded. It now includes detailed steps for evaluating feedback, choosing appropriate response strategies (code fix, explanation, or praise acknowledgment), committing fixes, and requesting re-reviews, with an iterative loop until all threads are resolved.
• Improved Review Respond Guidelines: The .claude/commands/review-respond.md command now incorporates comprehensive reply content guidelines, emphasizing the importance of meaningful explanations over simply posting commit hashes. Updated examples are provided for different thread types, and a typo in the arguments field was corrected.
• New Gemini Style Guide Rule: A new rule has been added to the .gemini/styleguide.md to discourage 'praise-only' review comments, aiming to ensure that all feedback provided is actionable and contributes to the review process.

Changelog

• .claude/commands/review-cycle.md
  • Expanded the review cycle workflow to include detailed steps for addressing feedback based on thread type (code fix, explanation, praise).
  • Added comprehensive reply content guidelines, emphasizing meaningful explanations over just commit hashes.
  • Implemented a loop to repeat the review process until there are no unresolved threads.
• .claude/commands/review-respond.md
  • Corrected a typo in the arguments field from [commit-message] to [commit_message].
  • Integrated detailed reply content guidelines, promoting explanation-first responses.
  • Updated examples to align with the new content guidelines for different response types.

Ignored Files

• Ignored by pattern: .gemini/** (1)
  • .gemini/styleguide.md

Activity

• The changes were informed by learnings from review cycles in PR feat(fuzzy-finder): statement name + argument completion framework #507, specifically addressing the issue of frequent praise-only comments.
• The author verified that the skills render correctly by invoking /review-cycle and /review-respond.
• The validity of the Gemini styleguide as Markdown was confirmed.

Using Gemini Code Assist

The 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 /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

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 .gemini/ folder in the base of the repository. Detailed instructions can be found here.

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

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request refines the AI-assisted review workflow by expanding the review-cycle skill and clarifying the review-respond skill. The changes provide clearer instructions and better examples for handling review feedback. However, I've identified a critical logical flaw in the new review-cycle workflow that could lead to an infinite loop. My feedback includes a suggested correction to ensure the process completes successfully.

[github-actions]

Code Metrics Report

📊 View detailed coverage report (available for 7 days)

	main (1744964)	#508 (1b50800)	+/-
Coverage	68.5%	68.5%	0.0%
Code to Test Ratio	1:1.2	1:1.2	0.0
Test Execution Time	1m6s	1m11s	+5s

Details

  |                     | main (1744964) | #508 (1b50800) | +/-  |
  |---------------------|----------------|----------------|------|
  | Coverage            |          68.5% |          68.5% | 0.0% |
  |   Files             |             55 |             55 |    0 |
  |   Lines             |           5879 |           5879 |    0 |
  |   Covered           |           4031 |           4031 |    0 |
  | Code to Test Ratio  |          1:1.2 |          1:1.2 |  0.0 |
  |   Code              |          13514 |          13514 |    0 |
  |   Test              |          16900 |          16900 |    0 |
- | Test Execution Time |           1m6s |          1m11s |  +5s |

---

Reported by octocov

[apstndb]

/gemini review

[gemini-code-assist]

Code Review

The pull request updates the review workflow and Gemini style guide documentation. The changes aim to streamline the review cycle by providing more detailed instructions for responding to feedback and introducing a guideline to avoid praise-only comments. The review-cycle.md command is expanded to a more autonomous workflow, and review-respond.md includes new reply content guidelines and an argument typo fix. The .gemini/styleguide.md now explicitly states that every review comment should contain actionable feedback. Overall, these changes improve the clarity and efficiency of the code review process.

[apstndb]

/gemini summary

[gemini-code-assist]

Summary of Changes

This pull request significantly refines the automated review processes and guidelines to enhance the efficiency and quality of code reviews. It introduces a more robust and autonomous review cycle workflow, improves the clarity and substance of automated review responses, and establishes a new style guide rule to minimize non-actionable 'praise-only' comments, all aimed at streamlining the feedback loop based on past learnings.

Highlights

• Enhanced Review Cycle Automation: The .claude/commands/review-cycle.md command was significantly expanded to provide a fully autonomous workflow for addressing review feedback, including strategies for code fixes, explanations, and praise acknowledgment, with an iterative loop until all threads are resolved.
• Improved Review Response Guidelines: The .claude/commands/review-respond.md command now includes comprehensive guidelines for crafting meaningful replies, emphasizing detailed explanations over simple commit hashes, and correcting a typo in its arguments.
• New Style Guide Rule: A rule was added to the .gemini/styleguide.md to discourage praise-only comments, ensuring all review feedback is actionable.

Changelog

• .claude/commands/review-cycle.md
  • Expanded the review cycle workflow to include detailed steps for addressing feedback based on thread type (code fix, explanation, praise).
  • Added comprehensive reply content guidelines, emphasizing meaningful explanations over just commit hashes.
  • Implemented a loop to repeat the review process until there are no unresolved threads.
• .claude/commands/review-respond.md
  • Corrected a typo in the arguments field from [commit-message] to [commit_message].
  • Integrated detailed reply content guidelines, promoting explanation-first responses.
  • Updated examples to align with the new content guidelines for different response types.
• .gemini/styleguide.md
  • Added a new section "Avoid Praise-Only Comments" to ensure all review comments contain actionable feedback.

Ignored Files

• Ignored by pattern: .gemini/** (1)
  • .gemini/styleguide.md

Activity

• Gemini Code Assist identified a logical gap in the review-cycle.md workflow regarding the explicit resolution of code-fix threads, which the author subsequently adopted.
• Gemini Code Assist provided positive feedback on the new reply content guidelines in review-respond.md, noting their alignment with reducing review noise.
• Gemini Code Assist suggested a more concise example for explanation-only responses, but the author chose to retain a longer version to better illustrate the expected level of detail.