[skills,docs] docs: add KeepGPU repository workflow skill#65
[skills,docs] docs: add KeepGPU repository workflow skill#65Wangmerlyn merged 7 commits intomainfrom
Conversation
Summary of ChangesHello, 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 significantly enhances the development workflow for the KeepGPU repository by integrating a new skill designed to guide LLM agents. This skill provides structured instructions for implementing, testing, and documenting changes, ensuring consistency and adherence to architectural principles. The changes also include validation reports and a visible badge, promoting confidence in the quality and reliability of the automated guidance. 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. Changelog
Activity
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
|
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (3)
📝 WalkthroughWalkthroughAdds KeepGPU workflow documentation and metadata: a new Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
Poem
🚥 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)
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 introduces a new skill for the KeepGPU repository workflow, enhancing the project's documentation and providing clear guidelines for contributors. The changes include a new SKILL.md file outlining the workflow, a skillcheck-free-report.md detailing its validation, and an openai.yaml agent configuration. The additions are well-structured and contribute positively to the project's maintainability and clarity for future development.
| - Description includes activation triggers (8.3) | ||
| - Description includes negative triggers (8.7) | ||
| - Skill specifies output format with examples (8.4) | ||
| - Skill includes example section (8.1) | ||
| - Skill documents error handling or limitations (8.2) | ||
| - Skill uses structured instructions (8.5) | ||
| - Skill documents prerequisites (8.6) |
There was a problem hiding this comment.
The "Strengths detected" section lists rule numbers (e.g., 8.3) without a brief explanation of what each rule signifies. To make this report more self-contained and immediately understandable for readers who may not have direct access to or familiarity with the skill-check/SKILL.md document, consider adding a concise description for each strength. This would improve the clarity and overall usefulness of the report as a standalone document.
| Preferred targeted test commands: | ||
|
|
||
| ```bash | ||
| pytest tests/cuda_controller tests/global_controller tests/utilities/test_platform_manager.py | ||
| pytest tests -k threshold | ||
| pytest tests/mcp tests/utilities/test_gpu_info.py |
There was a problem hiding this comment.
In the "Preferred targeted test commands" section, the pytest commands are listed sequentially within a single bash code block. If these commands are intended to be run as alternatives or distinct steps, presenting them as a markdown bulleted list, with each command in its own inline code block, would enhance clarity and make it easier for users to understand and execute them individually. For example:
pytest tests/cuda_controller tests/global_controller tests/utilities/test_platform_manager.pypytest tests -k thresholdpytest tests/mcp tests/utilities/test_gpu_info.py
| Preferred targeted test commands: | |
| ```bash | |
| pytest tests/cuda_controller tests/global_controller tests/utilities/test_platform_manager.py | |
| pytest tests -k threshold | |
| pytest tests/mcp tests/utilities/test_gpu_info.py | |
| - `pytest tests/cuda_controller tests/global_controller tests/utilities/test_platform_manager.py` | |
| - `pytest tests -k threshold` | |
| - `pytest tests/mcp tests/utilities/test_gpu_info.py` |
|
@coderabbitai review |
✅ Actions performedReview triggered.
|
|
@coderabbitai review\n/gemini review |
|
Acknowledged! I'm performing a review of the pull request in its current state. I will post my feedback shortly. |
|
✅ Actions performedReview triggered.
|
1 participant
Summary
skills/keepgpu-repo-workflowskill that guides LLM agents on KeepGPU architecture boundaries, interface parity, and validation workflowagents/openai.yamlmetadata and a SkillCheck Free validation report underdocs/skills/keepgpu-repo-workflow/README.mdValidation
Summary by CodeRabbit