Add "review" claude skill and use it in "gitbhub-pr-review" (#172797)

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Abílio Costa
2026-06-03 15:57:21 +01:00
committed by GitHub
parent 593ae9eb80
commit 4593059db2
2 changed files with 40 additions and 33 deletions
+2 -33
View File
@@ -8,39 +8,8 @@ description: Reviews GitHub pull requests and provides feedback comments. This i
## Follow these steps:
1. Use 'gh pr view' to get the PR details and description.
2. Use 'gh pr diff' to see all the changes in the PR.
3. Analyze the code changes for:
- Code quality and style consistency
- Potential bugs or issues
- Performance implications
- Security concerns
- Test coverage
- Documentation updates if needed
4. Ensure any existing review comments have been addressed.
5. Generate constructive review comments in the CONSOLE. DO NOT POST TO GITHUB YOURSELF.
## Verification:
- After the review, run parallel subagents for each finding to double check it.
- Spawn up to a maximum of 10 parallel subagents at a time.
- Gather the results from the subagents and summarize them in the final review comments.
3. Review the changes following the `review` skill. It is VERY IMPORTANT to follow the `review` skill instructions.
4. Check if all existing review comments have been addressed.
## IMPORTANT:
- Just review. DO NOT make any changes
- Be constructive and specific in your comments
- Suggest improvements where appropriate
- Only provide review feedback in the CONSOLE. DO NOT ACT ON GITHUB.
- No need to run tests or linters, just review the code changes.
- No need to highlight things that are already good.
## Output format:
- List specific comments for each file/line that needs attention.
- In the end, summarize with an overall assessment (approve, request changes, or comment) and bullet point list of changes suggested, if any.
- Example output:
```
Overall assessment: request changes.
- [CRITICAL] sensor.py:143 - Memory leak
- [PROBLEM] data_processing.py:87 - Inefficient algorithm
- [SUGGESTION] test_init.py:45 - Improve x variable name
```
- Make sure to include the file and line number when possible in the bullet points.
+38
View File
@@ -0,0 +1,38 @@
---
name: review
description: Reviews code changes and provides constructive feedback. Should be used when a review is requested to provide a consistent review behavior and output format. This skill can be used for code reviews in general, not just for GitHub pull requests.
---
# Review Code Changes
## Analyze the code changes for:
- Code quality and style consistency
- Potential bugs or issues
- Performance implications
- Security concerns
- Test coverage
- Documentation updates if needed
## Verification:
- After the review, run parallel subagents for each finding to double-check it.
- Spawn up to a maximum of 10 parallel subagents at a time.
- Gather the results from the subagents and summarize them in the final review comments.
## IMPORTANT:
- Just review. DO NOT make any changes.
- Be constructive and specific in your comments.
- Suggest improvements where appropriate.
- No need to run tests or linters, just review the code changes.
- No need to highlight things that are already good.
## Output format:
- List specific comments for each file/line that needs attention.
- In the end, summarize with an overall assessment (approve, request changes, or comment) and bullet point list of changes suggested, if any.
- Example output:
```
Overall assessment: request changes.
- [CRITICAL] sensor.py:143 - Memory leak
- [PROBLEM] data_processing.py:87 - Inefficient algorithm
- [SUGGESTION] test_init.py:45 - Improve x variable name
```
- Make sure to include the file and line number when possible in the bullet points.