obra-requesting-code-review
Scannednpx machina-cli add skill faulkdev/github-copilot-superpowers/obra-requesting-code-review --openclawRequesting Code Review
Use the code-reviewer prompt in this directory to catch issues before they cascade (if your environment supports subagents). Otherwise, perform the same review manually.
Core principle: Review early, review often.
When to Request Review
Mandatory:
- After each task in subagent-driven development
- After completing major feature
- Before merge to main
Optional but valuable:
- When stuck (fresh perspective)
- Before refactoring (baseline check)
- After fixing complex bug
How to Request
1. Get git SHAs:
BASE_SHA=$(git rev-parse HEAD~1) # or origin/main
HEAD_SHA=$(git rev-parse HEAD)
2. Dispatch code-reviewer subagent:
Use the code-reviewer.md template in this directory for the review prompt.
Placeholders:
{WHAT_WAS_IMPLEMENTED}- What you just built{PLAN_OR_REQUIREMENTS}- What it should do{BASE_SHA}- Starting commit{HEAD_SHA}- Ending commit{DESCRIPTION}- Brief summary
3. Act on feedback:
- Fix Critical issues immediately
- Fix Important issues before proceeding
- Note Minor issues for later
- Push back if reviewer is wrong (with reasoning)
Example
[Just completed Task 2: Add verification function]
You: Let me request code review before proceeding.
BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)
[Dispatch code-reviewer prompt]
WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/deployment-plan.md
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
[Subagent returns]:
Strengths: Clean architecture, real tests
Issues:
Important: Missing progress indicators
Minor: Magic number (100) for reporting interval
Assessment: Ready to proceed
You: [Fix progress indicators]
[Continue to Task 3]
Integration with Workflows
Subagent-Driven Development:
- Review after EACH task
- Catch issues before they compound
- Fix before moving to next task
Executing Plans:
- Review after each batch (3 tasks)
- Get feedback, apply, continue
Ad-Hoc Development:
- Review before merge
- Review when stuck
Red Flags
Never:
- Skip review because "it's simple"
- Ignore Critical issues
- Proceed with unfixed Important issues
- Argue with valid technical feedback
If reviewer wrong:
- Push back with technical reasoning
- Show code/tests that prove it works
- Request clarification
See template at: requesting-code-review/code-reviewer.md
Source
git clone https://github.com/faulkdev/github-copilot-superpowers/blob/integrate-obra-superpowers/.github/skills/obra/obra-requesting-code-review/SKILL.mdView on GitHub Overview
This skill guides you to trigger a code-review before merges, major features, or task completion. It emphasizes catching issues early using the code-reviewer prompt to prevent cascading defects. It defines when to review (mandatory) and how to act on feedback.
How This Skill Works
Capture BASE_SHA and HEAD_SHA from git, then dispatch the code-reviewer subagent using the code-reviewer.md template. Fill placeholders for WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, and DESCRIPTION, and review the subagent's feedback. Prioritize Critical issues, then Important, and note Minor items for later before proceeding.
When to Use It
- After each task in subagent-driven development
- After completing major feature
- Before merge to main
- When stuck (fresh perspective)
- After fixing complex bug
Quick Start
- Step 1: Get git SHAs: BASE_SHA=$(git rev-parse HEAD~1) and HEAD_SHA=$(git rev-parse HEAD)
- Step 2: Dispatch code-reviewer with placeholders: WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, DESCRIPTION
- Step 3: Act on feedback: fix Critical, then Important issues; note Minor issues for later; push changes
Best Practices
- Always request a review after each task in subagent-driven development
- Use the code-reviewer.md template and fill the required placeholders precisely
- Capture BASE_SHA and HEAD_SHA with git commands before dispatch
- Act on feedback by fixing Critical issues first, then Important; note Minor issues for later; push back if reviewer is wrong with reasoning
- Integrate review results into your workflow before moving to the next task or merging
Example Use Cases
- Example 1: Just completed Task 2: Add verification function. You request code review with BASE_SHA and HEAD_SHA, fill WHAT_WAS_IMPLEMENTED and PLAN_OR_REQUIREMENTS, and receive feedback like 'Strengths: Clean architecture, real tests; Issues: Important: Missing progress indicators.' You fix the issue types accordingly and proceed.
- Example 2: After implementing a major feature, you dispatch code-reviewer to validate requirements alignment and edge cases; reviewer surfaces 'Critical: security consideration' and you address it before merging.
- Example 3: Before merging a long-lived feature branch, you perform a final review to ensure no critical issues and documented changes.
- Example 4: When stuck on a refactor, you request a quick fresh perspective to surface hidden dependencies or regressions.
- Example 5: After fixing a complex bug, you run a targeted review to verify all related paths are covered and no new issues were introduced.
