diegosouzapw/awesome-omni-skill / skills/ai-agents/agent-ops-code-review-interactive
agent-ops-code-review-interactive
UnverifiedInteractive code review for agent iterations. Captures comments, tracks resolution status, and integrates with git diffs.
Interactive Code Review Skill
Purpose
Provide structured code review workflow after agent implementation iterations. Allows capturing comments with categories and tracking resolution status.
Storage Format
Reviews are stored in .agent/reviews/:
.agent/reviews/
├── YYYY-MM-DD-<short_hash>.md # Review for specific commit
├── active-review.md # Currently open review
└── README.md # Review folder documentation
Review Document Format
# Code Review: <commit_hash>
**Date**: YYYY-MM-DD HH:MM
**Author**: [user|agent]
**Commit**: <full_hash>
**Branch**: <branch_name>
## Summary
<brief description of changes reviewed>
## Changed Files
| File | Lines Changed | Status |
|------|---------------|--------|
| src/foo.py | +15 -3 | reviewed |
| tests/test_foo.py | +25 | pending |
## Comments
### [CATEGORY] File:Line — Comment Title
**File**: `path/to/file.py`
**Line**: 42-45
**Category**: fix | question | suggestion | concern | praise
**Status**: open | addressed | wont_fix | deferred
**Priority**: critical | high | normal | low
<comment body>
#### Response (if any)
<agent or user response>
---
### [SUGGESTION] src/utils.py:78 — Consider extracting helper
**File**: `src/utils.py`
**Line**: 78
**Category**: suggestion
**Status**: addressed
**Priority**: normal
This block of code appears in multiple places. Consider extracting to a helper function.
#### Response
Extracted to `_format_output()` helper in commit abc123.
---
## Metrics
- Total Comments: X
- Open: X
- Addressed: X
- Won't Fix: X
- Deferred: X
Comment Categories
| Category | Icon | Use For |
|---|---|---|
fix | 🔧 | Required changes, bugs, errors |
question | ❓ | Clarification needed |
suggestion | 💡 | Optional improvements |
concern | ⚠️ | Potential issues, risks |
praise | 👍 | Good patterns, well done |
Status Transitions
open → addressed (when fix is committed)
open → wont_fix (when decided not to fix with reason)
open → deferred (when moved to future work)
CLI Integration (Proposed)
# Start review for current changes
aoc review start
# Start review for specific commit
aoc review start <commit>
# View current review
aoc review show
# Add a comment
aoc review comment --file src/foo.py --line 42 --category fix "Fix null check"
# Mark comment as addressed
aoc review resolve <comment_id>
# Mark as won't fix
aoc review wontfix <comment_id> --reason "Out of scope"
# Defer to issue
aoc review defer <comment_id> --issue FEAT-0123
# Complete review
aoc review complete
# Generate summary
aoc review summary
Workflow Integration
After Implementation
User: Review the changes
Agent:
1. Get diff since last commit/baseline
2. Apply agent-ops-critical-review analysis
3. Create review document
4. Present findings organized by category
5. Ask for user feedback
User: [Provides comments]
Agent:
1. Record comments in review document
2. Address fix/question items
3. Commit changes
4. Update comment statuses
5. Present updated review
Integration with Validation
The validation skill can check for unresolved review comments:
## Pre-Commit Checklist
- [ ] All tests pass
- [ ] No lint errors
- [ ] Coverage maintained
- [x] Review comments addressed (3 open → requires resolution)
Review Templates
Quick Review (for small changes)
# Quick Review: <hash>
**Changes**: <summary>
## Comments
- **src/foo.py:23**: [fix] Missing null check
- **src/bar.py:45**: [suggestion] Could simplify with list comprehension
## Status: open/complete
Detailed Review (for PRs/major changes)
Full format as shown above.
Best Practices
- Review early, review often — Don't let comments accumulate
- Be specific — Include file paths and line numbers
- Categorize correctly — Helps prioritize response
- Track everything — All decisions should be captured
- Close the loop — Every comment should reach a final status
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 464k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 464k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 318k | Updated | Claude CodeCodex | Unverified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 318k | Updated | Claude CodeCodex | Unverified | Install |