Agent skill
address-feedback
Address and implement review feedback on a pull request
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/address-feedback-daemn256-workspace-repo-templ
SKILL.md
Address Feedback
Uses Implementer. Parse review feedback, plan changes, and implement them with approval at each step. Ensures feedback is addressed systematically without introducing unrelated changes.
Prerequisites: Review feedback available, PR context (branch, changes)
Phase 1: Parse Feedback
Gather and Categorize
- Read all review comments
- Categorize each item by type:
- Blocking — Must address before merge
- Suggestion — Non-blocking improvement
- Nitpick — Style preference, optional
- Question — May not require code change
- Identify exact file locations and planned actions
- Present in structured table
Output
## Context Anchors
- **PR:** #<number> - <title>
- **Phase:** 1 — Parse Feedback
- **Feedback items:** <count>
## Feedback Analysis
| # | Type | Location | Summary | Planned Action |
| --- | ---------- | ----------- | --------- | -------------- |
| 1 | Blocking | <file:line> | <summary> | <action> |
| 2 | Suggestion | <file:line> | <summary> | <action> |
## Next Step
Confirm understanding of feedback before implementing.
**Approval Required:** Yes
⛔ CHECKPOINT
STOP. Do not proceed until human explicitly approves:
- Feedback categorization is correct
- Planned actions are appropriate
- Priority order is agreed
Phase 2: Implement Changes
Address Each Item
- Work through items by priority (Blocking first)
- Make focused changes per item
- Run the workspace's build and test commands (read from
workspace.config.yaml) after each change - Report progress per item
Output
## Context Anchors
- **PR:** #<number> - <title>
- **Phase:** 2 — Implement Changes
- **Item:** <N of total>
## Progress
| # | Item | Status | Notes |
| --- | --------- | -------------- | --------------- |
| 1 | <summary> | ✅ Done | <what changed> |
| 2 | <summary> | 🔄 In Progress | <current state> |
## Verification
- [ ] Build passes
- [ ] Tests pass
## Next Step
<Continue to next item or proceed to report>
**Approval Required:** Yes
⛔ CHECKPOINT
STOP after each significant change. Await approval before proceeding to the next item.
Phase 3: Report
Summarize and Prepare Commit
-
List all changes made per feedback item
-
Run the workspace's build and test commands (read from
workspace.config.yaml) -
Prepare commit message:
git commit -m "fix(<scope>): address review feedback <body listing changes per item>"
Output
## Context Anchors
- **PR:** #<number> - <title>
- **Phase:** 3 — Report
## Changes Summary
| # | Feedback Item | Resolution | Files Modified |
| --- | ------------- | --------------- | -------------- |
| 1 | <summary> | <what was done> | <files> |
## Verification Block
- [x] Build passes
- [x] Tests pass (<counts>)
- [x] All blocking items addressed
## Next Step
Awaiting approval to commit changes.
**Approval Required:** Yes
⛔ CHECKPOINT
STOP. Do not commit until human explicitly approves:
- All changes are correct
- No unintended modifications
- Commit message is appropriate
Feedback Type Handling
| Type | Approach |
|---|---|
| Blocking | Must address before merge |
| Suggestion | Implement if reasonable, otherwise explain why not |
| Nitpick | Optional, can discuss or accept |
| Question | Provide answer, may not require code change |
Error Handling
| Error | Recovery |
|---|---|
| Ambiguous feedback | Ask for clarification |
| Conflicting feedback items | Flag conflict, ask for resolution |
| Feedback requires architectural change | Escalate, don't implement unilaterally |
| Tests fail after change | Report failure, seek guidance |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?