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
SKILL.md
Address Feedback
The Implementer drives this workflow. Parse review feedback, plan changes, and implement them with approval at each step.
Prerequisites: Review feedback (what was requested), access to codebase, PR context (branch, changes).
Phase 1: Parse Feedback
Extract and categorize specific requested changes.
Steps
- Read all review comments
- Categorize by type (Blocking, Suggestion, Nitpick, Question)
- Identify exact locations and planned actions
- Summarize in a structured table
Output
## Context Anchors
- **PR:** #<number> - <title>
- **Feedback items:** <count>
## Feedback Analysis
| # | Type | Feedback | Location | Planned Action |
| --- | -------- | --------- | ----------- | ---------------- |
| 1 | Blocking | <summary> | <file:line> | <planned change> |
## Next Step
Confirm understanding of feedback before implementing.
**Approval Required:** Yes
⛔ CHECKPOINT
STOP. Do not proceed until human confirms understanding of feedback.
Phase 2: Implement Changes
Address each feedback item by priority.
Steps
- Work through items by priority (Blocking first)
- Make focused changes per item
- Verify each change by running the workspace's build and test commands (read from
workspace.config.yaml) - Report progress per item
⛔ CHECKPOINT
STOP. Checkpoint after each significant change.
Phase 3: Report
Summarize changes made and prepare for re-review.
Steps
- List all changes made per feedback item
- Run build and tests
- Prepare commit message
Output
## Context Anchors
- **PR:** #<number> - <title>
- **Feedback items addressed:** <count>
## Changes Made
| # | Feedback | Change Made | Verified |
| --- | --------- | --------------- | -------- |
| 1 | <summary> | <what was done> | ✅ |
## Verification Block
- [x] Build passes
- [x] Tests pass
## Next Step
Approve to commit changes.
**Approval Required:** Yes
⛔ CHECKPOINT
STOP. Await approval to commit.
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.
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.
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.
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.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
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?