- Home
- Skills
- Mhattingpete
- Claude Skills Marketplace
- Review Implementing
review-implementing_skill
- HTML
269
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill mhattingpete/claude-skills-marketplace --skill review-implementing- SKILL.md3.6 KB
Overview
This skill processes and implements code review feedback in a systematic, traceable way. It turns reviewer comments into discrete todos, applies changes following project conventions, runs validations, and keeps the requester informed throughout the process.
How this skill works
The skill parses reviewer notes into individual actionable items, creates a prioritized todo list, and marks the first task in_progress. For each todo it locates relevant code, makes edits or adds files, writes tests or docs when needed, and verifies changes by running tests and lint checks. Todos are marked completed immediately after verification and progress is reported in real time.
When to use it
- You have reviewer comments, PR feedback, or pasted code review notes to implement
- You ask to “address these comments” or “implement feedback” on a PR
- You need review suggestions broken into actionable development tasks
- You want code changes, tests, or docs updated to reflect reviewer requests
Best practices
- Parse and break feedback into small, specific todos before editing code
- Keep only one todo in_progress at a time and mark completed immediately after verification
- Preserve existing functionality unless the review explicitly requires behavior changes
- Run affected tests and linting (e.g., uv run ruff check) before marking tasks done
- Ask clarifying questions for ambiguous or conflicting feedback
Example use cases
- Convert a reviewer’s numbered PR comments into a TodoWrite task list and implement each change
- Fix a failing edge-case test requested in a code review, then add a new unit test
- Update docstrings and markdown per reviewer suggestions while following project conventions
- Refactor duplicate logic as requested and verify no regressions by running the test suite
- Add type hints and small API improvements cited in a review and commit with conventional commit messages
FAQ
I will pause and ask for clarification, explain the conflict, and request guidance before implementing changes.
Do you run tests and linters after each change?
Yes — affected tests and lint checks are run before marking a todo completed. If tests fail, I fix them or report blockers.