# Receiving Code Review

> Use when receiving code review feedback, before implementing suggestions — verify each finding against the codebase, clarify unclear items first, act by severity, push back with evidence when the reviewer is wrong.

- **Type:** Skill
- **Install:** `agentstack add skill-skywalkercyt-mp-implement-receiving-code-review`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [skywalkercyt](https://agentstack.voostack.com/s/skywalkercyt)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [skywalkercyt](https://github.com/skywalkercyt)
- **Source:** https://github.com/skywalkercyt/mp-implement/tree/main/skills/receiving-code-review

## Install

```sh
agentstack add skill-skywalkercyt-mp-implement-receiving-code-review
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Receiving Code Review

> **Adapted skill** — discipline originating in Superpowers v5.1.0 (MIT, Jesse Vincent), rewritten in mattpocock-skills style. Governs how reviewer feedback is acted on in `/mp-implement-issue` step 8 and both pipelines' harvest.

Review feedback is data to evaluate, not orders to follow.

## Process

1. **Verify each finding against the codebase before acting on it.** Check it is technically correct for this code, doesn't break existing behavior, and isn't based on missing context.
2. **Clarify all unclear items before implementing any.** Findings may be related; partial understanding produces wrong fixes.
3. **Act by severity.** Fix Critical and Important before proceeding. Minor goes in the PR description or a follow-up issue.
4. Implement one item at a time; test each fix and check for regressions.

## Pushback

When the reviewer is wrong, push back with technical reasoning and evidence — working tests, the code itself, platform constraints. When a finding conflicts with a prior decision of the user's, put it to the user rather than silently following either side.

When your pushback was wrong, state the correction plainly and fix it. No apology, no defending the original position.

## YAGNI check

Before accepting a "do it properly" suggestion, grep for actual usage of the thing being improved. If nothing uses it, propose deleting it instead.

## Responding

Respond with the technical action — what you changed, what you verified, or why the finding is wrong. Agreement and gratitude carry no information; the code is the reply.

## GitHub threads

Reply to inline review comments in the comment thread, not as a top-level PR comment:

```
gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [skywalkercyt](https://github.com/skywalkercyt)
- **Source:** [skywalkercyt/mp-implement](https://github.com/skywalkercyt/mp-implement)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-skywalkercyt-mp-implement-receiving-code-review
- Seller: https://agentstack.voostack.com/s/skywalkercyt
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.