Skip to content
Back to skills

Requesting Code Review

ASecurity

Use after meaningful implementation work to create an independent Yardlet review task

  • 17 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 5, 2026
ai-agentsgocode-review

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned September 5, 2026

npx -y skills add zzunkie/yardlet --skill requesting-code-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Requesting Code Review?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Requesting Code Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/zzunkie-requesting-code-review/badge)](https://www.skillsdirectory.com/skills/zzunkie-requesting-code-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: requesting-code-review
description: Use after meaningful implementation work to create an independent Yardlet review task
---

# Requesting Code Review

## Purpose

Turn review into an explicit Yardlet queue item with bounded inputs and a
structured verdict. Review is independent work, not an implicit hidden action.

## When to Request

Request review after a meaningful implementation slice, before integration, or
when the task contract explicitly requires independent acceptance review.

## Prepare Evidence

Record:

- what was implemented;
- the governing intent, task, or specification;
- the exact changed files or local revision range;
- validation commands already run and their results;
- unresolved risks or assumptions.

Do not claim that the implementation is correct. The review task owns that
judgment.

## Create the Review Task

Create or propose a normal Yardlet queue task with `kind: review`. Keep its
allowed scope read-only unless the contract explicitly creates a separate
repair task. Use [code-reviewer.md](code-reviewer.md) as the review body.

The review must return one verdict per acceptance criterion with concrete file,
command, or runtime evidence. A failed criterion remains failed until a later
repair task changes the workspace and review is rerun.

## Act on Findings

- Repair critical and important findings in a bounded implementation task.
- Challenge an incorrect finding with code or test evidence.
- Keep optional polish separate from blocking acceptance.
- Never mark the reviewed task complete solely because the implementer reports success.

Files in this skill

  • .yardlet-managed.yaml320 B
  • LICENSE.txt1 KB
  • SKILL.md1.6 KB
  • code-reviewer.md934 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.