kiro-review

Review task implementations against specifications and boundary constraints with mechanical checks.

Updated Apr 16, 2026
One-click install
npx skills add https://github.com/manatago/gion --skill kiro-review-manatago
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kiro-review
Source: https://github.com/manatago/gion/tree/main/.claude/skills/kiro-review
Command: npx skills add https://github.com/manatago/gion --skill kiro-review-manatago

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The skill helps reviewers determine whether an implementer's work actually fulfills the approved requirements and design, stays inside the assigned task boundary, and includes verifiable evidence, preventing silent scope drift and hidden coupling.

Core Features & Use Cases

  • Adversarial, task-local review: reads the spec and diffs, executes mechanical checks (tests, greps) and flags concrete violations rather than relying on assertions.
  • Boundary and design audit: compares changed files to task boundary constraints and referenced design/requirements sections to detect spillover and hidden dependencies.
  • Validation evidence enforcement: verifies RED-phase outputs, scans for placeholder markers and secrets, runs static/runtime-sensitive checks, and reports required remediation.
  • Use case: run after an implementer marks a task READY_FOR_REVIEW to decide APPROVED or REJECTED with mechanistic supporting evidence.

Quick Start

Review task T123 using the task text, requirements.md sections, design.md sections, the implementer's status report, the task Boundary:, and validation commands, then run git diff and tests and return APPROVED or REJECTED with mechanical results and remediation.

Frequently Asked Questions about kiro-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify a code implementation meets specifications and boundaries before approval?

To verify spec compliance, review task implementations against approved requirements and boundary constraints by running git diff, executing tests, grepping changed files for placeholders and secrets, and cross-checking referenced design sections to return an APPROVED or REJECTED status.

What is task boundary auditing in an adversarial code review?

Task boundary auditing compares changed files to assigned task constraints and referenced design sections to detect scope spillover and hidden dependencies, preventing silent scope drift during post-implementation reviews and pre-acceptance verification.

How do I enforce validation evidence when reviewing a pull request?

Enforce validation evidence by verifying RED-phase test outputs, scanning changed files for placeholder markers and secrets, running static and runtime-sensitive checks, and reporting required remediation with mechanistic supporting evidence.

Can I use automated checks to detect scope drift in a codebase?

Yes, you can detect scope drift by running git diff to analyze changes, executing available project tests, and cross-checking referenced requirements against task boundary constraints to flag concrete violations mechanically.

Why does my code review miss hidden dependencies and scope spillover?

Code reviews miss hidden dependencies when they rely on assertions instead of mechanical verification, which you can fix by comparing changed files to task boundary constraints and grepping for placeholders and secrets to flag concrete violations.

What's the best way to check for placeholders and secrets in changed files?

The best way to check for placeholders and secrets is to grep changed files directly from the git diff output during the review process, ensuring validation evidence enforcement flags any embedded sensitive data or incomplete code markers.