micro-harsh-review

Scores code changes with three-critic review and flags anti-patterns before commit.

8|1|Updated Jan 24, 2026
One-click install
npx skills add https://github.com/bordenet/superpowers-plus --skill micro-harsh-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: micro-harsh-review
Source: https://github.com/bordenet/superpowers-plus/tree/main/skills/engineering/micro-harsh-review
Command: npx skills add https://github.com/bordenet/superpowers-plus --skill micro-harsh-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Developers need a rapid, yet rigorous review process for small code changes that is stricter than linting but much quicker than a full pull‑request review.

Core Features & Use Cases

  • 3‑Critic Protocol: NitpickLineByLine, ArchSoundnessProbe, and ProdBattleTest each score the change on ten‑point scales.
  • Scoring System: Average score ≥ 8 passes, 6–8 triggers conditional fixes, < 6 rejects the change.
  • Anti‑Pattern Detection: Flags rubber‑stamping, inflated scores, and overly long reviews.
  • Integration: Enables the pre-commit-gate and escalates to progressive-code-review-gate when needed.
  • Use Cases: Pre‑commit checks for any code modification, quick safety nets for router pattern updates, and lightweight gate before pushing to shared branches.

Quick Start

Run micro‑harsh‑review on the current change before committing.

Frequently Asked Questions about micro-harsh-review

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

FAQPage Schema
How do I run a fast pre-commit code review for small feature tweaks?

A pre-commit code review applies a multi-critic scoring protocol to individual code modifications before committing. It evaluates changes across three personas, requiring an average score of at least eight to pass.

What is a multi-critic code review and how does the scoring work?

A multi-critic code review scores changes using three personas: NitpickLineByLine, ArchSoundnessProbe, and ProdBattleTest. An average score of eight or higher passes, six to eight requires fixes, and below six rejects the change.

Can I use this pre-commit quality gate for router pattern updates?

Yes, you can use this pre-commit quality gate as a quick safety net for router pattern updates. It is designed for individual code modifications and small tweaks where a full pull-request review is excessive.

Does the pre-commit code review integrate with progressive code review gates?

Yes, the pre-commit code review enables the pre-commit-gate and escalates to the progressive-code-review-gate when needed. This integration ensures small changes are checked rapidly while larger issues trigger deeper reviews.

How does the code review critic handle anti-patterns like inflated scores?

The code review critic includes anti-pattern detection that actively flags rubber-stamping, inflated scores, and overly long reviews. This ensures the multi-critic evaluation remains rigorous and does not approve poor modifications.