self-review

Review git diffs for deletions, simplifications, and pattern mismatches.

2|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/thesyntaxninja/syntaxninja-dojo --skill self-review-thesyntaxninja
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: self-review
Source: https://github.com/thesyntaxninja/syntaxninja-dojo/tree/main/skills/self-review
Command: npx skills add https://github.com/thesyntaxninja/syntaxninja-dojo --skill self-review-thesyntaxninja

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents low-signal or biased self-assessments by providing a fresh-context review of the actual git diff, surfacing removals, simplifications, and pattern violations before code is committed or a PR is opened.

Core Features & Use Cases

  • Diff-first review: Instructs reviewers or agents to examine the git diff rather than relying on memory, ensuring decisions are based on the truth of changes.
  • Size-based strictness: Automatically adjusts review strictness by change size and file count, dispatching the sensei agent for medium-to-large changes and recommending quick inline checks for tiny edits.
  • Structured verdicts and loops: Produces actionable outcomes (REMOVE, SIMPLIFY, PATTERN MISMATCH, VERDICT) and supports up to two simplification rounds before escalation.
  • Use Case: Before opening a PR for a 40-line feature change, dispatch the sensei to catch dead code, pattern mismatches, and simplifications.

Quick Start

Dispatch the sensei agent to review the current git diff for quality, simplicity, and pattern compliance before creating a PR.

Frequently Asked Questions about self-review

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

FAQPage Schema
How do I review a git diff for code quality before committing?

To review a git diff for code quality before committing, this Skill runs git diff, assesses the change size, and dispatches a sensei review agent to identify deletions, simplifications, and pattern mismatches, returning structured verdicts and recommended actions.

What is a fresh-context code review and how does it work?

A fresh-context code review examines the git diff rather than relying on memory, preventing biased self-assessments by surfacing removals, simplifications, and pattern violations based strictly on the truth of the actual changes.

How do I get structured verdicts and actionable outcomes from a git diff?

You can get structured verdicts from a git diff by dispatching the sensei agent, which produces actionable outcomes like REMOVE, SIMPLIFY, PATTERN MISMATCH, and VERDICT, supporting up to two simplification rounds before escalation.

Can I adjust code review strictness based on the size of my changes?

Yes, you can adjust code review strictness automatically based on change size and file count. The system dispatches the sensei agent for medium-to-large changes and recommends quick inline checks for tiny edits.

When should I run a self-review on my git changes?

Run a self-review on your git changes when implementation and verification are complete and before committing or opening a pull request. It applies to changes ranging from small edits to multi-file refactors.

Does this code review tool work with multi-file refactors?

Yes, this code review tool works with multi-file refactors. It assesses change size and file count to automatically adjust review strictness, dispatching a sensei agent to catch dead code, pattern mismatches, and simplifications across the diff.