sherlock-review

Analyze code, tests, and runtime output to validate implementation claims.

1|Updated Dec 29, 2025
One-click install
npx skills add https://github.com/aquariuscook/Agent_Modus_Map --skill sherlock-review-aquariuscook
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sherlock-review
Source: https://github.com/aquariuscook/Agent_Modus_Map/tree/main/.claude/skills/sherlock-review
Command: npx skills add https://github.com/aquariuscook/Agent_Modus_Map --skill sherlock-review-aquariuscook

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a systematic, evidence-based approach to code review, ensuring that implementation claims are rigorously verified against actual behavior and data.

Core Features & Use Cases

  • Verifies Implementation Claims: Ensures code does what it says it does.
  • Investigates Bugs & Fixes: Identifies root causes and validates solutions.
  • Conducts Root Cause Analysis: Systematically observes, deduces, and concludes.
  • Use Case: When a pull request claims to fix a critical bug, use this Skill to meticulously examine the code changes, test results, and runtime behavior to confirm the fix is effective and doesn't introduce new issues.

Quick Start

Use the sherlock-review skill to investigate the claims made in PR #123.

Frequently Asked Questions about sherlock-review

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

FAQPage Schema
How do I validate implementation claims against actual runtime behavior during a code review?

Evidence-based code review validates implementation claims by systematically observing code, tests, and runtime output to deduce discrepancies. It eliminates impossible conclusions and relies on reproducible evidence to confirm actual behavior.

What is the best way to conduct root cause analysis for a critical bug fix?

Root cause analysis for a bug fix requires systematic observation of code changes and test results. By applying deductive reasoning, you eliminate impossible conclusions and validate the fix against reproducible runtime evidence.

How do I investigate if a pull request actually fixes a bug without introducing new issues?

To investigate a pull request, meticulously examine the code changes, test results, and runtime behavior. This validates the fix's effectiveness and ensures no new issues are introduced by relying on reproducible evidence.

Can I use deductive reasoning to verify bug validation in my test suite?

Yes, you can verify bug validation by analyzing test suite outputs and runtime behavior. Deductive reasoning helps systematically observe results, eliminate impossible conclusions, and confirm fixes using reproducible evidence.

What are the limitations of evidence-based code investigation for quality assurance?

Evidence-based code investigation requires reproducible runtime output and systematic observation to function effectively. It is limited when actual behavior cannot be observed or when test results lack the evidence needed for deductive reasoning.