review

Evaluate code findings with evidence-based criteria and confidence labeling.

211|9|Updated Dec 16, 2025
One-click install
npx skills add https://github.com/nexxeln/opencode-config --skill review-nexxeln
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/nexxeln/opencode-config/tree/main/skill/review
Command: npx skills add https://github.com/nexxeln/opencode-config --skill review-nexxeln

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides structured guidelines and best practices for producing and assessing defensible, high-quality findings during code reviews, debugging, and analysis.

Core Features & Use Cases

  • Standardized Evaluation: Offers explicit criteria for verifying correctness, understanding abstractions, and labeling confidence levels.
  • Falsification and Evidence: Guides users to design tests that could disprove hypotheses and to trace claims to concrete evidence.
  • Use Case: When reviewing complex code changes, use this Skill to systematically evaluate the correctness, identify potential contradictions, and record clear findings.

Quick Start

Load this Skill before reviewing code to follow epistemic standards and produce traceable, well-supported analysis.

Frequently Asked Questions about review

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

FAQPage Schema
What are epistemic standards for code review and why do they matter?

Epistemic standards for code review enforce strict criteria for verifying correctness and tracing claims to concrete evidence. They matter because they ensure your findings are defensible, traceable, and clearly labeled with confidence levels during technical assessments.

How do I produce defensible findings during debugging?

To produce defensible findings during debugging, you should design tests that could actively disprove your hypotheses and trace all claims back to concrete evidence. This structured approach ensures your analysis is high-quality and falsifiable.

How do I structure technical reports for code quality assurance?

Structure technical reports for code quality assurance by applying standardized evaluation criteria to verify correctness and label confidence levels. This ensures your analysis satisfies requirements for structured reporting and well-supported technical assessments.

Can I use standardized evaluation criteria to review complex code changes?

Yes, you can use standardized evaluation criteria to review complex code changes by systematically evaluating correctness, identifying potential contradictions, and recording clear findings with explicit confidence labels and evidence-based support.

What is falsification in software analysis and when should I apply it?

Falsification in software analysis is the practice of designing tests that could disprove your hypotheses rather than just confirming them. You should apply it during code reviews and debugging to enforce strict epistemic standards and improve analysis quality.