scrutinize

Trace real execution paths of plans, PRs, or code changes and produce rationale-backed findings.

Updated May 21, 2026
One-click install
npx skills add https://github.com/louderthanthunderx1/loki-skills --skill scrutinize-louderthanthunderx1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scrutinize
Source: https://github.com/louderthanthunderx1/loki-skills/tree/main/skills/engineering/scrutinize
Command: npx skills add https://github.com/louderthanthunderx1/loki-skills --skill scrutinize-louderthanthunderx1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Outsider-perspective end-to-end review of a plan, PR, or code change. First questions intent and whether a simpler/more elegant approach would achieve the same goal, then traces the actual code path (not just the diff) to verify the change does what it claims. Output is concise, actionable, and every call carries its rationale. Trigger on /scrutinize and proactively whenever the user asks to review, audit, sanity-check, or get a second opinion on a plan, PR, diff, design doc, or proposed code change.

Core Features & Use Cases

  • Outsider-perspective evaluation that ignores author identity and focuses on problem-solution fit.
  • End-to-end trace of the artifact’s real execution path, beyond the visible diff.
  • Actionable findings with concrete rationale, evidence, and suggested changes.

Quick Start

Tell me to scrutinize a specific plan, PR, or code change to receive an end-to-end, rationale-backed review.

Frequently Asked Questions about scrutinize

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

FAQPage Schema
How do I conduct an end-to-end code review that traces real execution paths instead of just diffs?

A PR audit reviews whether a change should exist by questioning intent and evaluating simpler approaches. It traces real execution paths to verify claims, identifying edge cases and mapping evidence to produce actionable, rationale-backed findings.

What is the best way to sanity-check a design doc or proposed code change from an outsider perspective?

An outsider review evaluates problem-solution fit by ignoring author identity. It audits plans, PRs, or code changes end-to-end, verifying execution paths and producing concise, actionable findings with concrete rationale and suggested changes.

How do I audit a project plan to identify edge cases and determine if the change should exist?

A plan audit questions whether a proposed change should exist by evaluating simpler alternatives. It traces execution paths to identify edge cases, mapping evidence to produce concise, rationale-backed findings and concrete suggestions.

Can I get a rationale-backed second opinion on a code diff before merging?

Yes, a rationale-backed second opinion traces the actual code path to verify a diff's claims. It produces concise findings with concrete suggestions, identified edge cases, and evidence mapping directly to the artifact under review.

Does an outsider code review require specific dependencies or components to function?

No, an outsider code review requires no specific dependencies or components. It operates directly on provided plans, PRs, or code changes to evaluate intent and trace execution paths without any environmental setup.