skills.rest
jnyross
jnyrossCOMMUNITY
Explore all skills by this author →
GitHub

interrogate

Spawns multiple LLM reviewers to adversarially review code changes and synthesizes a verdict.

Updated Sep 2, 2026
Search Tags:#code quality#diff analysis#code review#pull request#llm#multi-model#adversarial review
One-click install
npx skills add https://github.com/jnyross/pstack-muse --skill interrogate-jnyross
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: interrogate
Source: https://github.com/jnyross/pstack-muse/tree/main/skills/interrogate
Command: npx skills add https://github.com/jnyross/pstack-muse --skill interrogate-jnyross

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Single-reviewer code reviews miss blind spots and reflect one model's biases. This Skill runs adversarial multi-model review so independent reviewers challenge your changes from different angles, then filters the noise into an actionable verdict. ## Core Features & Use Cases - Multi-Model Adversarial Review: Spawns one reviewer per configured model, each applying the same rubric and code-quality lens to the same diff. - Consensus Synthesis: Deduplicates findings, highlights issues raised by 2+ models as high-confidence signal, and maps agreement and disagreement across reviewers. - Lead Judgment Filtering: Categorizes every finding as act on, consider, noted, or dismissed, with rationale, so nitpicks and context-blind findings don't block shipping. - Use Case: Before merging a feature branch, run an adversarial review on git diff main...HEAD to catch correctness bugs, security issues, and structural regressions that a single reviewer would miss. ## Quick Start Ask the AI to interrogate the changes on your current feature branch and produce a synthesized adversarial review verdict.

Frequently Asked Questions about interrogate

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

FAQPage Schema
How do I run a multi-model adversarial code review?▼

Point the skill at a diff or files, state the intent of the change, and it spawns one reviewer per configured model with the same prompt and rubric. Results are synthesized into a verdict with consensus findings and lead-judgment categorization.

What is the benefit of multi-model code review over a single reviewer?▼

Different models have different blind spots, priors, and reasoning patterns. Findings raised independently by two or more models are high-confidence signal, while lone-model findings are weighted lower during synthesis.

Does adversarial review automatically apply fixes to my code?▼

No. The deliverable is a synthesized verdict only, with findings categorized as act on, consider, noted, or dismissed. You decide which findings to address before making any changes.

What happens if a configured reviewer model slug is invalid?▼

The skill checks the valid slugs in the error message, picks the closest equivalent preferring the highest-reasoning tier of the same family, and continues the review. It does not block on the slug issue.

When should I not use adversarial multi-model review?▼

It is overkill for trivial changes like typo fixes or small config edits. The multi-reviewer spawn cost is justified for feature branches, security-sensitive code, or structural changes where blind spots carry real risk.

Related Skills

Explore More Software Engineering Skills→
reactivereactive
2.0k

pr

Creates GitHub pull requests from working changes with generated titles and descriptions.

Official
Intermediate
RayzerrekRayzerrek

code-review-and-quality

Review code changes for correctness, readability, architecture, security, and performance.

Community
Advanced
criniscrinis
4

css-review

Reviews CSS code for redundancy, duplication, and semantic consistency with linters.

Community
Advanced
summarybotngsummarybotng
2

code-review-quality

Conduct context-driven code reviews focusing on quality, testability, and maintainability.

Official
Advanced