agent-skeptic

Reviews Worker outputs for weaknesses and classifies findings as Critical, Major, or Minor.

12|1|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/Space-Dinosaurs/DinoStack --skill agent-skeptic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-skeptic
Source: https://github.com/Space-Dinosaurs/DinoStack/tree/main/.openclaw/skills/agent-skeptic
Command: npx skills add https://github.com/Space-Dinosaurs/DinoStack --skill agent-skeptic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Adversarial code reviewer spawned when performing Skeptic Protocol reviews of Worker output. It evaluates implementation against an adversarial brief, classifies findings as Critical/Major/Minor, and produces a structured sign-off. The spawn prompt must contain four things: (1) the adversarial brief defining the attack surface to probe, (2) Worker output as inline text or file paths, (3) a resolved-issues preflight listing findings addressed in prior rounds, and (4) a Global-context input set containing the architect plan path, Brief/Plan artifact path, qa_criteria block, per-consumer impact table, related files list, and diff under review. See content/references/skeptic-protocol.md Section 4.5 for the canonical block format.

Core Features & Use Cases

  • Supports complete Skeptic Protocol reviews by acting as adversarial reviewer.
  • Classifies findings into Critical/Major/Minor and provides a formal sign-off.
  • Enforces the four required spawn prompt components to ensure thorough evaluation.

Quick Start

Give the adversarial brief and Worker outputs to the skeptic and request a structured sign-off.

Frequently Asked Questions about agent-skeptic

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

FAQPage Schema
How do I conduct an adversarial code review of worker output?

Adversarial code review evaluates worker output against a defined attack surface brief, classifying findings as Critical, Major, or Minor to produce a structured sign-off.

What is the Skeptic Protocol for code review?

The Skeptic Protocol is a review process where an adversarial reviewer probes implementation weaknesses using a brief, worker outputs, resolved-issues preflight, and global-context inputs to drive classification and sign-off.

How do I classify code review findings by risk severity?

Risk classification sorts code review findings into Critical, Major, and Minor severity levels based on the adversarial brief and the potential attack surfaces identified in the worker output.

What inputs are required to spawn a structured adversarial review?

Spawning an adversarial review requires four components: an adversarial brief, worker outputs, a resolved-issues preflight, and a global-context input set containing the architect plan, qa_criteria, and diff under review.

Can I use adversarial review without a resolved-issues preflight list?

No, a resolved-issues preflight listing findings addressed in prior rounds is a required spawn prompt component to ensure the adversarial reviewer does not duplicate previously resolved work.

What is the best way to structure a global-context input for code sign-off?

A structured global-context input must contain the architect plan path, Brief artifact path, qa_criteria block, per-consumer impact table, related files list, and diff under review to generate a formal sign-off.