agent-skeptic
OfficialAdversarial reviewer for robust code reviews.
System Documentation
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.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agent-skeptic Download link: https://github.com/Space-Dinosaurs/DinoStack/archive/main.zip#agent-skeptic Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.