Skeptic Reviewer — Development agent for Claude Code
Hunts handwavium, underestimated complexity, and fragile assumptions in the subject under review.
How to install Skeptic Reviewer
Installs to ~/.claude/agents/skillweave-loom-skeptic-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/skillweave/loom/HEAD/agents/skeptic-reviewer.md -o ~/.claude/agents/skillweave-loom-skeptic-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Skeptic Reviewer does
name: skeptic-reviewer description: Hunts handwavium, underestimated complexity, and fragile assumptions in the subject under review. tools: [Read, Grep, Glob, SendMessage]
skeptic-reviewer
You are the skeptic. You hunt handwavium — vague phrasing that sounds confident but commits to nothing.
Your project context
Read the **project-context block** under `## Project context (from .loom/project.md)` before reviewing. The **Conventions** and **Review discipline** sections tell you
Alternatives in Development
- Seam Analyzer — Hunts for a missing type at a seam — structure flattened and rebuilt downstream, hand-maintained lists held to 2.2k ★
- Review Performance — Reviews code changes for performance issues including algorithmic complexity, unnecessary allocations, lock co 432 ★
- Skeptic 194 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Doey Masterplan Critic
Masterplan Critic — 'what could go wrong' reviewer for draft PLANS (not code). Hunts unstated assumptions, edg
Coverage Reviewer
Finds gaps, missing scenarios, ambiguity, and scope drift in the subject under review.
Tech Reviewer
Verifies factual claims in the subject under review against the actual code and external references the subjec
Psychodrama Skeptic
Use ONLY by psychodrama-protocol skill orchestrator. Anti-groupthink role — must surface weaknesses, contradic
Mb Reviewer Scalability
Performance/scalability reviewer for Memory Bank governed review ensembles. Focuses on complexity, hot paths,
Simplicity Reviewer
Review code for unnecessary complexity, complection, premature abstraction, and incidental complexity
Related Skills
Autonomous Learning OS
AGENTIC · LEARNING — Hand this repo to your agent. It interviews you, hunts down the best sources in the world
Karpathy Check
Run Karpathy's 4-principle review on staged changes or the last commit. Checks complexity, diff noise, hidden
Cmd Judge
Adversarial verifier for the PROVE phase: treats a finished-work report as untrusted claims, re-runs every ver