World Render Reviewer — Data & AI agent for Claude Code
Tiered visual/geometric quality review of a rendered world state — Tier 0 pure-data scoring by default, escalating to the annotated/gridlined render only when Tier 0/1 flags an anomaly.
How to install World Render Reviewer
Installs to ~/.claude/agents/ttnhan18062000-rpg-based-simulation-world-render-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ttnhan18062000/rpg-based-simulation/HEAD/.claude/agents/world-render-reviewer.md -o ~/.claude/agents/ttnhan18062000-rpg-based-simulation-world-render-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What World Render Reviewer does
name: world-render-reviewer description: Tiered visual/geometric quality review of a rendered world state — Tier 0 pure-data scoring by default, escalating to the annotated/gridlined render only when Tier 0/1 flags an anomaly. Cites tile coordinates from the annotated image, never the plain render. tools: Read
World Render Reviewer
You are a **tiered** visual/geometric quality review subagent for the rpg-based-simulation project's rendered world states. Given a `Tier1Digest` produced
Alternatives in Data & AI
- Visual Explainer — Agent skill + prompt templates that generate rich HTML pages for visual diff reviews, architecture overviews 6.8k ★
- Stack Auditor — Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses th 801 ★
- Pricing Updater — Use this agent to update LLM pricing data in the default-pricing.ts file 175 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Exec Subtle
FRONTIER-DO tier at max effort. ULTRATHINK execution agent for the single subtlest workstream in a plan - deri
Implementer Opus
High implementation tier. Use when the change carries design weight or risk — touching an architectural bounda
Post Producer
A specialized post-production agent that reviews rendered videos using TwelveLabs AI vision, provides professi
Analytics Analyst
Invoke when the user needs help with marketing measurement, KPI definition, dashboard design, attribution mode
Eval Best No Type Rules
Eval arm best-no-type-rules (best without render_chart's per-type rules; Q23 arm C). Answers one building-data
Chadi Performance
Performance and reliability review subagent for render performance, bundle size, API latency, database queries
Related Skills
Cole
Delegate a task to Cole, the morning-briefing + pipeline-anomaly agent. Authors the 06:30 MT digest, flags dea
Tty7
A terminal workbench in pure Rust: shells, persistent sessions, SSH, coding agents. GPU-rendered on Zed's gpui
Authenticity Check
Pure-prompt skill that scores how authentically text reads as a real human author's work and flags AI-generate