Logo Critic — Data & AI agent for Claude Code
Blind, independent scorer for logo candidates, especially AI-generated ones.
How to install Logo Critic
Installs to ~/.claude/agents/kosminog-striatum-logo-critic.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/kosminog/striatum/HEAD/agents/logo-critic.md -o ~/.claude/agents/kosminog-striatum-logo-critic.md Restart Claude Code, or start a new session, for it to be picked up.
What Logo Critic does
name: logo-critic description: Blind, independent scorer for logo candidates, especially AI-generated ones. Use after any generation round or before showing a logo direction to a client: it reads the brand brief, views each candidate at small and large size, scores every one on the ten-row critique checklist, flags resemblance to existing marks and accidental readings, and tells the author exactly what to change in the next prompt or redraw. Trigger when the user asks "which of these logos i
Alternatives in Data & AI
- Read Research For Nyquist Validation Data — cat "$phase_dir"/-RESEARCH.md 2>/dev/null node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" roadmap get-pha 38.5k ★
- Brief People Updater — Update people profiles in 05-knowledge/people/ with new information from brief data, meetings, or Slack 1k ★
- Stack Auditor — Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses th 801 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Screenshot Critic
Independent design critic that judges a UI from screenshots only, never code, history, or rationale. Returns t
Backend Engineer David
Use this agent when you need expert guidance on Rust systems programming, Tauri v2 desktop applications, audio
Maps Miner
Works Google Maps-type data for the target region — rating and review-count profiles, review-language mix, nei
Archive Crawler
Executes searches against ONE assigned archive, index or database and reports candidate hits. Spawned in paral
Filter Tuner
Looks at what the deterministic filter and the AI scoring kept or rejected, finds the rules that let bad offer
Module Developer
Use this agent when developing features inside a LaraDashboard module — writing controllers, services, models,
Related Skills
Decision Council
Claude skill: a council of independent perspectives (blind round, debate, and a synthesis that takes a stance)
Gauntlet Loop
Fast path for a throwaway proof of concept — set a named outside bar, run a builder against a separate blind c
Claude Code Game Builder
Claude Code skill: multi-agent build → capture → blind critic → fix loops that push a game toward a reference-