Design Evaluator — Design agent for Claude Code
Persistent evaluator on a design sprint team.
How to install Design Evaluator
Installs to ~/.claude/agents/phobologic-claude_code_helpers-design-evaluator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/phobologic/claude_code_helpers/HEAD/agents/design-evaluator.md -o ~/.claude/agents/phobologic-claude_code_helpers-design-evaluator.md Restart Claude Code, or start a new session, for it to be picked up.
What Design Evaluator does
name: design-evaluator description: Persistent evaluator on a design sprint team. Scores three designer proposals across three rounds against weighted criteria, issues shared briefs between rounds, and writes the final design specification synthesis after Round 3. model: opus effort: high
Design Evaluator
You are the evaluator on a design sprint team. You will score design proposals across three rounds and issue a shared brief after each round. You persist across all three rounds — y
Alternatives in Design
- Fidelity Check — Phase 4 per-round fidelity check for design-final.md: matches the final design against the step and track epis 432 ★
- Heuristic Evaluator — Use this agent to evaluate a design against established usability heuristics (Nielsen's 10) and conduct cognit 240 ★
- Experience Reviewer — Use when reviewing the experience dimension of a written plan (UX + DX) 98 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
UI Evaluator
Adversarial UI evaluator that tests live web applications via Playwright. Use only in projects with a running
Fix Reviewer
Fresh fix reviewer for the UI-Evaluator verify workflow. Spawn with the packet from uie packet --role fix-revi
Game Critic
Adversarial validator for game-design proposals. Finds counter-examples, known failure cases, and post-mortem
Severity Rater
Blind severity rater for UI-Evaluator. Spawn three or more, one per packet from uie packet --role severity-rat
Fec UI Checker
Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inc
UX Red Team
Hostile UX reviewer. Assumes the implementation is flawed. Finds friction, hierarchy issues, accessibility gap
Related Skills
Rate Cv
Claude Code skill that scores and critiques CVs against a weighted engineering-leadership rubric, with ATS and
Agentic QA Copilot
Automated call center QA analytics agent — scores every call against a weighted rubric (with emphasis on ident
Cw Evaluate
Score options against weighted criteria and recommend one. Structured decision-making with adversarial review.