Fix Reviewer — Design agent for Claude Code
Fresh fix reviewer for the UI-Evaluator verify workflow.
How to install Fix Reviewer
Installs to ~/.claude/agents/horace-maxwell-ui-evaluator-fix-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Horace-Maxwell/UI-Evaluator/HEAD/agents/fix-reviewer.md -o ~/.claude/agents/horace-maxwell-ui-evaluator-fix-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Fix Reviewer does
name: fix-reviewer description: "Fresh fix reviewer for the UI-Evaluator verify workflow. Spawn with the packet from `uie packet --role fix-reviewer`; from before-and-after evidence only it scores each claimed fix confirmed_fixed, partially_fixed or not_fixed and names up to three regressions." tools: Read, Glob, Grep, Bash, Write model: inherit
Alternatives in Design
- UI Verify — 2.1k ★
- Role Design Author — Generates multi-file role analysis for a brainstorm session — analysis.md index + per-feature files + optional 530 ★
- Heuristic Evaluator — Use this agent to evaluate a design against established usability heuristics (Nielsen's 10) and conduct cognit 240 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Direction Designer
Direction designer for the UI-Evaluator direct workflow. Spawn with the packet from uie packet --role directio
Severity Rater
Blind severity rater for UI-Evaluator. Spawn three or more, one per packet from uie packet --role severity-rat
Fix Builder
Fresh session that revises a Blender asset after a critic FAIL. Use only when gauntlet/evidence/ / / contains
Design Evaluator
Persistent evaluator on a design sprint team. Scores three designer proposals across three rounds against weig
UI Evaluator
Adversarial UI evaluator that tests live web applications via Playwright. Use only in projects with a running
Fixme Browser Verify
Browser verification after code changes. Loads dev server, checks bug is fixed, verifies no visual regressions
Related Skills
Identity Orchestrator
Load orchestrator role identity (required on fresh session and after compaction)
Debrief Prep
Build a debrief packet for one candidate from scorecards (sample data, a paste, an export, or your connected G
Eval Swarm
Fan every eval- evaluator agent across slices of the monorepo as a parallel swarm via the eval-swarm workflow