Uxaudit L4 Judge — Development agent for Claude Code
L4-journey Judge for the uxaudit pipeline.
How to install Uxaudit L4 Judge
Installs to ~/.claude/agents/gotalab-uxaudit-uxaudit-l4-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/gotalab/uxaudit/HEAD/agents/uxaudit-l4-judge.md -o ~/.claude/agents/gotalab-uxaudit-uxaudit-l4-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Uxaudit L4 Judge does
name: uxaudit-l4-judge description: "L4-journey Judge for the uxaudit pipeline. Reads the per-journey capture directory (screenshots + steps.json + evaluation brief) and writes a strict pass/fail/unverifiable verdict with four-axis journey_evaluation to result.json. Has Read, Write, Glob — no Bash, no WebFetch — physically cannot drive a browser or curl the app. Invoked from Phase 04 Step 11 of the orchestrator playbook, one dispatch per L4 journey, batched in parallel." tools: Read, Write,
Alternatives in Development
- Penn — Journal Writer 296 ★
- PR Screenshotter — Produces real before/after PNG screenshots for a YAS branch's rendering changes and publishes them to the yas 241 ★
- Claude Bowser Agent — Browser automation agent 222 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Uxaudit L3 Judge
L3-vision Judge for the uxaudit pipeline. Reads ONE captured screenshot plus a check-specific prompt.md (and o
Keepr
Use this agent to evaluate PR review comments and classify them into actionable recommendations. keepr (keeper
Demo
Demo Agent that silently captures screenshots during a build and assembles them into a 60-second demo video us
Sonnet Verifier
Use proactively to run tests, builds, typechecks, linters, screenshots, and programmatic checks after any impl
V Pre Flight Runner
Runs /v pre-flight quality gates (TSC, PHPStan, lint, build, pest, vitest, audits) and writes PRE_FLIGHT_REPOR
CI Watcher
Watch PR checks for the current branch and report pass/fail with relevant links and concise next steps. Use wh
Related Skills
Creative Director Skill
AI creative director with recursive self-assessment: 20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER, Synec
Enso Test
Comprehensive live end-to-end test of the Enso platform. Tests infrastructure, backend, and frontend features
Reflex Cu
Computer-use MCP server for coding agents: local macOS, local Windows, or remote Windows over SSH, with a fast