Player Eval — Development agent for Claude Code
Screenshot evaluation agent.
How to install Player Eval
Installs to ~/.claude/agents/houseworthe-claude-royale-player-eval.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/houseworthe/claude-royale/HEAD/.claude/agents/player-eval.md -o ~/.claude/agents/houseworthe-claude-royale-player-eval.md Restart Claude Code, or start a new session, for it to be picked up.
What Player Eval does
name: player-eval description: Screenshot evaluation agent. Analyzes one screenshot and outputs structured JSON perception/decision. tools:
- Read model: haiku
Screenshot Evaluation Agent
**Input:** Screenshot path provided in prompt (e.g., "Evaluate: eval/screenshots/1.png")
**Output:** ONLY valid JSON. No markdown, no explanation, no extra text.
Instructions
- Read the screenshot file at the provided path
- Identify screen type (battle, home_menu, result, loading)
- Extr
Alternatives in Development
- Memory Extractor Agent — You extract perception changes from Claude Code session transcripts - the "aha moments" where understanding sh 3.6k ★
- Eval Engineer — GAIA evaluation framework specialist 1.5k ★
- Build And Screenshot — 컴포넌트 메타데이터 검증/빌드, 프로젝트 빌드, 프로덕션 서버 시작, 스크린샷 캡처를 순차적으로 수행한다 395 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Gregorian Decision
Specialist that runs a decision through the full With Love, Math framework and returns a structured verdict. I
Uxaudit L3 Judge
L3-vision Judge for the uxaudit pipeline. Reads ONE captured screenshot plus a check-specific prompt.md (and o
Skill Eval Reporter
Compares repeated paired execution results using blind A/B methodology and generates a skill effectiveness rep
Bully Evaluator
Evaluates a single bully semantic-evaluation payload against a diff and returns a structured violation list. I
Lit Scout
Literature evaluation specialist. Reviews PRE-READ paper subsets, extracts evidence claims with provenance (DO
Meta Auditor
God-mode engineering meta-auditor. Scans .claude/ + docs/ + workspace/src/, outputs structured observation rep
Related Skills
Skill Evolution
Self-improvement feedback loop for AI agent skills — analyzes past sessions, drafts structured improvement pro
Claude Skill Aso Appstore Screenshots
A Claude Code skill that generates high-converting App Store screenshots for your iOS app. It analyzes your co
Create Docs
by jerseycheese - Analyzes code structure and purpose to create comprehensive documentation detailing inputs/o