Eval Best V1 — Data & AI agent for Claude Code
Eval arm best-v1 (best as measured in Q19, before its app tools were rebuilt; Q22).
How to install Eval Best V1
Installs to ~/.claude/agents/davegold-mcp-metadata-demo-eval-best-v1.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/DaveGold/mcp-metadata-demo/HEAD/.claude/agents/eval-best-v1.md -o ~/.claude/agents/davegold-mcp-metadata-demo-eval-best-v1.md Restart Claude Code, or start a new session, for it to be picked up.
What Eval Best V1 does
name: eval-best-v1 description: Eval arm best-v1 (best as measured in Q19, before its app tools were rebuilt; Q22). Answers one building-data question using ONLY the eval-best-v1 MCP server. Not for general use — spawned by the run-eval skill. tools: mcp__eval-best-v1__get_building_profile, mcp__eval-best-v1__get_weather_context, mcp__eval-best-v1__render_chart, mcp__eval-best-v1__render_table, mcp__eval-best-v1__render_map, mcp__eval-best-v1__get_tool_call_log
You are answering a singl
Alternatives in Data & AI
- Gaia Agent Builder — GAIA agent creation specialist 1.5k ★
- General Backend Developer — Use this agent proactively when you need to design, implement, or optimize backend API systems, including REST 248 ★
- Agentic Auditor — PYA specialist spawned by the /pya orchestrator 240 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Eval Best
Eval arm best (the reference implementation built with the rich-domain-mcp-server skill; Q19, app tools rebuil
Eval Best No Type Rules
Eval arm best-no-type-rules (best without render_chart's per-type rules; Q23 arm C). Answers one building-data
Opus Answer
A simple question-answering agent that responds naturally like a standard LLM. No special research context, no
Data Viz Designer
Desk Studio's Data Viz Designer. Turns a question and data into a chart that answers it in two seconds: the ri
Question Forger
Generates evaluation questions with gold answers and gold evidence from real graph paths and from the syntheti
ML Reviewer
Machine-learning expert for the code-review panel. Spawned when the diff touches ML frameworks (torch, tensorf
Related Skills
Fulfillment Ops Agent
Claude-powered ops agent and MCP server for grocery pickup: answers manager questions over PostgreSQL and draf
Ytswarm
Bulk YouTube transcripts → AI agent swarm. Ask any YouTube channel a question: one AI agent reads every video
Evolving Memory
[MOVED → evolving-agents/packages/memory] Cognitive Trajectory Engine. Its dual-embedding resolver was rebuilt
