Eval Words Recipe — Data & AI agent for Claude Code
Eval arm words-recipe (Q1b — the DERIVED FIGURES recipe, shipped by one of two channels).
How to install Eval Words Recipe
Installs to ~/.claude/agents/davegold-mcp-metadata-demo-eval-words-recipe.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/DaveGold/mcp-metadata-demo/HEAD/.claude/agents/eval-words-recipe.md -o ~/.claude/agents/davegold-mcp-metadata-demo-eval-words-recipe.md Restart Claude Code, or start a new session, for it to be picked up.
What Eval Words Recipe does
name: eval-words-recipe description: Eval arm words-recipe (Q1b — the DERIVED FIGURES recipe, shipped by one of two channels). Answers one building-data question using ONLY the eval-words-recipe MCP server. Not for general use — spawned by the run-eval skill. tools: mcp__eval-words-recipe__get_building_profile, mcp__eval-words-recipe__get_weather_context, mcp__eval-words-recipe__render_chart, mcp__eval-words-recipe__render_table, mcp__eval-words-recipe__render_map, mcp__eval-words-recipe__ge
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 ★
- AI Eval Engineer — Builds and maintains the eval pipeline for ai-system / agent-product archetypes 83 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Eval Inline Recipe
Eval arm inline-recipe (Q1b — the DERIVED FIGURES recipe, shipped by one of two channels). Answers one buildin
Eval Guidance Recipe
Eval arm guidance-recipe (Q8 — the DERIVED FIGURES recipe, returned by a no-argument guidance call). Answers o
Opus Answer
A simple question-answering agent that responds naturally like a standard LLM. No special research context, no
Question Forger
Generates evaluation questions with gold answers and gold evidence from real graph paths and from the syntheti
Reconciler
Close open tasks that are already done, by matching them against evidence across ALL channels (Gmail sent/inbo
Reviewer Compatibility
Compatibility specialist reviewer. Focuses on breaking changes to code already shipped in the default branch:
Related Skills
Think Issue Position Argument Mapping
Turn a tangled multi-question deliberation or transcript into an inspectable typed map by chaining shipped mov
AI Powered Devloper Platform For Databricks
Just shipped a full-stack AI developer platform for Databricks 🚀 → Claude agent with live SSE streaming + too
Kimi CLI Agent
Answers one council question as plain text, with no tool access.