Eval Guidance Recipe — Data & AI agent for Claude Code
Eval arm guidance-recipe (Q8 — the DERIVED FIGURES recipe, returned by a no-argument guidance call).
How to install Eval Guidance Recipe
Installs to ~/.claude/agents/davegold-mcp-metadata-demo-eval-guidance-recipe.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/DaveGold/mcp-metadata-demo/HEAD/.claude/agents/eval-guidance-recipe.md -o ~/.claude/agents/davegold-mcp-metadata-demo-eval-guidance-recipe.md Restart Claude Code, or start a new session, for it to be picked up.
What Eval Guidance Recipe does
name: eval-guidance-recipe description: Eval arm guidance-recipe (Q8 — the DERIVED FIGURES recipe, returned by a no-argument guidance call). Answers one building-data question using ONLY the eval-g-recipe MCP server. Not for general use — spawned by the run-eval skill. tools: mcp__eval-g-recipe__get_building_profile, mcp__eval-g-recipe__get_weather_context, mcp__eval-g-recipe__render_chart, mcp__eval-g-recipe__render_table, mcp__eval-g-recipe__render_map, mcp__eval-g-recipe__get_tool_call_lo
Alternatives in Data & AI
- Gaia Agent Builder — GAIA agent creation specialist 1.5k ★
- AI Architect — Specializes in architecting AI-powered applications on Vercel — choosing between AI SDK patterns, configuring 263 ★
- General Backend Developer — Use this agent proactively when you need to design, implement, or optimize backend API systems, including REST 248 ★
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 Words Recipe
Eval arm words-recipe (Q1b — the DERIVED FIGURES recipe, shipped by one of two channels). Answers one building
MCP Integrator
Decides what tool or data access a task needs and how to wire it via MCP, preferring an existing server over a
Claims DB Analyst
Answers questions about the live Contoso Claims MySQL database using the claims MCP server's tools — claim cou
Read Only Explorer
Maps how code actually works — call paths, call sites, data flow, existing patterns, ownership boundaries, and
AI Output Reviewer
Read-only reviewer for AI/LLM integration in the forgeward gate. Fires ONLY when the diff adds or modifies a c
Related Skills
AI Usage MCP
A local-first MCP server that answers, from real data on your machine: How many tokens have I used, from which
Weather MCP
Free, open-source MCP server giving AI assistants 17 weather tools — a one-call weather summary plus forecasts
Pi Codegraph
Pi-agent wrapper around codebase-memory-mcp: derived code knowledge (call graphs, blast radius) over a harness