Evaluation Matrix Builder — Data & AI agent for Claude Code
Builds a complete evaluation matrix (KEQs, sub-questions, ToC links, judgement criteria, indicators, data sources, methods, analysis, evidence strength) from programme documents such as a theory of ch.
How to install Evaluation Matrix Builder
Installs to ~/.claude/agents/dutchy313-evaluation-question-design-skill-evaluation-matrix-builder.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/dutchy313/evaluation-question-design-skill/HEAD/agents/evaluation-matrix-builder.md -o ~/.claude/agents/dutchy313-evaluation-question-design-skill-evaluation-matrix-builder.md Restart Claude Code, or start a new session, for it to be picked up.
What Evaluation Matrix Builder does
name: evaluation-matrix-builder description: Builds a complete evaluation matrix (KEQs, sub-questions, ToC links, judgement criteria, indicators, data sources, methods, analysis, evidence strength) from programme documents such as a theory of change, logframe, results framework, ToR or project document. Use when the user asks for an evaluation matrix, design matrix or inception-report evaluation framework. tools: Read, Grep, Glob, Write, Skill model: inherit
You are an evaluation design
Alternatives in Data & AI
- PostgreSQL Pglite Pro — Role: Senior PostgreSQL and PgLite Engineer specializing in robust database architecture, perfor 1.5k ★
- Cartographer — Claude Code plugin that maps and documents codebases of any size using parallel AI subagents 520 ★
- Comprehension Review — De-warmed cold comprehension-and-structure gate for design.md and track files: reads only the document, never 432 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Question Forger
Generates evaluation questions with gold answers and gold evidence from real graph paths and from the syntheti
Theme Evidence Collector
Builds an evidence pack for one assigned theme, collecting real data on demand, supply, capex, policy, earning
Social Scientist
Orchestrates evidence disciplined social science research workflows, selects the minimum sufficient skills, pr
Question Architect
Compiles a published playbook position into a per-clause question tree (format, AI guidance, branching sub-que
Gsd Domain Researcher
Researches the business domain and real-world application context of the AI system being built. Surfaces domai
Ferrox Domain Researcher
Researches the business domain and real-world application context of the AI system being built. Surfaces domai
Related Skills
Toc
Theory of Constraints Thinking Processes — full analysis pipeline or individual tool routing
Intent Driven Development
Turn an ambiguous or high-impact change into scoped, verifiable acceptance criteria (observable AC-NNN, explic
Open Science Skills
Agentic skills for Claude Code and Codex, built from published social-science methods sources. Covers experime