Noemeo Researcher — Development agent for Claude Code
Plans, runs and writes up studies in Noemeo repos -- falsifiable questions, prior-work checks, public benchmarks with their terms, controlled experiments with repeated runs and validated graders, immu.
How to install Noemeo Researcher
Installs to ~/.claude/agents/ilya-at-noemeo-noemeo-roles-noemeo-researcher.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ilya-at-noemeo/noemeo-roles/HEAD/agents/noemeo-researcher.md -o ~/.claude/agents/ilya-at-noemeo-noemeo-roles-noemeo-researcher.md Restart Claude Code, or start a new session, for it to be picked up.
What Noemeo Researcher does
name: noemeo-researcher description: Plans, runs and writes up studies in Noemeo repos -- falsifiable questions, prior-work checks, public benchmarks with their terms, controlled experiments with repeated runs and validated graders, immutable raw data, research notes and publication packages -- as Noemeo's research role, grounded in its foundation and decision logs. Use for self-contained research work worth delegating, e.g. "measure whether this prompt change reduces misreadings on a public
Alternatives in Development
- Sales Automator — Draft cold emails, follow-ups, and proposal templates 2.8k ★
- Gpui Researcher — Researches and validates GPUI usage patterns, APIs, and conventions 2.2k ★
- Eval Engineer — GAIA evaluation framework specialist 1.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Perf Theory Tester
Execute controlled perf experiments, one change at a time, with rollback between runs.
Selfish Evolution
Run retrospectives and controlled experiments that improve the system while preserving the human’s authority o
Evaluation Orchestrator
Use for coordinating evaluation experiments, managing experiment execution, and overseeing evaluation workflow
Fk Librarian
Finds the right API pattern or prior evidence - Triton/TileLang/CuTe/CUDA docs, the starter templates in fastk
Harvest Worker
Grounded recon for ONE audience segment — gathers real, signal-backed user queries and returns validated Quest
Sccm
Domain assistant for SCCM/ConfigMgr work. Use for SCCM technical questions ("how do I do X in ConfigMgr", "can
Related Skills
Foundation Skills
Open-source agent skills for professional feasibility studies: market sizing, competitor benchmarks, pricing,
Contract Review Skill
Review legal contracts for risks, extract key terms, and suggest redlines. Built on the CUAD dataset (41 risk
Jev Cold Start Prior
Can a TypeSafe Jev prior read from a README on day one predict which new agent-skill repos gain stars? Zero-sh