Hypothesis Gen — Data & AI agent for Claude Code
Delegate when generating candidate research hypotheses for a topic — produces ranked, physics-grounded, falsifiable hypotheses with explicit AI-generated labels.
How to install Hypothesis Gen
Installs to ~/.claude/agents/taewooopark-maglab-hypothesis-gen.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/TaewoooPark/MagLab/HEAD/agents/hypothesis-gen.md -o ~/.claude/agents/taewooopark-maglab-hypothesis-gen.md Restart Claude Code, or start a new session, for it to be picked up.
What Hypothesis Gen does
name: hypothesis-gen description: Delegate when generating candidate research hypotheses for a topic — produces ranked, physics-grounded, falsifiable hypotheses with explicit AI-generated labels. Backs the `maglab hypotheses` command. tools: [physics_check, physics_compute, material_lookup, provenance_query] model: sonnet max_turns: 10 context: isolated
You are the hypothesis-generation subagent of MagLab (D1, §5.10).
① Single objective
Generate candidate research hypotheses for a
Alternatives in Data & AI
- Credential Hunter — Autonomous credential-attack pipeline runner 4.5k ★
- Engagement Hitlist — Generate ranked, copy-paste-ready engagement actions from pipeline data 108 ★
- UI Behavior Reviewer — Compares prototype vs live UI behavior - state mismatches from the capture fingerprints, copy, labels, compone 61 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Prospector
Generates candidate data center sites from first principles across a region by constraint intersection, then w
Experiment Interpreter
Use this agent to interpret ML experiment results from log files. It extracts numerical results, generates dat
Hypothesis Generator
Research hypothesis generation specialist for creating testable hypotheses, experimental designs, and research
Experiment Verifier
Use this agent to verify ML experiment interpretations against actual log data. It cross-checks every numerica
SEO Fixer Writer
The ONLY agent allowed to write files. Used exclusively by the fix skill (the /claude-seo-ai:fix command) AFTE
Bd Lit Scan
Scans literature in bulk, extracts bibliographic data and updates the INDEX. Lists PDFs, extracts title, autho
Related Skills
Bug Race
Use when a bug has already survived at least one debugging attempt and you have 2-3 genuinely distinct root-ca
Hypothesis Agent
Generate high-value, non-obvious attack hypotheses from recon data during bug bounty hunting. Use this skill w
Hypothesis
Generate research hypotheses and experimental designs based on data patterns