Save, version, and evolve metamaterial design hypotheses over time. Use when you need to persist hypothesis records with full provenance for iterative design refinement.
Save hypotheses with full provenance and manage their lifecycle through iterative refinement.
When this skill is invoked:
Save artifacts from the current pipeline run:
cd D:/Claude && python -c "
from target_to_hypothesis.skills.versioning import save_hypotheses, save_target, save_papers, save_summary
# save_target(target, run_id)
# save_papers(paper_candidates, run_id)
# save_summary(synthesis, run_id, 'synthesis')
# save_hypotheses(ranked, target, run_id, evidence_summary={...})
"
Artifact structure saved to D:/Claude/target_to_hypothesis/artifacts/:
artifacts/
├── targets/ # Normalized target JSON
├── papers/ # Retrieved paper metadata
├── summaries/ # Synthesis and evidence reports
└── hypotheses/ # Versioned hypothesis records
└── {run_id}/
├── v001.json # Version 1 (full hypothesis set)
├── v001.md # Human-readable markdown
└── log.jsonl # Append-only status log
Hypothesis lifecycle: proposed → tested → revised → rejected | accepted
tested with simulation resultsrevised and modify parametersacceptedTo update a hypothesis status:
cd D:/Claude && python -c "
from target_to_hypothesis.skills.versioning import update_hypothesis_status
update_hypothesis_status(run_id, hypothesis_id, 'tested', notes='Absorption 87% at 10 GHz, need optimization')
"
To load previous hypotheses for revision:
cd D:/Claude && python -c "
from target_to_hypothesis.skills.versioning import load_latest_hypotheses
record = load_latest_hypotheses(run_id)
print(record.ranked_hypotheses.recommendation)
"
D:/Claude/target_to_hypothesis/skills/versioning.py
D:/Claude/target_to_hypothesis/models/hypothesis.py (HypothesisVersionRecord, HypothesisStatus)