Menu
Start a new experiment with hypothesis and success criteria
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Assay an experiment — deep analysis of results with cross-run comparison
Conjure a experimentalist agent — initialize and launch a new autonomous experiment
Distill insights from a experimentalist agent's session histories — zero API calls
Steer a experimentalist agent — review progress and redirect a running experiment
Check connector status — show which integrations are connected and configured
Sign up for email notifications — experiment reports, paper suggestions, weekly digest
| name | experiment |
| description | Start a new experiment with hypothesis and success criteria |
| disable-model-invocation | true |
Before running the next experiment, document your plan:
After the experiment completes, append a line to .distillate/runs.jsonl:
{"$schema":"distillate/run/v1", "id":"run_NNN", "timestamp":"ISO8601", "status":"keep|discard|crash", "hypothesis":"...", "changes":"...", "hyperparameters":{...}, "results":{...}, "reasoning":"..."}
Set status to keep if results improved, discard if not, or crash on failure.
Include reasoning to explain your decision.