with one click
assay
Assay an experiment — deep analysis of results with cross-run comparison
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.
Menu
Assay an experiment — deep analysis of results with cross-run comparison
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
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
Brew — sync papers, process highlights, refresh the library
| name | assay |
| description | Assay an experiment — deep analysis of results with cross-run comparison |
Test the purity of what the experimentalist agent produced. Deep analysis of an experiment's results.
The user provides an experiment name or project ID.
mcp__distillate__scan_project to ensure we have the most recent runsmcp__distillate__get_project_details for complete run history with metricsmcp__distillate__compare_runs to understand what changed between breakthrough runs~/.claude/projects/*<name>*/*.jsonl) to understand why the agent made its choicesmcp__distillate__suggest_from_literature to compare with published resultsmcp__distillate__get_experiment_notebook for the full record