interpret-experiment
OfficialTurn experiment runs into grounded reports.
Education & Research#research reporting#automated analysis#mechanistic interpretability#experiment interpretation#causal abstraction#artifact grounding#replication comparison
Authorgoodfire-ai
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It prevents research results from being hard to summarize by automatically converting an experiment plan plus produced artifacts into a single, evidence-grounded report.
Core Features & Use Cases
- Plan-to-evidence scoring: Extracts objective, success criteria, and hypotheses from the session plan, then matches them to shipped and session-local analysis outputs.
- Artifact-aware interpretation: Discovers what actually ran from resolved configs and on-disk artifacts, including session-local methods and analyses, and records plan-vs-reality gaps.
- Optional paper comparison: When replication context is present, compares key metrics against the paper’s reported findings and annotates discrepancy categories.
- Figure embedding and structured output: Copies/symlinks curated figures into the session result folder and writes a consistent
result/REPORT.md, while logging issues separately.
Quick Start
Run the experiment with /run-experiment, then invoke interpret-experiment (or let it auto-run) to generate ${SESSION_DIR}/result/REPORT.md from the plan and artifacts.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: interpret-experiment Download link: https://github.com/goodfire-ai/causalab/archive/main.zip#interpret-experiment Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.