exp-pilot-run
CommunityRun safe pilot experiments with manual approval.
Education & Research#research automation#remote execution#human approval#pilot experiment#training evaluation#GPU orchestration#metrics reporting
Authorduany049
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It helps you execute a pilot experiment from a spec reliably, producing code and diagnostic results without accidentally changing the wiki or making automated pass/fail judgments.
Core Features & Use Cases
- Pilot-spec driven execution: Reads
experiments/pilot/{slug}.yaml(pilot_spec) to generate and run a short diagnostic experiment for a given idea slug. - Deterministic pilot artifacts: Writes pilot code to
experiments/pilot/code/{slug}/and saves raw JSON results (results/seed_{N}.json) plus apilot.log. - Human-in-the-loop safety gate: Requires user confirmation and manual inspection of code/config before deployment/run; does not create graph edges and does not modify wiki pages.
Quick Start
Ask the AI to run a pilot for idea slug "my-idea" in local mode: exp-pilot-run my-idea --env local.
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: exp-pilot-run Download link: https://github.com/duany049/multi-skill-orchestration/archive/main.zip#exp-pilot-run 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.