Overview
experiment-bridge is an open-source data skill for Claude Code and compatible agents, published by wanshuiyin. Its author describes it as: “Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge"…”. The project has 15k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/experiment-bridge`.
What experiment-bridge does
Implement and deploy experiments from plan: **$ARGUMENTS**
Best for
What’s inside
The SKILL.md for experiment-bridge is organised into these sections:
- Overview
- Constants
- Inputs
- Workflow
- Phase 1: Parse the Experiment Plan
- Phase 2: Implement Experiment Code
- Phase 2.5: Cross-Model Code Review (when CODEREVIEW = true)
- Phase 3: Sanity Check (if SANITYFIRST = true)
- Phase 4: Deploy Full Experiments
- Phase 5: Collect Initial Results
- Phase 5.5: Write Compact Log (when COMPACT = true)
- Phase 5.6: Auto Ablation Planning
Installation
Add experiment-bridge to your agent with:
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/experiment-bridgeReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — declared in the repository topics
- Codex — declared in the repository topics
License
experiment-bridge is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in wanshuiyin/Auto-claude-code-research-in-sleep, an established project with 14,858 GitHub stars
- Works with Claude Code, Codex
- Actively maintained — repository updated in the last 90 days
Author
Topics
Frequently asked questions
- What does experiment-bridge do?
- Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.
- How do I install experiment-bridge?
- Run git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/experiment-bridge in your agent, then reload your skills. Review the source at https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep before installing.
- Is experiment-bridge free to use?
- Yes. experiment-bridge is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does experiment-bridge work with?
- experiment-bridge lists Claude Code and Codex — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does experiment-bridge come from?
- experiment-bridge ships inside wanshuiyin/Auto-claude-code-research-in-sleep, a repository that contains 41 catalogued skills in total. The repository's 14,858 GitHub stars apply to that whole collection, not to this skill on its own.