Skip to content

KevinBian107/propel

Repository files navigation

Propel Logo

Propel

A structured constraint framework for Claude Code in research workflows.

Website | Documentation | Vibe Coding Articles

Propel Pipeline — Human-in-the-Loop Research Workflow with Four Modes

Why Propel?

Without structure, an unconstrained LLM produces the mean of its training data. Ask it to "implement RVQ" and you get a plausible-looking average — not the one matching your paper, your architecture, your constraints. The output compiles, but embeds wrong assumptions, silent numerical bugs, and design decisions made without asking.

The fix isn't better prompts — it's structured constraints. Propel enforces human-in-the-loop gates, domain-specific auditors, and investigation-first methodology so the output goes from "plausible average" to precisely what you need.

Core Principles

Principle Rule
Assistant, not agent Investigate and present — don't guess and act. Every claim traceable to evidence.
Evidence over agreement Be correct, not agreeable. Steel-man the counterargument before agreeing.
Context discipline Hallucination risk grows with context. Preserve state in living READMEs, clear proactively.
Critical self-reflection Question your own reasoning as hard as the user's.
Break logic loops Name circular reasoning, reframe, or bring new data. 3-strike limit.

Four Modes

Mode Active Gates When to Use
Researcher Gate 0, 1 Understanding the problem space — papers, code tracing, approaches
Engineer All (0–4) Full pipeline from investigation through implementation (default)
Debugger Gate 0, 1, 4 Root-cause analysis — classify bugs vs. design issues with evidence
Trainer Gate 4 (runtime) Launch training, monitor, fix CUDA/OOM/path errors

Switch anytime: /switch researcher, /switch engineer, /switch debugger, /switch trainer.

Installation

git clone https://github.com/KevinBian107/propel.git
cd propel && pip install -e .

cd /path/to/your/project
propel init

Then start Claude and run /intro to select a mode and set up your project. See the Getting Started guide for details.

Documentation

Full documentation is available on the Propel website:

  • Getting Started — Installation and first workflow
  • Core Principles — The five non-negotiable principles
  • Pipeline — Gates, questioners, and phase transitions
  • Modes — Researcher, Engineer, Debugger, Trainer
  • Skills — 17 specialized skills by workflow phase
  • Agents — 8 domain-specific auditors
  • Customization — Project-specific agents, skills, commands
  • Common Pitfalls — Known failure modes and anti-patterns

Acknowledgments

Propel combines ideas from: obra/superpowers, scott-yj-yang/new-prompt, Talmo's sleap-io, Sionic AI, brunoasm's claude skills, Weizhena's Deep-Research, and Context Engineering Template.

External plugins bridged by Propel skills: openai/codex-plugin-cc (via /c-codex), anthropics/claude-code code-review plugin (via /c-review).

Skills vendored directly: anthropics/skills — frontend-design (see source repo for LICENSE).

License

MIT — Built by Kaiwen Bian and Yuer Tang.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors