ohh
Chengkun Rao publishes a set of skills for AI agents working on deep learning research repositories, covering the full path from repository intake and README-driven reproduction to training runs and debugging. His skills direct an agent to read the repository first, identify the smallest documented inference or evaluation target, and record command, config, seed, log, and checkpoint evidence. The distinctive feature of his work is its conservatism: skills separate read-only analysis, bounded exploratory runs, and debug fixes so that patches are never mixed with diagnosis.
Rigorpilot Skills
11 skills · 486 stars · MIT
Ai Research Explore Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research c…
Ai Research Reproduction Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction.
Analyze Project Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories.
Env And Assets Bootstrap Rigor Setup skill for README-first deep learning repo reproduction.
Explore Code Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning r…
Explore Run Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning re…
Minimal Run And Audit Rigor Run skill for README-first deep learning repo reproduction.
Paper Context Resolver Rigor Paper Context helper for README-first deep learning repo reproduction.
Repo Intake And Plan Rigor Intake helper for README-first deep learning repo reproduction.
Run Train Rigor Train skill for deep learning research repositories.
Safe Debug Rigor Debug / Rigor Audit skill for deep learning research work.