/safe-debug
Run Rigor Debug on a research repository failure before patching.
$ npx -y skills add lllllllama/rigorpilot-skills --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/safe-debug
Context preview
What this command does when you run it.
Run Rigor Debug on a research repository failure before patching.
Command definition
safe-debug.mddescription: Run Rigor Debug on a research repository failure before patching. argument-hint: [traceback, failing command, or debug focus]
Read and follow @skills/safe-debug/SKILL.md.
Use the current conversation context plus `$ARGUMENTS` as the failure report. If there is still no actionable traceback, command output, or failure description, ask for the missing failure context instead of guessing.
Stay in Rigor Debug:
- diagnose before patching
- prefer the smallest safe fix
- do not treat this as exploratory work
- preserve scientific meaning and trusted-lane semantics
Additional user context: $ARGUMENTS
Research-first Agent Skills for Deep Learning Experiments. Main idea: RigorPilot keeps AI-assisted deep learning research grounded in comparability, reproducible evidence, and auditable changes while an agent reproduces, improves, or explores a research
Repo: lllllllama/rigorpilot-skills
Other commands on rigorpilot-skills.
- /ai-research-explore
Run Rigor Explore on top of current_research using the current compatible slug.
Open command - /ai-research-reproduction
Run Rigor Reproduce on this repository using the current compatible slug.
Open command - /analyze-project
Run Rigor Analyze on this repository using the current compatible slug.
Open command