mcpField
S
safe-debug

safe-debug

github.com/lllllllamaTesting & quality486339.5k installsUpdated 5w ago
Repository

About safe-debug

safe-debug is the Rigor debug and audit skill, used to diagnose a concrete traceback, terminal error or training or inference failure. It narrows the root cause and proposes minimal patches, and it requires explicit human approval before any repository code is changed.

Key features

  1. 01Diagnosis from tracebacks and error symptoms
  2. 02Root-cause narrowing before any changes
  3. 03Minimal patch proposals
  4. 04Explicit approval required before mutation
  5. 05Notes whether a fix changes experiment meaning

Use cases

  1. 01Diagnosing errors raised during model training
  2. 02Investigating failed inference runs
  3. 03Producing a reviewed fix plan before editing repository code

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/lllllllama/rigorpilot-skills --skill safe-debug

After installing, type/safe-debugin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
debug-policy.md
scripts/
safe_debug.py

Details

From the project README

safe-debug

Use this as the Rigor Debug / Rigor Audit skill. The installed slug remains safe-debug for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide conservative diagnosis without blocking the model from finding the local root cause.

When to apply

  • The user provides a traceback, terminal error, or concrete training or inference failure symptom.
  • The user wants diagnosis, root-cause narrowing, and minimal patch suggestions before code is changed.
  • The user wants a safe debug flow with explicit human approval before mutation.

When not to apply

  • When the user wants a broad repository walkthrough without an active failure.
  • When the task is speculative experimentation or code adaptation.
  • When the user is asking for a large refactor or readability rewrite.

Clear boundaries

  • Diagnose first.
  • Do not modify repository code by default.
  • If a patch is needed, propose the smallest fix and require explicit approval first.
  • Escalate savepoint or branch creation before medium-risk or high-risk changes.
  • A debug fix is not automatically a research contribution; if it changes experiment meaning or comparability, say so explicitly.

Output expectations

  • debug_outputs/DIAGNOSIS.md
  • debug_outputs/PATCH_PLAN.md
  • debug_outputs/status.json

Notes

Use references/debug-policy.md, ../ai-research-reproduction/references/research-rigor-principles.md, and the shared ../ai-research-reproduction/references/research-pitfall-checklist.md.

Comments

Markdown supported