Safe Debug (RigorPilot)
Conservative diagnosis for deep-learning failures — tracebacks, CUDA OOM, NaN loss, checkpoint issues — diagnose first, then propose the smallest fix with explicit approval before any mutation
- What
- Conservative diagnosis for deep-learning failures — tracebacks, CUDA OOM, NaN loss, checkpoint issues — diagnose first, then propose the smallest fix with explicit approval before any mutation
- Cost
- Free
- Needs
- none — a concrete failure to diagnose (traceback, terminal error, CUDA OOM, NaN loss, checkpoint issue) is what you bring at use time; the skill diagnoses first and requires explicit approval before any patch.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — the RigorPilot "Rigor Debug / Rigor Audit" skill for deep-learning research work. It applies when you paste a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom or training failure and want conservative diagnosis before any patching. The discipline is diagnose-first: no repository modification by default; if a patch is needed, the smallest fix is proposed and explicit approval is required first; savepoint or branch creation is escalated before medium- or high-risk changes. And a hard conceptual line is drawn: a debug fix is not automatically a research contribution — if it changes experiment meaning or comparability, the skill says so explicitly. Outputs are `debug_outputs/DIAGNOSIS.md`, `debug_outputs/PATCH_PLAN.md` and `debug_outputs/status.json`. Not for broad refactoring, speculative adaptation, automatic exploratory patching, or general repository familiarization. By @lllllllama, listed here with credit to its creator. Honest caveats: diagnosis needs concrete failure evidence — a vague "it doesn't work" gets you little; human approval is a hard gate, so don't expect autonomous repair; a flagged root cause remains a diagnosis until a run confirms it. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Safe Debug is a free RigorPilot skill for conservative diagnosis of deep-learning failures, including tracebacks, CUDA out-of-memory errors, NaN loss, and checkpoint problems. Its diagnose-first discipline makes no repository modification by default, proposes the smallest fix with explicit approval before any patch, and escalates savepoint or branch creation before medium- or high-risk changes.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit fb3ccdfStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: none — a concrete failure to diagnose (traceback, terminal error, CUDA OOM, NaN loss, checkpoint issue) is what you bring at use time; the skill diagnoses first and requires explicit approval before any patch. Install "Safe Debug (RigorPilot)" for me. The RigorPilot conservative debugging skill for deep-learning failures: diagnosis before any patching, smallest-fix proposals, explicit human approval required, and debug fixes clearly separated from research contributions. Repository: https://raw.githubusercontent.com/lllllllama/rigorpilot-skills/fb3ccdf5aa64b1fa5b1d0463e666a8bc8bc26e01/skills/safe-debug/SKILL.md Pinned version: install the code at commit fb3ccdf5aa64b1fa5b1d0463e666a8bc8bc26e01 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "rigorpilot-safe-debug". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself. GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- fb3ccdf · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: files.pythonhosted.org, pypi.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.