Ut Refactor Review
intel/torch-xpu-ops
Review PyTorch upstream unit-test (UT) PRs that enable Intel GPU (XPU) on existing tests.
Rigor Debug / Rigor Audit skill for deep learning research work.
Install Safe Debug
$ npx skills add lllllllama/RigorPilot-Skills --skill safe-debug -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lllllllama/RigorPilot-Skills safe-debug --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/lllllllama/RigorPilot-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/safe-debug .claude/skills/safe-debug && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "safe-debug" agent skill from https://github.com/lllllllama/RigorPilot-Skills/tree/main/skills/safe-debug into .claude/skills/safe-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safe-debug", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/lllllllama/RigorPilot-Skills/tree/main/skills/safe-debugType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add lllllllama/RigorPilot-Skills --skill safe-debug -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lllllllama/RigorPilot-Skills safe-debug --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lllllllama/RigorPilot-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/safe-debug .agents/skills/safe-debug && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "safe-debug" agent skill from https://github.com/lllllllama/RigorPilot-Skills/tree/main/skills/safe-debug into .agents/skills/safe-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safe-debug", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lllllllama/RigorPilot-Skills --skill safe-debug -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lllllllama/RigorPilot-Skills safe-debug --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lllllllama/RigorPilot-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/safe-debug .cursor/skills/safe-debug && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "safe-debug" agent skill from https://github.com/lllllllama/RigorPilot-Skills/tree/main/skills/safe-debug into .cursor/skills/safe-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safe-debug", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/lllllllama/RigorPilot-Skills.git --path skills/safe-debug--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add lllllllama/RigorPilot-Skills --skill safe-debug -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lllllllama/RigorPilot-Skills safe-debug --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lllllllama/RigorPilot-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/safe-debug .gemini/skills/safe-debug && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "safe-debug" agent skill from https://github.com/lllllllama/RigorPilot-Skills/tree/main/skills/safe-debug into .gemini/skills/safe-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safe-debug", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lllllllama/RigorPilot-Skills safe-debugInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lllllllama/RigorPilot-Skills --skill safe-debug -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lllllllama/RigorPilot-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/safe-debug .github/skills/safe-debug && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "safe-debug" agent skill from https://github.com/lllllllama/RigorPilot-Skills/tree/main/skills/safe-debug into .github/skills/safe-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safe-debug", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lllllllama/RigorPilot-Skills --skill safe-debug -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lllllllama/RigorPilot-Skills safe-debug --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lllllllama/RigorPilot-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/safe-debug .opencode/skills/safe-debug && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "safe-debug" agent skill from https://github.com/lllllllama/RigorPilot-Skills/tree/main/skills/safe-debug into .opencode/skills/safe-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safe-debug", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
safe-debug- GitHub stars
- 497
- Used in
- 1 other repo
- Token cost
- ~522 tokens
- SKILL.md length
- 188 words
- Files
- 4 (incl. scripts, references)
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
Rigor Debug / Rigor Audit skill for deep learning research work.
- The user pastes a traceback
- SKILL.md covers When to apply, When not to apply, Clear boundaries and Output expectations, plus 1 more section
- Runs Python scripts from its folder
- Checkpoint load failure
What it does
Safe Debug is an agent skill from lllllllama/RigorPilot-Skills. Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research contributions. Do not use for broad refactoring, speculative adaptation, automatic exploratory patching, or general repository familiarization.
Its SKILL.md is about 520 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/debug-policy.md` and `scripts/safe_debug.py`).
It sits in Development, covering Deep learning and Refactoring. It works with CUDA. The repository describes itself as: README-first research reproduction skills with bounded execution, auditable evidence, and byte-preserving README annotations. The licence is MIT.
When your agent uses it
- The user pastes a traceback
- Checkpoint load failure
- NaN loss symptom
- Training failure and wants conservative diagnosis before any patching
Example prompts
- “/safe-debug”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit fb3ccdf. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Safe Debug loads about 522 tokens when it runs, and up to ~650 if it reads all its reference files. Until then it costs about 116 tokens; SKILL.md has 188 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from lllllllama/RigorPilot-Skills at commit fb3ccdf, republished under its MIT licence (© lllllllama). 188 words, ~522 tokens.
Download SKILL.mdSave it as
.claude/skills/safe-debug/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- safe-debug
- description
- Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research contributions. Do not use for broad refactoring, speculative adaptation, automatic exploratory patching, or general repository familiarization.
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.mddebug_outputs/PATCH_PLAN.mddebug_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.
© lllllllama, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (scripts, references) in skills/safe-debug of lllllllama/RigorPilot-Skills.
- SKILL.md
- agents/openai.yaml
- references/debug-policy.md
- scripts/safe_debug.py
Open the folder on GitHubat commit fb3ccdf
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in lllllllama/RigorPilot-Skills, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Safe Debug next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Safe Debug this skilllllllllama/RigorPilot-Skills | 497 | 1 repos | ~522 | Automated safety check: Pass | MIT | |
| Ut Refactor Reviewintel/torch-xpu-ops | 115 | — | ~917 | Automated safety check: Pass | Apache-2.0 | |
| Aoti Debugpytorch/pytorch | 104k | 1 repos | ~1.7k | Automated safety check: Pass | Custom licence | |
| The Art of Debuggingstas00/the-art-of-debugging | 1.7k | — | ~6.1k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| ExecuTorch Build Guidepytorch/executorch | 5.1k | — | ~2.3k | Automated safety check: Notes | Custom licence | |
| Veomni DebugByteDance-Seed/VeOmni | 2.2k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Aoti Debug
pytorch/pytorch
Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.
The Art of Debugging
stas00/the-art-of-debugging
Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.
ExecuTorch Build Guide
pytorch/executorch
Builds ExecuTorch from source: the Python package, C++ runtime, model runners, Android and iOS cross-compilation and backend-specific builds, with environment checks.
Veomni Debug
ByteDance-Seed/VeOmni
A skill your agent uses for ANY bug, error, crash, wrong output, loss divergence, gradient explosion, test failure, CUDA error, distributed training hang, checkpoint load failure, or unexpected…
3dgs Code Reviewer
jaccen/Awesome-Gaussian-Skills
Review 3DGS implementation code for correctness, performance bugs, and best practices.
More from lllllllama/RigorPilot-Skills
All 11 skills in this repoAI Research Reproduction
lllllllama/RigorPilot-Skills
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction.
Explore Run
lllllllama/RigorPilot-Skills
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories.
Minimal Run And Audit
lllllllama/RigorPilot-Skills
Rigor Run skill for README-first deep learning repo reproduction.
Run Train
lllllllama/RigorPilot-Skills
Rigor Train skill for deep learning research repositories. An agent skill from lllllllama/RigorPilot-Skills.
AI Research Explore
lllllllama/RigorPilot-Skills
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates.
Analyze Project
lllllllama/RigorPilot-Skills
Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories.
Related
Works with
Categories
Questions about Safe Debug
What does Safe Debug do?
Rigor Debug / Rigor Audit skill for deep learning research work. Safe Debug is an agent skill from lllllllama/RigorPilot-Skills. Rigor Debug / Rigor Audit skill for deep learning research work.
When should I use Safe Debug?
Safe Debug fits situations like: the user pastes a traceback; checkpoint load failure; naN loss symptom; training failure and wants conservative diagnosis before any patching.
How do I install Safe Debug in Claude Code?
Run `npx skills add lllllllama/RigorPilot-Skills --skill safe-debug -a claude-code`. Or copy the skill folder (skills/safe-debug in lllllllama/RigorPilot-Skills) into .claude/skills/safe-debug in your project. Claude Code loads it when a task matches its description.
How do I install Safe Debug in Codex?
Run `npx skills add lllllllama/RigorPilot-Skills --skill safe-debug -a codex`. Or copy the skill folder (skills/safe-debug in lllllllama/RigorPilot-Skills) into .agents/skills/safe-debug in your project. Codex loads it when a task matches its description.
Can I use Safe Debug in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lllllllama/RigorPilot-Skills --skill safe-debug -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/safe-debug, .gemini/skills/safe-debug, .github/skills/safe-debug and .opencode/skills/safe-debug in your project.
What does Safe Debug need to run?
Going by SKILL.md and its folder, Safe Debug needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Safe Debug access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Safe Debug safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Safe Debug use?
Safe Debug is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Safe Debug use?
About 522 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 128 tokens, read only when the agent opens those files.
What are the alternatives to Safe Debug?
Skills that share tags, products or a category with Safe Debug: Ut Refactor Review (intel/torch-xpu-ops, 115 stars), Aoti Debug (pytorch/pytorch, 104k stars), The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars) and ExecuTorch Build Guide (pytorch/executorch, 5.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Safe Debug?
lllllllama (a GitHub user) maintains it in lllllllama/RigorPilot-Skills, which has 497 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 23, 2026.
Source: lllllllama/RigorPilot-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.