ML Failure Debugger
Leeroo-AI/superml
Diagnoses failing ML and AI work, such as OOM, NaN, divergence, crashes, slow throughput, wrong outputs and dependency conflicts, with every claim backed by documentation citations.
Common mistake — retrying the same failing command or API call without understanding why it failed.
$ npx skills add aiming-lab/MetaClaw --skill do-not-retry-without-diagnosis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install aiming-lab/MetaClaw do-not-retry-without-diagnosis --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/aiming-lab/MetaClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/memory_data/skills/do-not-retry-without-diagnosis .claude/skills/do-not-retry-without-diagnosis && 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 "do-not-retry-without-diagnosis" agent skill from https://github.com/aiming-lab/MetaClaw/tree/main/memory_data/skills/do-not-retry-without-diagnosis into .claude/skills/do-not-retry-without-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "do-not-retry-without-diagnosis", 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/aiming-lab/MetaClaw/tree/main/memory_data/skills/do-not-retry-without-diagnosisType 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 aiming-lab/MetaClaw --skill do-not-retry-without-diagnosis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install aiming-lab/MetaClaw do-not-retry-without-diagnosis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiming-lab/MetaClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/memory_data/skills/do-not-retry-without-diagnosis .agents/skills/do-not-retry-without-diagnosis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "do-not-retry-without-diagnosis" agent skill from https://github.com/aiming-lab/MetaClaw/tree/main/memory_data/skills/do-not-retry-without-diagnosis into .agents/skills/do-not-retry-without-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "do-not-retry-without-diagnosis", 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 aiming-lab/MetaClaw --skill do-not-retry-without-diagnosis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install aiming-lab/MetaClaw do-not-retry-without-diagnosis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiming-lab/MetaClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/memory_data/skills/do-not-retry-without-diagnosis .cursor/skills/do-not-retry-without-diagnosis && 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 "do-not-retry-without-diagnosis" agent skill from https://github.com/aiming-lab/MetaClaw/tree/main/memory_data/skills/do-not-retry-without-diagnosis into .cursor/skills/do-not-retry-without-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "do-not-retry-without-diagnosis", 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/aiming-lab/MetaClaw.git --path memory_data/skills/do-not-retry-without-diagnosis--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 aiming-lab/MetaClaw --skill do-not-retry-without-diagnosis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install aiming-lab/MetaClaw do-not-retry-without-diagnosis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiming-lab/MetaClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/memory_data/skills/do-not-retry-without-diagnosis .gemini/skills/do-not-retry-without-diagnosis && 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 "do-not-retry-without-diagnosis" agent skill from https://github.com/aiming-lab/MetaClaw/tree/main/memory_data/skills/do-not-retry-without-diagnosis into .gemini/skills/do-not-retry-without-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "do-not-retry-without-diagnosis", 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 aiming-lab/MetaClaw do-not-retry-without-diagnosisInstalls 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 aiming-lab/MetaClaw --skill do-not-retry-without-diagnosis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/aiming-lab/MetaClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/memory_data/skills/do-not-retry-without-diagnosis .github/skills/do-not-retry-without-diagnosis && 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 "do-not-retry-without-diagnosis" agent skill from https://github.com/aiming-lab/MetaClaw/tree/main/memory_data/skills/do-not-retry-without-diagnosis into .github/skills/do-not-retry-without-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "do-not-retry-without-diagnosis", 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 aiming-lab/MetaClaw --skill do-not-retry-without-diagnosis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install aiming-lab/MetaClaw do-not-retry-without-diagnosis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiming-lab/MetaClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/memory_data/skills/do-not-retry-without-diagnosis .opencode/skills/do-not-retry-without-diagnosis && 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 "do-not-retry-without-diagnosis" agent skill from https://github.com/aiming-lab/MetaClaw/tree/main/memory_data/skills/do-not-retry-without-diagnosis into .opencode/skills/do-not-retry-without-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "do-not-retry-without-diagnosis", 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.
do-not-retry-without-diagnosisCommon mistake — retrying the same failing command or API call without understanding why it failed.
Do Not Retry Without Diagnosis is an agent skill from aiming-lab/MetaClaw. Common mistake — retrying the same failing command or API call without understanding why it failed. Always diagnose the root cause before retrying anything.
Its SKILL.md is about 190 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Root cause analysis. The repository describes itself as: 🦞 Just talk to your agent — it learns and EVOLVES 🧬. The licence is MIT.
Read from SKILL.md and the folder at commit 922caf3. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Do Not Retry Without Diagnosis loads about 189 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 73 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.
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); files beside SKILL.md are not scanned.
The full file from aiming-lab/MetaClaw at commit 922caf3, republished under its MIT licence (© aiming-lab). 73 words, ~189 tokens.
.claude/skills/do-not-retry-without-diagnosis/SKILL.md (or your agent's skills folder).Mistake pattern: Tool call fails → retry the same call → fails again → repeat.
Fix: After the first failure, read the error message carefully and diagnose the root cause before retrying.
Questions to ask:
Anti-pattern: Blindly retrying or escalating without examining the error output.
© aiming-lab, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in memory_data/skills/do-not-retry-without-diagnosis of aiming-lab/MetaClaw.
Open the folder on GitHubat commit 922caf3
Do Not Retry Without Diagnosis 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 |
|---|---|---|---|---|---|---|
| Do Not Retry Without Diagnosis this skillaiming-lab/MetaClaw | 3.5k | — | ~189 | Automated safety check: Pass | MIT | |
| ML Failure DebuggerLeeroo-AI/superml | 195 | — | ~9.5k | Automated safety check: Pass | Apache-2.0 | |
| Train Infer Consistencyverl-project/verl-omni | 1.2k | — | ~860 | Automated safety check: Pass | Apache-2.0 | |
| The Art of Debuggingstas00/the-art-of-debugging | 1.7k | — | ~6.1k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| Xpu CI Health Checkintel/torch-xpu-ops | 115 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Datadog Query Recipeslangfuse/langfuse | 36k | — | ~824 | Automated safety check: Pass | Custom licence |
Leeroo-AI/superml
Diagnoses failing ML and AI work, such as OOM, NaN, divergence, crashes, slow throughput, wrong outputs and dependency conflicts, with every claim backed by documentation citations.
verl-project/verl-omni
Route verl-omni training/inference consistency checks through MindStudio's MSProbe collection and root-cause analysis skills.
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.
intel/torch-xpu-ops
Check PyTorch ciflow/xpu (xpu.yml) on the main branch, collect the failing XPU test cases from the most recent completed run(s), analyze the ROOT CAUSE of each failure with AI, and produce a list…
langfuse/langfuse
Research Langfuse production telemetry with reusable Datadog queries.
facebookexperimental/triton
Diagnose CUDA "illegal instruction" / kernel crashes on Triton kernels that reference to TMA loads or stores (maketensordescriptor, TensorDescriptor, descriptor.load, descriptor.store…
aiming-lab/MetaClaw
Use this skill before any data analysis, transformation, or modeling.
aiming-lab/MetaClaw
A skill your agent uses when implementing any endpoint, form handler, CLI tool, or function that accepts external input.
aiming-lab/MetaClaw
A skill your agent uses when writing shell scripts, Python automation, or any unattended batch job.
aiming-lab/MetaClaw
A skill your agent uses when building production services, pipelines, or automation that needs to be debugged, monitored, or audited.
aiming-lab/MetaClaw
A skill your agent uses when delegating a subtask to a sub-agent, spawning a parallel worker, or handing off work across sessions.
aiming-lab/MetaClaw
A skill your agent uses when writing messages in async channels (Slack, GitHub issues, email threads) where the reader may not have context and cannot ask follow-up questions immediately.
Categories
Common mistake — retrying the same failing command or API call without understanding why it failed. Do Not Retry Without Diagnosis is an agent skill from aiming-lab/MetaClaw. Common mistake — retrying the same failing command or API call without understanding why it failed.
Do Not Retry Without Diagnosis fits situations like: tasks that involve Root cause analysis.
Run `npx skills add aiming-lab/MetaClaw --skill do-not-retry-without-diagnosis -a claude-code`. Or copy the skill folder (memory_data/skills/do-not-retry-without-diagnosis in aiming-lab/MetaClaw) into .claude/skills/do-not-retry-without-diagnosis in your project. Claude Code loads it when a task matches its description.
Run `npx skills add aiming-lab/MetaClaw --skill do-not-retry-without-diagnosis -a codex`. Or copy the skill folder (memory_data/skills/do-not-retry-without-diagnosis in aiming-lab/MetaClaw) into .agents/skills/do-not-retry-without-diagnosis in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiming-lab/MetaClaw --skill do-not-retry-without-diagnosis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/do-not-retry-without-diagnosis, .gemini/skills/do-not-retry-without-diagnosis, .github/skills/do-not-retry-without-diagnosis and .opencode/skills/do-not-retry-without-diagnosis in your project.
SKILL.md names no scripts, command-line tools or credentials: Do Not Retry Without Diagnosis is instructions for the agent only.
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.
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. Review the folder before installing.
Do Not Retry Without Diagnosis is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 189 tokens (SKILL.md is roughly 756 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Do Not Retry Without Diagnosis: ML Failure Debugger (Leeroo-AI/superml, 195 stars), Train Infer Consistency (verl-project/verl-omni, 1.2k stars), The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars) and Xpu CI Health Check (intel/torch-xpu-ops, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
aiming-lab (a GitHub organization) maintains it in aiming-lab/MetaClaw, which has 3,459 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on June 7, 2026.
Source: aiming-lab/MetaClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.