Marimo Batch
koaning/gitcharts
An opintionated skill to prepare a marimo notebook to make it ready for a scheduled run.
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs).
No licenceAuto-check: notes
Install Training Check
$ npx skills add AI4Scientist/nano-scientist --skill training-check -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AI4Scientist/nano-scientist training-check --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/AI4Scientist/nano-scientist.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/training-check .claude/skills/training-check && 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 "training-check" agent skill from https://github.com/AI4Scientist/nano-scientist/tree/main/skills/training-check into .claude/skills/training-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-check", 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/AI4Scientist/nano-scientist/tree/main/skills/training-checkType 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 AI4Scientist/nano-scientist --skill training-check -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AI4Scientist/nano-scientist training-check --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AI4Scientist/nano-scientist.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/training-check .agents/skills/training-check && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "training-check" agent skill from https://github.com/AI4Scientist/nano-scientist/tree/main/skills/training-check into .agents/skills/training-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-check", 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 AI4Scientist/nano-scientist --skill training-check -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AI4Scientist/nano-scientist training-check --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AI4Scientist/nano-scientist.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/training-check .cursor/skills/training-check && 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 "training-check" agent skill from https://github.com/AI4Scientist/nano-scientist/tree/main/skills/training-check into .cursor/skills/training-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-check", 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/AI4Scientist/nano-scientist.git --path skills/training-check--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 AI4Scientist/nano-scientist --skill training-check -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AI4Scientist/nano-scientist training-check --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AI4Scientist/nano-scientist.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/training-check .gemini/skills/training-check && 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 "training-check" agent skill from https://github.com/AI4Scientist/nano-scientist/tree/main/skills/training-check into .gemini/skills/training-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-check", 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 AI4Scientist/nano-scientist training-checkInstalls 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 AI4Scientist/nano-scientist --skill training-check -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AI4Scientist/nano-scientist.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/training-check .github/skills/training-check && 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 "training-check" agent skill from https://github.com/AI4Scientist/nano-scientist/tree/main/skills/training-check into .github/skills/training-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-check", 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 AI4Scientist/nano-scientist --skill training-check -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AI4Scientist/nano-scientist training-check --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AI4Scientist/nano-scientist.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/training-check .opencode/skills/training-check && 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 "training-check" agent skill from https://github.com/AI4Scientist/nano-scientist/tree/main/skills/training-check into .opencode/skills/training-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "training-check", 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
training-check- GitHub stars
- 128
- Used in
- 3 other repos
- Token cost
- ~1.3k tokens
- SKILL.md length
- 528 words
- Files
- 1
- Skills in repo
- 74
- Repo updated
- First seen
- Licence
- None found
At a glance
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs).
- Works in 4 steps: Read WandB Metrics → Judgment → Codex Judgment (only when unsure) → …
- Training is running and you want automated health checks
- SKILL.md covers Context: $ARGUMENTS, Constants, When to Use and Workflow, plus 3 more sections
- Calls ssh
What it does
Training Check is an agent skill from AI4Scientist/nano-scientist. Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with Weights & Biases. The repository describes itself as: An autonomous research agent that turns a topic into a peer-reviewed technical report.
When your agent uses it
- Training is running and you want automated health checks
Example prompts
- “/training-check”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Bash(*), Read, Grep, Glob, Write, Edit, mcp__codex__codex, mcp__codex__codex-reply
Workflow steps
4 steps, taken from the step headings in SKILL.md.
- Read WandB Metrics
- Judgment
- Codex Judgment (only when unsure)
- Act
What it can do on your machine
Read from SKILL.md and the folder at commit 7132192. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash(*)ReadGrepGlobWriteEditmcp__codex__codexmcp__codex__codex-reply
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
ssh
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use ssh, which can reach the network depending on how they are called.
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
Training Check loads about 1.3k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 528 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash(*), Read, Grep, Glob, Write, Edit, mcp__codex__codex, mcp__codex__codex-reply
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.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 528 words (~1,316 tokens).
“Periodically read WandB metrics during training to catch problems early. Do not wait until training finishes to discover it was a waste of GPU time.”
- name
- training-check
- allowed-tools
- Bash(*), Read, Grep, Glob, Write, Edit, mcp__codex__codex, mcp__codex__codex-reply
- argument-hint
- wandb-run-path
Files
Just SKILL.md in skills/training-check of AI4Scientist/nano-scientist.
Open the folder on GitHubat commit 7132192
Used in 3 other repositories
We found 4 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in AI4Scientist/nano-scientist, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Training Check 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 |
|---|---|---|---|---|---|---|
| Training Check this skillAI4Scientist/nano-scientist | 128 | 3 repos | ~1.3k | Automated safety check: Notes | None | |
| Marimo Batchkoaning/gitcharts | 145 | 1 repos | ~819 | Automated safety check: Notes | None | |
| Weights & Biases Experiment TrackingOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.1k | Automated safety check: Pass | MIT | |
| Comparefcakyon/phd-skills | 415 | — | ~1.2k | Automated safety check: Pass | MIT | |
| ML Experiment IterationLeeroo-AI/superml | 195 | — | ~4.8k | Automated safety check: Pass | Apache-2.0 | |
| LaminDB Biological Data Managementdavila7/claude-code-templates | 33k | 12 repos | ~3.6k | Automated safety check: Pass | MIT |
Similar skills
Weights & Biases Experiment Tracking
Orchestra-Research/AI-Research-SKILLs
Guides an agent through tracking ML experiments with W&B: run logging, config capture, hyperparameter sweeps, artifacts and a model registry.
Compare
fcakyon/phd-skills
Same-epoch comparison of training runs across wandb, neptune, tensorboard, or mlflow.
ML Experiment Iteration
Leeroo-AI/superml
Produces ranked, evidence-grounded next steps when an ML experiment has stalled, drawing on a Leeroopedia knowledge base or on fetched docs and issues.
LaminDB Biological Data Management
davila7/claude-code-templates
Manages biological datasets with LaminDB: versioned artifacts, run lineage, ontology-based annotation, schema validation and links to workflow managers and ML tools.
Dashboard
LegoX/Lego-RL
Bring up the Lego-RL training dashboard (webui/) on whatever machine you are on, adapting to that box's layout instead of assuming this repo's paths.
More from AI4Scientist/nano-scientist
All 74 skills in this repoFormula Derivation
AI4Scientist/nano-scientist
Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a…
Paper Compile
AI4Scientist/nano-scientist
Compile LaTeX paper to PDF, fix errors, and verify output. An agent skill from AI4Scientist/nano-scientist.
Paper Figure
AI4Scientist/nano-scientist
Generate publication-quality figures and tables from experiment results.
Paper Navigator
AI4Scientist/nano-scientist
Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA)…
Proof Writer
AI4Scientist/nano-scientist
Writes rigorous mathematical proofs for ML/AI theory. An agent skill from AI4Scientist/nano-scientist.
Ablation Planner
AI4Scientist/nano-scientist
A skill your agent uses when main results pass result-to-claim (claimsupported=yes or partial) and ablation studies are needed for paper submission.
Related
Works with
Questions about Training Check
What does Training Check do?
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Training Check is an agent skill from AI4Scientist/nano-scientist. Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs).
When should I use Training Check?
Training Check fits situations like: training is running and you want automated health checks.
How do I install Training Check in Claude Code?
Run `npx skills add AI4Scientist/nano-scientist --skill training-check -a claude-code`. Or copy the skill folder (skills/training-check in AI4Scientist/nano-scientist) into .claude/skills/training-check in your project. Claude Code loads it when a task matches its description.
How do I install Training Check in Codex?
Run `npx skills add AI4Scientist/nano-scientist --skill training-check -a codex`. Or copy the skill folder (skills/training-check in AI4Scientist/nano-scientist) into .agents/skills/training-check in your project. Codex loads it when a task matches its description.
Can I use Training Check 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 AI4Scientist/nano-scientist --skill training-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/training-check, .gemini/skills/training-check, .github/skills/training-check and .opencode/skills/training-check in your project.
What does Training Check need to run?
Going by SKILL.md and its folder, Training Check needs the command-line tools its instructions call (ssh). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash(*), Read, Grep, Glob, Write, Edit, mcp__codex__codex, mcp__codex__codex-reply.
Does Training Check access the network?
SKILL.md contains no URLs. Its commands use ssh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Training Check safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Training Check use?
No licence was found for Training Check or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Training Check use?
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Training Check?
Skills that share tags, products or a category with Training Check: Marimo Batch (koaning/gitcharts, 145 stars), Weights & Biases Experiment Tracking (Orchestra-Research/AI-Research-SKILLs, 13k stars), Compare (fcakyon/phd-skills, 415 stars) and ML Experiment Iteration (Leeroo-AI/superml, 195 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Training Check?
AI4Scientist (a GitHub organization) maintains it in AI4Scientist/nano-scientist, which has 128 GitHub stars. The repository holds 74 skills in this directory. The repository was last updated on June 3, 2026.
Source: AI4Scientist/nano-scientist on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.