Agent skill

Scaffold Example

by comet-ml in comet-ml/comet-examples

Scaffold a brand-new Comet example in this repo from the canonical template under templates/integration-example/.

No licenceAuto-check passedAI & LLM Engineering

Install Scaffold Example

skills CLI
$ npx skills add comet-ml/comet-examples --skill scaffold-example -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install comet-ml/comet-examples scaffold-example --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/comet-ml/comet-examples.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/scaffold-example .claude/skills/scaffold-example && rm -rf skills-src

Use ~/.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/

Facts

Skill name
scaffold-example
GitHub stars
175
Token cost
~1k tokens
SKILL.md length
395 words
Files
2 (incl. scripts)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Scaffold a brand-new Comet example in this repo from the canonical template under templates/integration-example/.

  • Works in 3 steps: Generate the example → Make it real → Verify
  • The user wants to create
  • SKILL.md covers When to refuse, Step 1 — Generate the example, Step 2 — Make it real and Step 3 — Verify, plus 1 more section
  • Runs Python scripts from its folder; calls uv and python; needs COMET_API_KEY

What it does

Scaffold Example is an agent skill from comet-ml/comet-examples. Scaffold a brand-new Comet example in this repo from the canonical template under templates/integration-example/. Use whenever the user wants to create, add, or start a new example, demo, or integration on Comet — phrasings like "add a Comet example for X", "scaffold an integration example", "create a new example for <framework", "start a hello-world for <library", "set up a new example project". Do NOT hand-build the folder structure or copy files manually — this skill stamps out the example and renames it…

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/scaffold.py`).

It sits in AI & LLM Engineering, covering File organization, Deep learning and Machine learning. It works with Python. The repository describes itself as: Examples of Machine Learning code using Comet.ml.

When your agent uses it

  • The user wants to create
  • Start a new example
  • Integration on Comet — phrasings like add a Comet example for X
  • Scaffold an integration example

Example prompts

  • “add a Comet example for X”
  • “scaffold an integration example”
  • “create a new example for <framework”
  • “/scaffold-example”

Requirements

  • Python 3
  • A credential in COMET_API_KEY

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Generate the example
  2. Make it real
  3. Verify

What it can do on your machine

Read from SKILL.md and the folder at commit b37756c. 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.

    Shell commands in SKILL.md call:

    • uv
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, 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 these keys or tokens, usually read from environment variables:

    • COMET_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Scaffold Example loads about 1k tokens when it runs. Until then it costs about 161 tokens; SKILL.md has 395 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~161
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 395 words (~1,026 tokens).

“This repo has one canonical example shape, a real, runnable template under templates/integration-example/: a uv project (pyproject.toml), a single comet_ml script (example_integration.py), and a README in the house structure (Title → Documentation → See it → Setup → Run the…”

— opening of SKILL.md by comet-ml
name
scaffold-example

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in .claude/skills/scaffold-example of comet-ml/comet-examples.

  • SKILL.md
  • scripts/scaffold.py

Open the folder on GitHubat commit b37756c

Compare with similar skills

Scaffold Example 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.

Scaffold Example compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scaffold Example this skillcomet-ml/comet-examples175—~1kAutomated safety check: PassNone
PyTorch Lightning TrainingOrchestra-Research/AI-Research-SKILLs13k7 repos~2.3kAutomated safety check: PassMIT
Ray Train Distributed TrainingOrchestra-Research/AI-Research-SKILLs13k3 repos~2.7kAutomated safety check: PassMIT
PyHealth Clinical ML Toolkitdavila7/claude-code-templates32k12 repos~4.4kAutomated safety check: PassMIT
Scikit Learn Machine Learningjaechang-hits/SciAgent-Skills3701 repos~4kAutomated safety check: PassBSD-3-Clause
Deep Learningericrisco/rsc-harness156—~3.4kAutomated safety check: PassMIT

Similar skills

  • PyTorch Lightning Training

    Orchestra-Research/AI-Research-SKILLs

    Shows how to organize PyTorch training with Lightning's LightningModule and Trainer, covering validation, DDP, callbacks and learning-rate scheduling.

    13k GitHub starsUsed in 7 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed
  • Ray Train Distributed Training

    Orchestra-Research/AI-Research-SKILLs

    Scales PyTorch, TensorFlow and Hugging Face training from a single GPU to multi-node clusters with Ray Train, including Ray Tune sweeps and checkpoint recovery.

    13k GitHub starsUsed in 3 repos~2.7k tokens
    AI & LLM EngineeringAuto-check passed
  • PyHealth Clinical ML Toolkit

    davila7/claude-code-templates

    Builds machine learning pipelines on clinical data with PyHealth: EHR datasets, prediction tasks, medical code mapping, healthcare models and evaluation.

    32k GitHub starsUsed in 12 repos~4.4k tokens
    Research & ScienceAuto-check passed
  • Scikit Learn Machine Learning

    jaechang-hits/SciAgent-Skills

    Classical ML in Python: classification, regression, clustering, dim reduction, evaluation, tuning, preprocessing pipelines.

    370 GitHub starsUsed in 1 repo~4k tokens
    Data & AnalyticsAuto-check passed
  • Deep Learning

    ericrisco/rsc-harness

    A skill your agent uses when training or debugging a neural net in PyTorch — the forward/loss/backward/step loop and its silent bugs, mixed precision (AMP), AdamW/LR schedules, DDP/FSDP/ZeRO…

    156 GitHub stars~3.4k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 9 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed

Works with

Questions about Scaffold Example

What does Scaffold Example do?

Scaffold a brand-new Comet example in this repo from the canonical template under templates/integration-example/. Scaffold Example is an agent skill from comet-ml/comet-examples. Scaffold a brand-new Comet example in this repo from the canonical template under templates/integration-example/.

When should I use Scaffold Example?

Scaffold Example fits situations like: the user wants to create; start a new example; integration on Comet — phrasings like add a Comet example for X; scaffold an integration example.

How do I install Scaffold Example in Claude Code?

Run `npx skills add comet-ml/comet-examples --skill scaffold-example -a claude-code`. Or copy the skill folder (.claude/skills/scaffold-example in comet-ml/comet-examples) into .claude/skills/scaffold-example in your project. Claude Code loads it when a task matches its description.

How do I install Scaffold Example in Codex?

Run `npx skills add comet-ml/comet-examples --skill scaffold-example -a codex`. Or copy the skill folder (.claude/skills/scaffold-example in comet-ml/comet-examples) into .agents/skills/scaffold-example in your project. Codex loads it when a task matches its description.

Can I use Scaffold Example 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 comet-ml/comet-examples --skill scaffold-example -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scaffold-example, .gemini/skills/scaffold-example, .github/skills/scaffold-example and .opencode/skills/scaffold-example in your project.

What does Scaffold Example need to run?

Going by SKILL.md and its folder, Scaffold Example needs Python for the scripts in its folder, the command-line tools its instructions call (uv and python) and credentials named COMET_API_KEY. Our summary lists: Python 3; A credential in COMET_API_KEY.

Does Scaffold Example access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Scaffold Example 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 Scaffold Example use?

No licence was found for Scaffold Example or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Scaffold Example use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Scaffold Example?

Skills that share tags, products or a category with Scaffold Example: PyTorch Lightning Training (Orchestra-Research/AI-Research-SKILLs, 13k stars), Ray Train Distributed Training (Orchestra-Research/AI-Research-SKILLs, 13k stars), PyHealth Clinical ML Toolkit (davila7/claude-code-templates, 32k stars) and Scikit Learn Machine Learning (jaechang-hits/SciAgent-Skills, 370 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scaffold Example?

comet-ml (a GitHub organization) maintains it in comet-ml/comet-examples, which has 175 GitHub stars. The repository was last updated on August 12, 2026.

Source: comet-ml/comet-examples on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.