New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Onboard Marin

by marin-community in marin-community/marin

Verify or complete a new internal Marin developer's local setup and access to GitHub, GCP, Iris, Weights & Biases, Hugging Face, and optional CoreWeave storage.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Onboard Marin

skills CLI
$ npx skills add marin-community/marin --skill onboard-marin -a claude-code

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

GitHub CLI
$ gh skill install marin-community/marin onboard-marin --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/marin-community/marin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/onboard-marin .claude/skills/onboard-marin && 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
onboard-marin
GitHub stars
3.9k
Token cost
~1.1k tokens
SKILL.md length
553 words
Files
1
Skills in repo
41
Repo updated
First seen
Licence
Apache-2.0

At a glance

Verify or complete a new internal Marin developer's local setup and access to GitHub, GCP, Iris, Weights & Biases, Hugging Face, and optional CoreWeave storage.

  • Works in 8 steps: Confirm the command is running from a… → Check the required local tools and… → Check GitHub authentication and… → …
  • A team member asks to onboard
  • SKILL.md covers Sources, Verify, Smoke tests and Report
  • Calls pulumi; needs WANDB_API_KEY and HF_TOKEN

What it does

Onboard Marin is an agent skill from marin-community/marin. Verify or complete a new internal Marin developer's local setup and access to GitHub, GCP, Iris, Weights & Biases, Hugging Face, and optional CoreWeave storage. Use when a team member asks to onboard, validate onboarding, or diagnose missing development access.

Its SKILL.md is about 1.1k 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 Model hubs and datasets. It works with Google Cloud, GitHub, Hugging Face and Weights & Biases. The repository describes itself as: Open-source framework for the research and development of foundation models. The licence is Apache-2.0.

When your agent uses it

  • A team member asks to onboard
  • Validate onboarding
  • Diagnose missing development access

Example prompts

  • “/onboard-marin”

Requirements

  • Python 3
  • A credential in WANDB_API_KEY

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Confirm the command is running from a Marin checkout and inspect the working
  2. Check the required local tools and Python version. Check dependency and
  3. Check GitHub authentication and repository push permission without pushing a
  4. Check the active GCP account, the hai-gcp-models project, Application
  5. When the user will operate the marin GCP Pulumi stack
  6. Check Iris authentication and read-only cluster status. Use iris login
  7. Check whether WANDB_API_KEY and HF_TOKEN are present without printing
  8. Check CoreWeave object-storage access only when the user needs to inspect GPU

What it can do on your machine

Read from SKILL.md and the folder at commit c468793. 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

    Shell commands in SKILL.md call:

    • pulumi

    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 these keys or tokens, usually read from environment variables:

    • WANDB_API_KEY
    • HF_TOKEN

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

Context cost

Onboard Marin loads about 1.1k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 553 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from marin-community/marin at commit c468793, republished under its Apache-2.0 licence (© marin-community). 553 words, ~1,065 tokens.

Download SKILL.mdSave it as .claude/skills/onboard-marin/SKILL.md (or your agent's skills folder).
name
onboard-marin
description
Verify or complete a new internal Marin developer's local setup and access to GitHub, GCP, Iris, Weights & Biases, Hugging Face, and optional CoreWeave storage. Use when a team member asks to onboard, validate onboarding, or diagnose missing development access.

Onboard a Marin developer

Establish which parts of the developer environment are ready, fix local setup when safe, and identify each missing external grant. Keep secrets out of command output and the final report.

Sources

Use these as the current sources of truth:

  • Local installation: docs/tutorials/installation.md.
  • Development workflow: docs/dev-guide/contributing.md.
  • Iris authentication and access checks: lib/iris/OPS.md and the use-iris skill.
  • CoreWeave credentials and routing: docs/tutorials/cloud-gpu.md.
  • Pulumi operator grants and state access: infra/pulumi/README.md, the add-grant skill, and the review-grant skill.

Do not copy procedures from infra/README.md; it is an infrastructure index.

Verify

Start with read-only checks. Report each area as ready, missing access, missing local setup, or not checked.

  1. Confirm the command is running from a Marin checkout and inspect the working tree without changing user work.
  2. Check the required local tools and Python version. Check dependency and pre-commit setup against the installation and contributing guides. Install or repair local dependencies when the user's onboarding request authorizes it.
  3. Check GitHub authentication and repository push permission without pushing a branch.
  4. Check the active GCP account, the hai-gcp-models project, Application Default Credentials, and read access to gs://marin-us-central2. Confirm the current principal has projects/hai-gcp-models/roles/marindev with a filtered IAM query that prints only the matching role name. Do not print credential contents or the complete project policy.
  5. When the user will operate the marin GCP Pulumi stack:
    • In addition to the marindev check above, confirm the current principal has projects/hai-gcp-models/roles/marinPulumiAdmin with the same filtered IAM query.
    • Check that the Pulumi CLI and repository deploy dependencies are present. Run pulumi -C infra/pulumi stack export --stack marin >/dev/null to verify state access without printing state contents.
    • Report CoreWeave kubeconfig access separately when the user will operate a CoreWeave stack. Do not run pulumi up as an onboarding check. Do not grant roles or mutate live IAM unless the user asks for the grant workflow.
  6. Check Iris authentication and read-only cluster status. Use iris login only for an interactive human session; let the browser or headless login flow request the human's input.
  7. Check whether WANDB_API_KEY and HF_TOKEN are present without printing their values. When useful, perform a read-only identity check with the service's CLI and confirm access to the marin-community W&B entity. Do not persist a token outside the user's chosen credential store.
  8. Check CoreWeave object-storage access only when the user needs to inspect GPU job outputs. Do not treat storage credentials as proof of GPU scheduling access; Iris controls compute access separately.
Show full SKILL.md (141 more words)Show less

Distinguish local configuration failures from permissions that a maintainer must grant. GCP project access, Iris IAP access, GitHub access, Weights & Biases, Hugging Face, Pulumi operator access, and CoreWeave storage are independent.

Smoke tests

Run local import or CPU checks when they are cheap and do not download a large dataset. A remote Iris job changes shared state: submit one only when the user explicitly authorizes the smoke job. Keep it CPU-only, small, and bounded. Never request a GPU or TPU during onboarding.

Do not start, stop, restart, deploy, or otherwise mutate a shared cluster.

Report

Give the user a compact checklist of verified capabilities and remaining actions. Include the failing command category and error summary without secret values. Distinguish grants the user can request from local fixes. Do not edit IAM data or file a grant request unless the user asks.

© marin-community, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/onboard-marin of marin-community/marin.

Open the folder on GitHubat commit c468793

Compare with similar skills

Onboard Marin 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.

Onboard Marin compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Onboard Marin this skillmarin-community/marin3.9k—~1.1kAutomated safety check: PassApache-2.0
Esmfold2JimLiu/science-skills2284 repos~2.5kAutomated safety check: PassApache-2.0
Hugging Face Spaces DeployVincentqyw/image-matching-webui1.3k—~721Automated safety check: PassApache-2.0
Publish Tracelab Huggingfaceuw-syfi/TraceLab142—~1.4kAutomated safety check: PassApache-2.0
Discovertaishi-i/awesome-japanese-nlp-resources1k—~6.5kAutomated safety check: NotesCC0-1.0
News Aggregator Skilldracohu2025-cloud/draco-skills-collection227—~596Automated safety check: PassMIT

Similar skills

  • Esmfold2

    JimLiu/science-skills

    Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

    228 GitHub starsUsed in 4 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Spaces Deploy

    Vincentqyw/image-matching-webui

    Releases a new imcui version on GitHub, then deploys it to a test and a production Hugging Face Space from a dedicated huggingface branch.

    1.3k GitHub stars~721 tokensUpdated 5 days ago
    DevOps & CloudAuto-check passed

  • Publish Tracelab Huggingface

    uw-syfi/TraceLab

    Prepare, publish, refresh, or validate the TraceLab public dataset on Hugging Face under UW-SyFI/TraceLab.

    142 GitHub stars~1.4k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Discover

    taishi-i/awesome-japanese-nlp-resources

    Given a Japanese NLP GitHub repo/model/dataset (URL / owner/repo / tool name) OR a topic, find what's already in awesome-japanese-nlp-resources and discover related resources NOT yet listed…

    1k GitHub stars~6.5k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check: notes

  • News Aggregator Skill

    dracohu2025-cloud/draco-skills-collection

    A skill your agent uses when collecting public news candidates from Hacker News, GitHub Trending, Hugging Face papers, and other web sources for briefings and daily reports.

    227 GitHub stars~596 tokensUpdated 23 days ago
    AI & LLM EngineeringAuto-check passed

  • Relay

    xhluca/agent-talk

    Set up, check, stop, or delete a retalk relay server (retalk-server).

    191 GitHub stars~1.5k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

More from marin-community/marin

All 41 skills in this repo

  • Noslop

    marin-community/marin

    Deslop, simplify, or review low-value tests and prose only when explicitly requested for a branch or diff.

    3.9k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Use Iris

    marin-community/marin

    Use Iris to submit, inspect, debug, monitor, or recover jobs and tasks; diagnose scheduling and federation; deploy controllers; or reserve dev GPUs and TPUs.

    3.9k GitHub stars~745 tokensUpdated today
    Auto-check passed

  • Launch Rl

    marin-community/marin

    Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main.

    3.9k GitHub stars~894 tokensUpdated today
    Auto-check passed

  • Marina Applet

    marin-community/marin

    Build, validate, publish, update, inspect, query, roll back, or archive a dynamic Marina applet.

    3.9k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Query Finelog

    marin-community/marin

    Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding.

    3.9k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Trace Pulumi Diff

    marin-community/marin

    Run a read-only preview for a specified Marin infra/pulumi stack and trace each pending resource change to merged pull requests since its latest successful update when that update records a clean…

    3.9k GitHub stars~663 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Onboard Marin

What does Onboard Marin do?

Verify or complete a new internal Marin developer's local setup and access to GitHub, GCP, Iris, Weights & Biases, Hugging Face, and optional CoreWeave storage. Onboard Marin is an agent skill from marin-community/marin. Verify or complete a new internal Marin developer's local setup and access to GitHub, GCP, Iris, Weights & Biases, Hugging Face, and optional CoreWeave storage.

When should I use Onboard Marin?

Onboard Marin fits situations like: A team member asks to onboard; validate onboarding; diagnose missing development access.

How do I install Onboard Marin in Claude Code?

Run `npx skills add marin-community/marin --skill onboard-marin -a claude-code`. Or copy the skill folder (.agents/skills/onboard-marin in marin-community/marin) into .claude/skills/onboard-marin in your project. Claude Code loads it when a task matches its description.

How do I install Onboard Marin in Codex?

Run `npx skills add marin-community/marin --skill onboard-marin -a codex`. Or copy the skill folder (.agents/skills/onboard-marin in marin-community/marin) into .agents/skills/onboard-marin in your project. Codex loads it when a task matches its description.

Can I use Onboard Marin 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 marin-community/marin --skill onboard-marin -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/onboard-marin, .gemini/skills/onboard-marin, .github/skills/onboard-marin and .opencode/skills/onboard-marin in your project.

What does Onboard Marin need to run?

Going by SKILL.md and its folder, Onboard Marin needs the command-line tools its instructions call (pulumi) and credentials named WANDB_API_KEY and HF_TOKEN. Our summary lists: Python 3; A credential in WANDB_API_KEY.

Does Onboard Marin 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 Onboard Marin 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. Review the folder before installing.

What licence does Onboard Marin use?

Onboard Marin is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Onboard Marin use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Onboard Marin?

Skills that share tags, products or a category with Onboard Marin: Esmfold2 (JimLiu/science-skills, 228 stars), Hugging Face Spaces Deploy (Vincentqyw/image-matching-webui, 1.3k stars), Publish Tracelab Huggingface (uw-syfi/TraceLab, 142 stars) and Discover (taishi-i/awesome-japanese-nlp-resources, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Onboard Marin?

marin-community (a GitHub organization) maintains it in marin-community/marin, which has 3,921 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 10, 2026.

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