Agent skill

Use Iris

by marin-community in 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.

Apache-2.0Auto-check passedDevOps & Cloud

Install Use Iris

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

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

GitHub CLI
$ gh skill install marin-community/marin use-iris --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/use-iris .claude/skills/use-iris && 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
use-iris
GitHub stars
3.9k
Token cost
~745 tokens
SKILL.md length
236 words
Files
5 (incl. references)
Skills in repo
41
Repo updated
First seen
Licence
Apache-2.0

At a glance

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

  • Ordinary Iris operations
  • SKILL.md covers Common reads, Temporary outputs and Boundaries
  • Calls uv and kubectl
  • Including babysitting a job

What it does

Use Iris is an agent skill from 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. Use for ordinary Iris operations, including babysitting a job, controller rollouts, accelerator sessions, and stuck CoreWeave pods. Use a narrower production-run or Zephyr skill when that workflow is explicitly requested.

Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/controller-rollout.md`, `references/dev-accelerators.md` and `references/monitor-job.md`).

It sits in DevOps & Cloud. 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

  • Ordinary Iris operations
  • Including babysitting a job
  • Controller rollouts
  • Accelerator sessions

Example prompts

  • “/use-iris”

What it can do on your machine

Read from SKILL.md and the folder at commit 61bb85c. 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:

    • uv
    • kubectl

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

  • Network

    No URLs in SKILL.md. Its commands use uv and kubectl, 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

Use Iris loads about 745 tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 236 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~745
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

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 61bb85c, republished under its Apache-2.0 licence (© marin-community). 236 words, ~745 tokens.

Download SKILL.mdSave it as .claude/skills/use-iris/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
use-iris
description
Use Iris to submit, inspect, debug, monitor, or recover jobs and tasks; diagnose scheduling and federation; deploy controllers; or reserve dev GPUs and TPUs. Use for ordinary Iris operations, including babysitting a job, controller rollouts, accelerator sessions, and stuck CoreWeave pods. Use a narrower production-run or Zephyr skill when that workflow is explicitly requested.

Use Iris

Read only the material needed for the request:

Resolve cluster facts from lib/iris/config/<cluster>.yaml; do not copy live coordinates from memory.

Common reads

bash
uv run iris --cluster=<cluster> job describe <job>
uv run iris --cluster=<cluster> task describe <task>
uv run iris --cluster=<cluster> task events <task>
uv run iris --cluster=<cluster> rpc controller list-backends

For a pending federated root, inspect all three parent-side views:

bash
uv run iris --cluster=<parent> job list --prefix <root-job>
uv run iris --cluster=<parent> rpc controller list-peers
uv run iris --cluster=<parent> query \
  "SELECT job_id, peer_id, handoff_state FROM federated_jobs WHERE job_id='<root-job>'"

Only root jobs federate; their whole tree stays on the peer. Parent job describe is the liveness source, while forwarded logs may lag. CoreWeave tasks normally read regional S3 and GCP tasks read GCS.

Temporary outputs

Write bounded diagnostics to $IRIS_OUTPUT_DIR. Iris preserves that directory as one outputs.tar.zst archive per attempt without changing the command outcome when capture fails. Find the archive URI and its uploaded, empty, failed, or unavailable state with:

bash
uv run iris --cluster=<cluster> attempt describe <task>:<attempt>

Use direct object-storage writes for large or durable outputs. See lib/iris/docs/task-outputs.md for retention, limits, and data-access boundaries.

Boundaries

  • Start read-only and name the evidence that distinguishes each cause.
  • Never run iris cluster restart without explicit approval for the named cluster; it kills all workers and jobs.
  • Treat a controller restart as a deployment and require an explicitly named target.
  • Cancel, complete, fail, preempt, resubmit, or change Kubernetes state only when the request or selected reference authorizes that exact action.
  • Avoid kubectl describe pod on task pods because it can print environment values.

© 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

SKILL.md and 4 other files (references) in .agents/skills/use-iris of marin-community/marin.

  • SKILL.md
  • references/controller-rollout.md
  • references/dev-accelerators.md
  • references/monitor-job.md
  • references/stuck-pod.md

Open the folder on GitHubat commit 61bb85c

Compare with similar skills

Use Iris 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.

Use Iris compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Use Iris this skillmarin-community/marin3.9k—~745Automated safety check: PassApache-2.0
Monitor CInrwl/nx29k6 repos~4.7kAutomated safety check: PassMIT
Terraform and OpenTofu Guideagentscope-ai/QwenPaw36k6 repos~4.2kAutomated safety check: PassApache-2.0
Vercel Optimize Auditvercel-labs/agent-skills32k8 repos~4.3kAutomated safety check: PassNone
Analyze GitHub Action Logswithastro/astro63k1 repos~1.3kAutomated safety check: PassCustom licence
Openclaw Live Updateropenclaw/openclaw392k—~3.7kAutomated safety check: PassMIT

Similar skills

  • Monitor CI

    nrwl/nx

    Monitor Nx Cloud CI pipeline and handle self-healing fixes. An agent skill from nrwl/nx.

    29k GitHub starsUsed in 6 repos~4.7k tokens
    DevOps & CloudAuto-check passed
  • Terraform and OpenTofu Guide

    agentscope-ai/QwenPaw

    Guidance for writing and testing Terraform and OpenTofu code: module structure, naming, test approaches, CI/CD workflows, state handling and security scanning.

    36k GitHub starsUsed in 6 repos~4.2k tokens
    DevOps & CloudAuto-check passed
  • Vercel Optimize Audit

    vercel-labs/agent-skills

    Official

    Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.

    32k GitHub starsUsed in 8 repos~4.3k tokens
    DevOps & CloudAuto-check passed
  • Official

    Analyze recent GitHub Actions workflow runs to identify patterns, mistakes, and improvements.

    63k GitHub starsUsed in 1 repo~1.3k tokens
    DevOps & CloudAuto-check passed
  • Openclaw Live Updater

    openclaw/openclaw

    Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation.

    392k GitHub stars~3.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Docs Learn PR Preview

    netdata/netdata

    Use only when the user explicitly asks to build, run, preview, inspect, or validate learn.netdata.cloud locally using the contents of a PR or documentation branch before merge.

    81k GitHub stars~2k tokensUpdated today
    DevOps & CloudAuto-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
  • 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
  • Deploy Hero Change

    marin-community/marin

    Deploy a significant code change (backend, kernel, optimizer, data path) to the live hero run: relaunch it under a new run id from a permanent checkpoint, compare against the old run over a trial…

    3.9k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Categories

Questions about Use Iris

What does Use Iris do?

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

When should I use Use Iris?

Use Iris fits situations like: ordinary Iris operations; including babysitting a job; controller rollouts; accelerator sessions.

How do I install Use Iris in Claude Code?

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

How do I install Use Iris in Codex?

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

Can I use Use Iris 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 use-iris -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/use-iris, .gemini/skills/use-iris, .github/skills/use-iris and .opencode/skills/use-iris in your project.

What does Use Iris need to run?

Going by SKILL.md and its folder, Use Iris needs the command-line tools its instructions call (uv and kubectl).

Does Use Iris 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 Use Iris 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 Use Iris use?

Use Iris 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 Use Iris use?

About 745 tokens (SKILL.md is roughly 3k 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 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Use Iris?

Skills that share tags, products or a category with Use Iris: Monitor CI (nrwl/nx, 29k stars), Terraform and OpenTofu Guide (agentscope-ai/QwenPaw, 36k stars), Vercel Optimize Audit (vercel-labs/agent-skills, 32k stars) and Analyze GitHub Action Logs (withastro/astro, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Use Iris?

marin-community (a GitHub organization) maintains it in marin-community/marin, which has 3,920 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 9, 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.