Reproduce Chat States
different-ai/openwork
Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.
Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main.
Install Launch Rl
$ npx skills add marin-community/marin --skill launch-rl -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install marin-community/marin launch-rl --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/marin-community/marin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/launch-rl .claude/skills/launch-rl && 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 "launch-rl" agent skill from https://github.com/marin-community/marin/tree/main/.agents/skills/launch-rl into .claude/skills/launch-rl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-rl", 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/marin-community/marin/tree/main/.agents/skills/launch-rlType 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 marin-community/marin --skill launch-rl -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install marin-community/marin launch-rl --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/marin-community/marin.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/launch-rl .agents/skills/launch-rl && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "launch-rl" agent skill from https://github.com/marin-community/marin/tree/main/.agents/skills/launch-rl into .agents/skills/launch-rl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-rl", 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 marin-community/marin --skill launch-rl -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install marin-community/marin launch-rl --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/marin-community/marin.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/launch-rl .cursor/skills/launch-rl && 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 "launch-rl" agent skill from https://github.com/marin-community/marin/tree/main/.agents/skills/launch-rl into .cursor/skills/launch-rl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-rl", 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/marin-community/marin.git --path .agents/skills/launch-rl--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 marin-community/marin --skill launch-rl -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install marin-community/marin launch-rl --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/marin-community/marin.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/launch-rl .gemini/skills/launch-rl && 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 "launch-rl" agent skill from https://github.com/marin-community/marin/tree/main/.agents/skills/launch-rl into .gemini/skills/launch-rl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-rl", 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 marin-community/marin launch-rlInstalls 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 marin-community/marin --skill launch-rl -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/marin-community/marin.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/launch-rl .github/skills/launch-rl && 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 "launch-rl" agent skill from https://github.com/marin-community/marin/tree/main/.agents/skills/launch-rl into .github/skills/launch-rl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-rl", 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 marin-community/marin --skill launch-rl -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install marin-community/marin launch-rl --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/marin-community/marin.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/launch-rl .opencode/skills/launch-rl && 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 "launch-rl" agent skill from https://github.com/marin-community/marin/tree/main/.agents/skills/launch-rl into .opencode/skills/launch-rl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-rl", 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
launch-rl- GitHub stars
- 3.9k
- Token cost
- ~894 tokens
- SKILL.md length
- 436 words
- Files
- 2
- Skills in repo
- 41
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main.
- RL launch files
- SKILL.md covers Define the experiment, Validate before launch, Submit and observe and Diagnose preflight gaps
- Calls uv
- SkyRLTopology changes
What it does
Launch Rl is an agent skill from marin-community/marin. Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main. Use for RL launch files, SkyRLRolePlan or SkyRLTopology changes, MarinSkyRL configuration, RL smoke tests, and requests to launch or relaunch RL on Iris.
Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Testing & QA, covering QA and bug reports. 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
- RL launch files
- SkyRLTopology changes
- MarinSkyRL configuration
- Requests to launch
Example prompts
- “/launch-rl”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit be1f5f1. 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
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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Launch Rl loads about 894 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 436 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 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 be1f5f1, republished under its Apache-2.0 licence (© marin-community). 436 words, ~894 tokens.
Download SKILL.mdSave it as
.claude/skills/launch-rl/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- launch-rl
- description
- Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main. Use for RL launch files, SkyRLRolePlan or SkyRLTopology changes, MarinSkyRL configuration, RL smoke tests, and requests to launch or relaunch RL on Iris.
Launch RL
Use the experiment's artifact graph as the launch interface. For the configuration model, role arithmetic, and ownership boundaries, read RL launching.
Define the experiment
- Define a Click
mainthat constructs and returns the requested terminalArtifactStephandles. - Decorate it with
@rl_build_options. Do not add another submission path to an experiment. - Put artifact identity and a fully explicit
SkyRLRolePlaninSkyRLSpec. Put cluster placement inIrisSkyRLExecution. - Render role geometry from the plan. Do not repeat DP, TP, PP, EP, engine count, placement, or batch sizes as independent literals or Hydra overrides.
- Express models and data as artifact dependencies. Pin tokenizer and source revisions; do not depend on an ambient checkpoint path or whatever happens to be on a worker.
- Keep the generated
SkyRLLaunchConfigYAML as the only Marin-to-MarinSkyRL boundary. Extend that config instead of adding request envelopes or internal per-field command-line flags.
Validate before launch
Run the main without --run first, using an immutable calendar version for a real experiment:
uv run python -m experiments.<module> --version YYYY.MM.DD <selection-options>Treat a preflight failure as a recipe error. Fix the source config or role plan instead of weakening the validator. Check the printed runtime commit, physical allocation, role geometry, entrypoint, batch sizes, artifact identities, output paths, and terminal stage.
Use a fresh RL artifact version whenever SkyRLRuntime.commit changes. The temporary checkpoint
root follows the artifact name and version, so reusing a version can make resume_mode=latest load
private Torch or distributed state written by the old runtime. Reuse an RL version across a repin
only when checkpoint compatibility has been established explicitly or resume points at a fresh
checkpoint root.
Before a large launch, run a smoke through the same strategy, artifact handoffs, and role geometry. Confirm the runtime contains the required backend fixes and that host resources, credentials, context budget, checkpoint/export policy, and W&B identity are explicit.
Show full SKILL.md (138 more words)Show less
Submit and observe
Launch through the same main:
uv run python -m experiments.<module> --version YYYY.MM.DD <selection-options> --runChoose the terminal stage explicitly when a main offers one. For example, use --stage rl when the
request is only to train; a default evaluation stage may add downstream GPU work.
For a live submission or inspection, use use-iris. Record the coordinator ID, child job ID,
artifact version, runtime commit, and topology in the task's durable surface. Verify all expected
tasks join, the configured model-loading path is active, optimizer steps advance, and terminal
checkpoint/export metadata exists before calling the smoke successful.
Diagnose preflight gaps
If a failure was deterministic from the artifact inputs, add a construction-time check with a behavior-focused regression test. Diagnose service outages, hardware faults, and data-dependent failures operationally. Cancel or resubmit only with current-thread authorization; a retry uses a fresh artifact version when the runtime commit changed.
© 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 1 other file in .agents/skills/launch-rl of marin-community/marin.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit be1f5f1
Compare with similar skills
Launch Rl 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 |
|---|---|---|---|---|---|---|
| Launch Rl this skillmarin-community/marin | 3.9k | — | ~894 | Automated safety check: Pass | Apache-2.0 | |
| Reproduce Chat Statesdifferent-ai/openwork | 24k | — | ~673 | Automated safety check: Pass | Custom licence | |
| Dynamo Jira TicketDynamoDS/Dynamo | 2k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Minimal Run And Auditlllllllama/RigorPilot-Skills | 497 | 2 repos | ~691 | Automated safety check: Pass | MIT | |
| Moav E2EMotherofallVPNs/MoaV | 448 | — | ~1.9k | Automated safety check: Notes | MIT | |
| Anchor Reprolynxlangya/techne | 105 | 1 repos | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
Dynamo Jira Ticket
DynamoDS/Dynamo
Create structured Jira tickets for Dynamo from bug reports, failing tests, or feature requests.
Minimal Run And Audit
lllllllama/RigorPilot-Skills
Rigor Run skill for README-first deep learning repo reproduction.
Moav E2E
MotherofallVPNs/MoaV
Run and debug MoaV's end-to-end tests — real protocol connectivity (client-test.sh) and the moav CLI smoke test — against a LIVE server, via the self-hosted e2e workflow or a local test VPS.
Anchor Repro
lynxlangya/techne
Reproduce a behavioral bug before fixing it, record the failing probe, and verify the fix with the same probe.
Creating A Coral Task
Human-Agent-Society/CORAL
Author a new CORAL task — the three pieces that must line up (task.yaml, seed/, a packaged grader/), the coral init → coral validate → smoke-test loop, and how to pick a grader pattern (stdout…
More from marin-community/marin
All 41 skills in this repoNoslop
marin-community/marin
Deslop, simplify, or review low-value tests and prose only when explicitly requested for a branch or diff.
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.
Marina Applet
marin-community/marin
Build, validate, publish, update, inspect, query, roll back, or archive a dynamic Marina applet.
Query Finelog
marin-community/marin
Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding.
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…
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…
Related
Categories
Questions about Launch Rl
What does Launch Rl do?
Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main. Launch Rl is an agent skill from marin-community/marin. Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main.
When should I use Launch Rl?
Launch Rl fits situations like: RL launch files; skyRLTopology changes; marinSkyRL configuration; requests to launch.
How do I install Launch Rl in Claude Code?
Run `npx skills add marin-community/marin --skill launch-rl -a claude-code`. Or copy the skill folder (.agents/skills/launch-rl in marin-community/marin) into .claude/skills/launch-rl in your project. Claude Code loads it when a task matches its description.
How do I install Launch Rl in Codex?
Run `npx skills add marin-community/marin --skill launch-rl -a codex`. Or copy the skill folder (.agents/skills/launch-rl in marin-community/marin) into .agents/skills/launch-rl in your project. Codex loads it when a task matches its description.
Can I use Launch Rl 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 launch-rl -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/launch-rl, .gemini/skills/launch-rl, .github/skills/launch-rl and .opencode/skills/launch-rl in your project.
What does Launch Rl need to run?
Going by SKILL.md and its folder, Launch Rl needs the command-line tools its instructions call (uv). Our summary lists: Python 3.
Does Launch Rl 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 Launch Rl 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 Launch Rl use?
Launch Rl 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 Launch Rl use?
About 894 tokens (SKILL.md is roughly 3.6k 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 Launch Rl?
Skills that share tags, products or a category with Launch Rl: Reproduce Chat States (different-ai/openwork, 24k stars), Dynamo Jira Ticket (DynamoDS/Dynamo, 2k stars), Minimal Run And Audit (lllllllama/RigorPilot-Skills, 497 stars) and Moav E2E (MotherofallVPNs/MoaV, 448 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Launch Rl?
marin-community (a GitHub organization) maintains it in marin-community/marin, which has 3,902 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 8, 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.