Tinker
sundial-org/skills
Fine-tune LLMs using the Tinker API. An agent skill from sundial-org/skills.
Router for adding a diffusion or omni pipeline to verl-omni.
Install Add Pipeline
$ npx skills add verl-project/verl-omni --skill add-pipeline -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install verl-project/verl-omni add-pipeline --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/verl-project/verl-omni.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/add-pipeline .claude/skills/add-pipeline && 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 "add-pipeline" agent skill from https://github.com/verl-project/verl-omni/tree/main/.agents/skills/add-pipeline into .claude/skills/add-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-pipeline", 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/verl-project/verl-omni/tree/main/.agents/skills/add-pipelineType 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 verl-project/verl-omni --skill add-pipeline -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install verl-project/verl-omni add-pipeline --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/verl-project/verl-omni.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/add-pipeline .agents/skills/add-pipeline && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "add-pipeline" agent skill from https://github.com/verl-project/verl-omni/tree/main/.agents/skills/add-pipeline into .agents/skills/add-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-pipeline", 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 verl-project/verl-omni --skill add-pipeline -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install verl-project/verl-omni add-pipeline --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/verl-project/verl-omni.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/add-pipeline .cursor/skills/add-pipeline && 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 "add-pipeline" agent skill from https://github.com/verl-project/verl-omni/tree/main/.agents/skills/add-pipeline into .cursor/skills/add-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-pipeline", 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/verl-project/verl-omni.git --path .agents/skills/add-pipeline--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 verl-project/verl-omni --skill add-pipeline -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install verl-project/verl-omni add-pipeline --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/verl-project/verl-omni.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/add-pipeline .gemini/skills/add-pipeline && 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 "add-pipeline" agent skill from https://github.com/verl-project/verl-omni/tree/main/.agents/skills/add-pipeline into .gemini/skills/add-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-pipeline", 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 verl-project/verl-omni add-pipelineInstalls 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 verl-project/verl-omni --skill add-pipeline -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/verl-project/verl-omni.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/add-pipeline .github/skills/add-pipeline && 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 "add-pipeline" agent skill from https://github.com/verl-project/verl-omni/tree/main/.agents/skills/add-pipeline into .github/skills/add-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-pipeline", 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 verl-project/verl-omni --skill add-pipeline -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install verl-project/verl-omni add-pipeline --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/verl-project/verl-omni.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/add-pipeline .opencode/skills/add-pipeline && 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 "add-pipeline" agent skill from https://github.com/verl-project/verl-omni/tree/main/.agents/skills/add-pipeline into .opencode/skills/add-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-pipeline", 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
add-pipeline- GitHub stars
- 1.2k
- Token cost
- ~1k tokens
- SKILL.md length
- 381 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Router for adding a diffusion or omni pipeline to verl-omni.
- Works in 5 steps: Classify, on two axes → Find the closest pair to copy → Work the guide's checklist literally → …
- Integrating a new model
- SKILL.md covers Step 0 — Classify, on two axes, Step 1 — Find the closest pair…, Step 2 — Work the guide's… and Step 3 — When the run is wrong…, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Add Pipeline is an agent skill from verl-project/verl-omni. Router for adding a diffusion or omni pipeline to verl-omni. Classifies the task (new architecture vs new algorithm; policy-gradient vs direct-preference) and points at the authoritative guide under docs/contributing/. Use when integrating a new model, or a new model+algorithm pair such as flow-GRPO / DPO / NFT / DanceGRPO.
Its SKILL.md is about 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 Fine-tuning, Reinforcement learning and Diffusion and image models. The repository describes itself as: Multimodal RL training framework for diffusion & omni models. The licence is Apache-2.0.
When your agent uses it
- Integrating a new model
- A new model+algorithm pair such as flow-GRPO / DPO / NFT / DanceGRPO
Example prompts
- “/add-pipeline”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 022b110. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Add Pipeline loads about 1k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 381 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 verl-project/verl-omni at commit 022b110, republished under its Apache-2.0 licence (© verl-project). 381 words, ~1,007 tokens.
Download SKILL.mdSave it as
.claude/skills/add-pipeline/SKILL.md (or your agent's skills folder).- name
- add-pipeline
- description
- Router for adding a diffusion or omni pipeline to verl-omni. Classifies the task (new architecture vs new algorithm; policy-gradient vs direct-preference) and points at the authoritative guide under docs/contributing/. Use when integrating a new model, or a new model+algorithm pair such as flow-GRPO / DPO / NFT / DanceGRPO.
Add a Pipeline
docs/contributing/ owns the steps and the final checklist for every case below.
This skill routes you to the right guide and adds only what those guides leave
out. Open the guide — do not work from a remembered procedure.
Step 0 — Classify, on two axes
Architecture and algorithm integration are orthogonal: one algorithm reaches any number of architectures through the adapter pair, and vice versa.
Adding an algorithm?
| Trains from | Family | Guide |
|---|---|---|
| reverse-trajectory logprob ratios + advantages (FlowGRPO, MixGRPO, DanceGRPO) | policy gradient | integrating_a_new_policy_gradient_algorithm_for_diffusion_model.md |
| final samples, rewards, or chosen/rejected pairs (offline DPO, DiffusionNFT) | direct preference | integrating_a_new_direct_preference_algorithm_for_diffusion_model.md |
Read ## Classify the Algorithm First at the top of the direct-preference guide
even if you land on the policy-gradient one: it also splits offline vs online and
maps each family to its trainer (PolicyGradientRayTrainer /
DirectPreferenceRayTrainer) and FSDP engine. That decides
algorithm.trainer_type and algorithm.sample_source, which nothing else in the
repo infers for you.
Adding an architecture?
| Model | Guide |
|---|---|
| diffusers text-to-image | integrating_a_diffusion_model.md — read first, the rest extend it |
| diffusers image-edit / I2I | integrating_an_i2i_diffusion_model.md |
a nn.Module that diffusers cannot load | integrating_a_non_diffusers_model.md |
| multimodal autoregressive (omni) | integrating_an_omni_model.md |
| step execution on an adapter that already works | integrating_a_stepwise_continuous_batching_model.md |
Both at once? Architecture first — an algorithm can only be paired with an adapter that already exists.
Step 1 — Find the closest pair to copy
List the live registry rather than guessing at a template:
grep -rhoE '@[A-Za-z]+\.register\([^)]*\)' verl_omni/pipelines/*/[dv]*.py | sort -uDiffusionModelBase rows are training adapters, VllmOmniPipelineBase rows are
rollout adapters; a pair with no rollout row reuses another package's pipeline.
Copy the closest package, then share rather than fork
(code-style).
Show full SKILL.md (177 more words)Show less
Step 2 — Work the guide's checklist literally
Every guide but the omni one ends in a - [ ] checklist (the omni guide ends in its
own ## Common pitfalls instead). Work it item by item; between them the checklists
cover what is most often missed: the star-import in verl_omni/pipelines/__init__.py
(without it the adapter is invisible and nothing errors at import time), mirroring a
new pipeline config field in both diffusion_rollout.yaml and
diffusion_model.yaml, and wiring a smoke test into tests/gpu_smoke/.
Step 3 — When the run is wrong rather than broken
docs/contributing/common_pitfalls.md is symptom-first: fp32 latent/scheduler
precision loss, RoPE sequence-length mismatch, per-request vs per-GPU SDE seeding.
Check it before debugging a reward curve that trains but diverges from diffusers.
Step 4 — Test, then open the PR
Adapter-boundary CPU tests: run-cpu-tests. Title, trailers, duplicate-work checks: commit-and-pr.
<!--
MAINTAINER GUIDE — this file must stay a router. If you catch yourself restating a
guide's steps here, edit the guide instead. Update the tables when a guide is
added, renamed, or changes scope. Also add or update the matching link in
CONTRIBUTING.md (and the Developer Guide toctree).
-->© verl-project, 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/add-pipeline of verl-project/verl-omni.
Open the folder on GitHubat commit 022b110
Compare with similar skills
Add Pipeline 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 |
|---|---|---|---|---|---|---|
| Add Pipeline this skillverl-project/verl-omni | 1.2k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Tinkersundial-org/skills | 153 | — | ~1.2k | Automated safety check: Pass | None | |
| Train RlOpenPipe/ART | 11k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Qwopus27b Rl TrainingR6410418/Jackrong-llm-finetuning-guide | 1.7k | — | ~830 | Automated safety check: Pass | Apache-2.0 | |
| Fine Tuning With TrlOrchestra-Research/AI-Research-SKILLs | 13k | 6 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Optim AgentOptim-Agent/optim-agent | 801 | — | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
Train Rl
OpenPipe/ART
RL training reference for the ART framework. An agent skill from OpenPipe/ART.
Qwopus27b Rl Training
R6410418/Jackrong-llm-finetuning-guide
Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO.
Fine Tuning With Trl
Orchestra-Research/AI-Research-SKILLs
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training.
Optim Agent
Optim-Agent/optim-agent
A skill your agent uses when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference, quantitative strategies…
Safactory Workflows
AI45Lab/SAfactory
Integrate a benchmark or custom environment into SAfactory using fixed adapter templates and local contract tests, optionally run Docker/RJob evaluation, or prepare GRPO/RL training.
More from verl-project/verl-omni
Add Reward Score
verl-project/verl-omni
Guide for adding a new reward scorer to verl-omni and wiring it into a run.
Profile
verl-project/verl-omni
Route a verl-omni performance investigation to the right tool and capture a usable trace.
Run Cpu Tests
verl-project/verl-omni
How to write and run verl-omni CPU tests (testoncpu.py) that exercise adapters, rewards, and configs without a GPU or model weights.
Commit And PR
verl-project/verl-omni
verl-omni commit message + PR conventions and the mandatory contribution policy.
Self Review
verl-project/verl-omni
Review your own verl-omni branch against the project rubric before opening or updating a PR.
Train Infer Consistency
verl-project/verl-omni
Route verl-omni training/inference consistency checks through MindStudio's MSProbe collection and root-cause analysis skills.
Related
Categories
Questions about Add Pipeline
What does Add Pipeline do?
Router for adding a diffusion or omni pipeline to verl-omni. Add Pipeline is an agent skill from verl-project/verl-omni. Router for adding a diffusion or omni pipeline to verl-omni.
When should I use Add Pipeline?
Add Pipeline fits situations like: integrating a new model; A new model+algorithm pair such as flow-GRPO / DPO / NFT / DanceGRPO.
How do I install Add Pipeline in Claude Code?
Run `npx skills add verl-project/verl-omni --skill add-pipeline -a claude-code`. Or copy the skill folder (.agents/skills/add-pipeline in verl-project/verl-omni) into .claude/skills/add-pipeline in your project. Claude Code loads it when a task matches its description.
How do I install Add Pipeline in Codex?
Run `npx skills add verl-project/verl-omni --skill add-pipeline -a codex`. Or copy the skill folder (.agents/skills/add-pipeline in verl-project/verl-omni) into .agents/skills/add-pipeline in your project. Codex loads it when a task matches its description.
Can I use Add Pipeline 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 verl-project/verl-omni --skill add-pipeline -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/add-pipeline, .gemini/skills/add-pipeline, .github/skills/add-pipeline and .opencode/skills/add-pipeline in your project.
What does Add Pipeline need to run?
SKILL.md names no scripts, command-line tools or credentials: Add Pipeline is instructions for the agent only.
Does Add Pipeline 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 Add Pipeline 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 Add Pipeline use?
Add Pipeline 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 Add Pipeline use?
About 1k tokens (SKILL.md is roughly 4k 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 Add Pipeline?
Skills that share tags, products or a category with Add Pipeline: Tinker (sundial-org/skills, 153 stars), Train Rl (OpenPipe/ART, 11k stars), Qwopus27b Rl Training (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars) and Fine Tuning With Trl (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Add Pipeline?
verl-project (a GitHub organization) maintains it in verl-project/verl-omni, which has 1,210 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 9, 2026.
Source: verl-project/verl-omni on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.