Refactoring Dbt Models
AltimateAI/data-engineering-skills
Safely refactors dbt models with downstream impact analysis.
VeOmni-specific checklist for feature development and refactoring.
Install Veomni Develop
$ npx skills add ByteDance-Seed/VeOmni --skill veomni-develop -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ByteDance-Seed/VeOmni veomni-develop --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/ByteDance-Seed/VeOmni.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/veomni-develop .claude/skills/veomni-develop && 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 "veomni-develop" agent skill from https://github.com/ByteDance-Seed/VeOmni/tree/main/.agents/skills/veomni-develop into .claude/skills/veomni-develop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "veomni-develop", 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/ByteDance-Seed/VeOmni/tree/main/.agents/skills/veomni-developType 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 ByteDance-Seed/VeOmni --skill veomni-develop -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ByteDance-Seed/VeOmni veomni-develop --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ByteDance-Seed/VeOmni.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/veomni-develop .agents/skills/veomni-develop && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "veomni-develop" agent skill from https://github.com/ByteDance-Seed/VeOmni/tree/main/.agents/skills/veomni-develop into .agents/skills/veomni-develop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "veomni-develop", 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 ByteDance-Seed/VeOmni --skill veomni-develop -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ByteDance-Seed/VeOmni veomni-develop --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ByteDance-Seed/VeOmni.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/veomni-develop .cursor/skills/veomni-develop && 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 "veomni-develop" agent skill from https://github.com/ByteDance-Seed/VeOmni/tree/main/.agents/skills/veomni-develop into .cursor/skills/veomni-develop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "veomni-develop", 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/ByteDance-Seed/VeOmni.git --path .agents/skills/veomni-develop--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 ByteDance-Seed/VeOmni --skill veomni-develop -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ByteDance-Seed/VeOmni veomni-develop --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ByteDance-Seed/VeOmni.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/veomni-develop .gemini/skills/veomni-develop && 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 "veomni-develop" agent skill from https://github.com/ByteDance-Seed/VeOmni/tree/main/.agents/skills/veomni-develop into .gemini/skills/veomni-develop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "veomni-develop", 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 ByteDance-Seed/VeOmni veomni-developInstalls 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 ByteDance-Seed/VeOmni --skill veomni-develop -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ByteDance-Seed/VeOmni.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/veomni-develop .github/skills/veomni-develop && 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 "veomni-develop" agent skill from https://github.com/ByteDance-Seed/VeOmni/tree/main/.agents/skills/veomni-develop into .github/skills/veomni-develop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "veomni-develop", 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 ByteDance-Seed/VeOmni --skill veomni-develop -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ByteDance-Seed/VeOmni veomni-develop --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ByteDance-Seed/VeOmni.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/veomni-develop .opencode/skills/veomni-develop && 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 "veomni-develop" agent skill from https://github.com/ByteDance-Seed/VeOmni/tree/main/.agents/skills/veomni-develop into .opencode/skills/veomni-develop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "veomni-develop", 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
veomni-develop- GitHub stars
- 2.2k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 755 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
VeOmni-specific checklist for feature development and refactoring.
- Works in 4 steps: Baseline first: run pytest tests/ before… → One change per commit: ONE structural… → Never batch multiple refactoring steps… → …
- Tasks that involve Refactoring
- SKILL.md covers Impact Analysis, Refactoring Safety Rules, Common Traps and Documentation, plus 2 more sections
- Calls pytest and make; reaches github.com
What it does
Veomni Develop is an agent skill from ByteDance-Seed/VeOmni. VeOmni-specific checklist for feature development and refactoring. Covers impact analysis across modalities, trainer hierarchy, data pipeline, and distributed code. Use before implementing any non-trivial change. For model-specific or ops-specific work, use veomni-new-model or veomni-new-op instead. Trigger: 'add feature', 'implement', 'refactor', 'reorganize', 'new capability'.
Its SKILL.md is about 1.5k 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 Development, covering Refactoring and Data pipelines and ETL. The repository describes itself as: VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Refactoring
- Tasks that involve Data pipelines and ETL
Example prompts
- “add feature”
- “implement”
- “refactor”
- “/veomni-develop”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Baseline first: run pytest tests/ before any change, record results.
- One change per commit: ONE structural change → update ALL callers → verify tests match baseline → commit.
- Never batch multiple refactoring steps into one commit.
- Check baseline again at the end — results must be identical.
What it can do on your machine
Read from SKILL.md and the folder at commit 16c94aa. 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:
pytestmake
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
github.com
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
Veomni Develop loads about 1.5k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 755 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 ByteDance-Seed/VeOmni at commit 16c94aa, republished under its Apache-2.0 licence (© ByteDance-Seed). 755 words, ~1,541 tokens.
Download SKILL.mdSave it as
.claude/skills/veomni-develop/SKILL.md (or your agent's skills folder).- name
- veomni-develop
- description
- VeOmni-specific checklist for feature development and refactoring. Covers impact analysis across modalities, trainer hierarchy, data pipeline, and distributed code. Use before implementing any non-trivial change. For model-specific or ops-specific work, use veomni-new-model or veomni-new-op instead. Trigger: 'add feature', 'implement', 'refactor', 'reorganize', 'new capability'.
Impact Analysis
Before implementing, check which areas your change affects:
| Area | What to check | Why it matters |
|---|---|---|
veomni/trainer/ | All trainer subclasses (TextTrainer, VLMTrainer, DitTrainer, RL trainers) | Changing BaseTrainer method signatures breaks all subclasses |
veomni/data/data_collator.py | All modalities (text, VLM, DiT) | Collators are tightly coupled to model-specific preprocessing |
veomni/distributed/ | FSDP2 + ExtraParallel/MoE/SP paths | Shared distributed code is used by many downstream modalities |
veomni/models/auto.py, loader.py | Model registry, import-time side effects | MODELING_REGISTRY is populated at import time; moving registrations breaks loading |
configs/ | YAML config keys | Renaming config keys breaks existing training configs silently |
veomni/models/transformers/*/ | __init__.py registration entry points | Every transformers-family LLM/VLM/Omni model ships a patchgen-generated path under generated/; never import or call legacy modeling_<m>.py or apply_veomni_<m>_patch() (these no longer exist). The non-transformers-architecture models (flux, movqgan, wan) have no generated/ and patch through device_patch.py or direct modeling — check the directory before assuming |
Refactoring Safety Rules
When restructuring code (same behavior, better structure):
- Baseline first: run
pytest tests/before any change, record results. - One change per commit: ONE structural change → update ALL callers → verify tests match baseline → commit.
- Never batch multiple refactoring steps into one commit.
- Check baseline again at the end — results must be identical.
Common Traps
veomni.models.autoregistration depends on import-time side effects — moving registrations into functions or delaying them breaks model loading.- Renaming config keys silently breaks existing YAML configs in
configs/— grep all YAML files first. veomni.distributedmodules feed into ExtraParallel/MoE/SP — touching shared code may affect every modality, so run the cross-cutting parallel tests.- Data collators in
veomni/data/data_collator.pyare coupled toDEFAULT_DATA_COLLATE_INFO— adding new tensor keys requires updating the collate info table. MainCollatorhas strict SP ordering (pad → slice → FA kwargs → slice position_ids) — reordering breaks SP correctness.position_ids == 0marks segment boundaries for FA varlen — any transform that produces position_ids must preserve this convention.
Documentation
Before committing, check if the change requires documentation updates:
- New/changed API → update or create docs in
docs/. - New/changed extension point (a mixin, hook, callback or base-class method that other modules or models must implement) → write a dedicated page, see below.
- New/changed config fields → update config examples in
configs/and relevant docs. - Architecture change → update
.agents/knowledge/architecture.md. - New constraint discovered → add to
.agents/knowledge/constraints.md.
Show full SKILL.md (398 more words)Show less
Documenting an extension point
A contract that other code has to implement gets its own page in the same PR,
not a bullet in a usage doc. Mirror the source layout (SeedOmni mixins go to
docs/seed_omni/mixins/<name>.md) and add the page to a toctree in
docs/index.md: the docs build runs with -W, so a page outside every toctree
fails CI.
For each function in the contract, the page states:
- Who owns it: the module must implement it, must call it, may override it, or the framework provides it and it must not be overridden.
- What it does: inputs, return value, units, and edge cases (for example what it must return for empty input).
- Where the framework calls it: the exact call site, not only the file that defines it.
- The end effect: the metrics, outputs or behavior a user observes, and what happens for a module that does not opt in.
Also include a minimal opt-in example that matches the real module layout, the call flow of one step or request as a nested list, the rules a correct implementation must follow, and the tests that cover the contract.
Link every symbol and call site with a path relative to the doc plus a line
anchor, e.g.
[metric_meter_add](../../../veomni/models/seed_omni/mixins/metric_meter_mixin.py#L120),
so the reader can jump to the code from the IDE and from GitHub. Prefer this
over https://github.com/.../blob/main/... URLs, which do not resolve until the
PR merges and do not open in the IDE. Keep call flows out of code fences: links
inside a fence are not clickable. Line anchors drift when code above them
changes, so re-check them after every code change in the PR (see
/veomni-fix-docs). Build with make -C docs html SPHINXOPTS=-W before
committing. Reference page: docs/seed_omni/mixins/metric_meter.md.
Tests
Follow .agents/knowledge/testing.md. In short: extend an existing
CI-enumerated test before creating a new file. If you do create one, check its
path against the table there and wire it into the workflow that owns that path
— the directory-level entries (tests/data/, tests/checkpoints/, tests/ops/ on GPU,
tests/parallel/context_parallel/ on GPU) need no line, e2e paths belong to
{gpu,npu}_e2e_test.yml, and everything else is invisible to CI until it is
listed. A pure refactor with existing coverage does not need a new test — say
so in the PR instead of adding one.
When to Use Other Skills
- New model →
/veomni-new-model - New op/kernel →
/veomni-new-op - Bug fix or debugging →
/veomni-debug - Dependency update →
/veomni-uv-update
© ByteDance-Seed, 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/veomni-develop of ByteDance-Seed/VeOmni.
Open the folder on GitHubat commit 16c94aa
Compare with similar skills
Veomni Develop 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 |
|---|---|---|---|---|---|---|
| Veomni Develop this skillByteDance-Seed/VeOmni | 2.2k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Refactoring Dbt ModelsAltimateAI/data-engineering-skills | 128 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Dependency Analysisrevfactory/harness-100 | 1.3k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| R Empirical Financeaspi6246/Claude-Code-Skills-for-Academics | 159 | — | ~1.3k | Automated safety check: Pass | None | |
| Archifymolvqingtai/WebChat | 2.6k | — | ~5.6k | Automated safety check: Pass | MIT | |
| Stereopy MaintainerSTOmics/Stereopy | 293 | — | ~1.7k | Automated safety check: Pass | MIT |
Similar skills
Dependency Analysis
revfactory/harness-100
Tools and methodologies for analyzing codebase dependency graphs and quantitatively measuring coupling/cohesion.
R Empirical Finance
aspi6246/Claude-Code-Skills-for-Academics
Conventions for writing empirical finance R code with data.table, fixest, arrow, and ggplot2.
Archify
molvqingtai/WebChat
Create professional architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as standalone HTML files with SVG graphics, a built-in dark/light theme toggle, and one-click export to…
Stereopy Maintainer
STOmics/Stereopy
Stereopy project maintenance guide for code review, bug fixing, and feature development.
Python Error Handling
wshobson/agents
Python error handling patterns including input validation, exception hierarchies, and partial failure handling.
More from ByteDance-Seed/VeOmni
All 10 skills in this repoCreate PR
ByteDance-Seed/VeOmni
Create a pull request for the current branch. An agent skill from ByteDance-Seed/VeOmni.
Veomni Debug
ByteDance-Seed/VeOmni
A skill your agent uses for ANY bug, error, crash, wrong output, loss divergence, gradient explosion, test failure, CUDA error, distributed training hang, checkpoint load failure, or unexpected…
Veomni New Model
ByteDance-Seed/VeOmni
A skill your agent uses when adding support for a new model to VeOmni.
Veomni New Op
ByteDance-Seed/VeOmni
A skill your agent uses when adding a new optimized kernel or operator to veomni/ops/.
Veomni Patchgen Model
ByteDance-Seed/VeOmni
Author or refresh a VeOmni model's patchgen-generated modeling under generated/ — GPU and/or NPU config, dense or MoE, text / VLM / Omni.
Veomni Profile
ByteDance-Seed/VeOmni
A skill your agent uses for performance profiling and optimization.
Related
Categories
Questions about Veomni Develop
What does Veomni Develop do?
VeOmni-specific checklist for feature development and refactoring. Veomni Develop is an agent skill from ByteDance-Seed/VeOmni. VeOmni-specific checklist for feature development and refactoring.
When should I use Veomni Develop?
Veomni Develop fits situations like: tasks that involve Refactoring; tasks that involve Data pipelines and ETL.
How do I install Veomni Develop in Claude Code?
Run `npx skills add ByteDance-Seed/VeOmni --skill veomni-develop -a claude-code`. Or copy the skill folder (.agents/skills/veomni-develop in ByteDance-Seed/VeOmni) into .claude/skills/veomni-develop in your project. Claude Code loads it when a task matches its description.
How do I install Veomni Develop in Codex?
Run `npx skills add ByteDance-Seed/VeOmni --skill veomni-develop -a codex`. Or copy the skill folder (.agents/skills/veomni-develop in ByteDance-Seed/VeOmni) into .agents/skills/veomni-develop in your project. Codex loads it when a task matches its description.
Can I use Veomni Develop 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 ByteDance-Seed/VeOmni --skill veomni-develop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/veomni-develop, .gemini/skills/veomni-develop, .github/skills/veomni-develop and .opencode/skills/veomni-develop in your project.
What does Veomni Develop need to run?
Going by SKILL.md and its folder, Veomni Develop needs the command-line tools its instructions call (pytest and make).
Does Veomni Develop access the network?
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Veomni Develop 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 Veomni Develop use?
Veomni Develop 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 Veomni Develop use?
About 1.5k tokens (SKILL.md is roughly 6.2k 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 Veomni Develop?
Skills that share tags, products or a category with Veomni Develop: Refactoring Dbt Models (AltimateAI/data-engineering-skills, 128 stars), Dependency Analysis (revfactory/harness-100, 1.3k stars), R Empirical Finance (aspi6246/Claude-Code-Skills-for-Academics, 159 stars) and Archify (molvqingtai/WebChat, 2.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Veomni Develop?
ByteDance-Seed (a GitHub organization) maintains it in ByteDance-Seed/VeOmni, which has 2,235 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 9, 2026.
Source: ByteDance-Seed/VeOmni on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.