Agent skill

Veomni Fix Docs

by ByteDance-Seed in ByteDance-Seed/VeOmni

Audit and correct VeOmni documentation links, Markdown, language, and technical claims against repository sources.

Apache-2.0Auto-check passedDocuments & Office

Install Veomni Fix Docs

skills CLI
$ npx skills add ByteDance-Seed/VeOmni --skill veomni-fix-docs -a claude-code

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

GitHub CLI
$ gh skill install ByteDance-Seed/VeOmni veomni-fix-docs --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/ByteDance-Seed/VeOmni.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/veomni-fix-docs .claude/skills/veomni-fix-docs && 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
veomni-fix-docs
GitHub stars
2.2k
Token cost
~1.4k tokens
SKILL.md length
756 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Audit and correct VeOmni documentation links, Markdown, language, and technical claims against repository sources.

  • Works in 3 steps: Read the request and applicable… → Run git status --short before editing.… → Record the repository revision and which…
  • Documentation scans
  • SKILL.md covers Scope and baseline, Mechanical checks, Meaning and language and Edit and validate
  • Calls git, python and rg

What it does

Veomni Fix Docs is an agent skill from ByteDance-Seed/VeOmni. Audit and correct VeOmni documentation links, Markdown, language, and technical claims against repository sources. Use for documentation scans, broken links, typos, or stale instructions in README, docs, examples, and agent guidance.

Its SKILL.md is about 1.4k 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 Documents & Office, covering Markdown. It works with Git. 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

  • Documentation scans
  • Stale instructions in README

Example prompts

  • “/veomni-fix-docs”

Requirements

  • Python 3

Workflow steps

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

  1. Read the request and applicable AGENTS.md. A review-only request calls for findings, not edits. A correction request permits verified…
  2. Run git status --short before editing. Preserve unrelated changes. Use requested paths; otherwise inspect tracked Markdown/MDX in…
  3. Record the repository revision and which files or directories you actually checked. For large scopes, work in batches and report any…

What it can do on your machine

Read from SKILL.md and the folder at commit 8791a71. 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:

    • git
    • python
    • rg

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

  • Network

    No URLs in SKILL.md. Its commands use git, 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

Veomni Fix Docs loads about 1.4k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 756 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 8791a71, republished under its Apache-2.0 licence (© ByteDance-Seed). 756 words, ~1,431 tokens.

Download SKILL.mdSave it as .claude/skills/veomni-fix-docs/SKILL.md (or your agent's skills folder).
name
veomni-fix-docs
description
Audit and correct VeOmni documentation links, Markdown, language, and technical claims against repository sources. Use for documentation scans, broken links, typos, or stale instructions in README, docs, examples, and agent guidance.

Fix VeOmni Documentation

Audit documentation and apply only corrections supported by evidence. This skill is self-contained: it requires no bundled script, extra Python package, GPU, or network connection. Use the repository's available search, build, and validation tools; do not imply that a manual search is an exhaustive parser-based scan.

Scope and baseline

  1. Read the request and applicable AGENTS.md. A review-only request calls for findings, not edits. A correction request permits verified documentation fixes, not unrelated code changes or a push.
  2. Run git status --short before editing. Preserve unrelated changes. Use requested paths; otherwise inspect tracked Markdown/MDX in README.md, docs/, .agents/, and component documentation. Include relevant new unignored files.
  3. Record the repository revision and which files or directories you actually checked. For large scopes, work in batches and report any uninspected area instead of claiming full coverage.

Mechanical checks

Enumerate candidates with git ls-files --cached --others --exclude-standard -- '*.md' '*.mdx'. Do not use rg --files, which skips hidden paths such as .agents/, or plain git ls-files, which omits untracked files. Search for Markdown links/images (including reference definitions), HTML a[href] and img[src], headings, code fences, and repeated words. Search output is a candidate list, not proof that all links were found: multiline Markdown, footnotes, comments, code spans, MyST directives, and HTML can defeat simple patterns. Use an available Markdown parser or renderer when comprehensive coverage matters, without introducing a permanent dependency just for this skill.

For each candidate link or image:

  • Resolve a relative path from the containing document, including .., URL decoding, and exact filename case. Do not resolve every link from the repository root. Check whether an absolute-site path is handled by the documentation renderer.
  • For a fragment, inspect the target heading or explicit HTML ID and the intended renderer's generated permalink. GitHub and Sphinx/MyST can produce different IDs, especially for Emoji, linked heading text, punctuation, and duplicate headings. Do not remove an icon or change a heading merely to make a guessed fragment match.
  • For a source-file link with a line anchor (file.py#L142), open the target line and confirm it is the symbol or statement the link text names. Line anchors drift silently when code above them changes; re-point a stale anchor to the current line rather than dropping it.
  • Check reference-style links against their definitions. Exclude literal code and commented examples unless the user asks to review examples.
  • Treat malformed URLs, suspicious duplicates, missing spaces after heading markers, and unmatched fences as review candidates. Verify context before editing. Do not guess a replacement URL or destination.
  • Check external links only if network access is available and authorized; otherwise mark them unverified. MyST labels/directives, generated targets, MDX/JSX routing, and site-specific URL rules need renderer-specific checks.

If a target is missing or ambiguous, search the repository for its intended replacement. Fix only when the destination is clear; otherwise report the uncertainty with file and line.

Show full SKILL.md (280 more words)Show less

Meaning and language

Review prose outside code blocks for objective spelling, grammar, punctuation, incomplete sentences, contradictory guidance, and outdated terminology. Verify commands, working directories, CLI flags, configuration paths and keys, defaults, versions, hardware claims, model registration examples, and API names against implementation, tests, current configs, CI, or Dockerfiles. rg definitions and call sites rather than relying on nearby prose. For procedures, check prerequisites and ordering; for examples, preserve executable quoting, indentation, and placeholders.

Apply a technical correction when an authoritative repository source proves it. Apply a language correction when there is only one reasonable reading. If evidence is insufficient, retain the original and report the candidate with the source checked and what remains uncertain. Do not turn a completed link check into a claim of semantic correctness.

Edit and validate

  1. Keep edits minimal. Preserve document language, voice, heading structure, Emoji, intentional hard breaks, and Markdown formatting. Change code blocks or commands only with evidence. Update directly affected cross-references.
  2. Recheck each changed link and claim against its target or source. Run available repository checks, such as python scripts/ci/check_doc_task_paths.py for task paths and python scripts/ci/check_agent_doc_paths.py for agent paths. When documentation dependencies are available, build Sphinx HTML and inspect warnings; for changed anchors, compare rendered links with actual generated IDs. A successful build alone does not prove every anchor is correct.
  3. Run applicable formatting/quality checks, git diff --check, and inspect the final diff. Do not install heavy training dependencies solely for documentation review.
  4. Report the actual scope, fixes and supporting evidence, checks run, false positives, and unverified areas (especially external URLs, MyST/MDX constructs, and semantic claims). Never state that all documentation is error-free unless that conclusion is genuinely supported.

© 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-fix-docs of ByteDance-Seed/VeOmni.

Open the folder on GitHubat commit 8791a71

Compare with similar skills

Veomni Fix Docs 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.

Veomni Fix Docs compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Veomni Fix Docs this skillByteDance-Seed/VeOmni2.2k—~1.4kAutomated safety check: PassApache-2.0
Cut Releasespiculedata/saiku1.3k—~502Automated safety check: PassApache-2.0
Ljg Pushlijigang/ljg-skills7.5k—~1.4kAutomated safety check: PassMIT
Flow Next Visualgmickel/flow-next709—~2.4kAutomated safety check: NotesMIT
Changelog Writerjihe520/mindpocket350—~1.1kAutomated safety check: PassNone
Notcrawlopenclaw/notcrawl134—~698Automated safety check: PassMIT

Similar skills

  • Cut Release

    spiculedata/saiku

    Cut a Saiku release via Gitflow — version bump, release branch, PR to main, tag, back-merge, and post-release chores.

    1.3k GitHub stars~502 tokensUpdated today
    DevelopmentAuto-check passed
  • Ljg Push

    lijigang/ljg-skills

    把 ~/.agents/skills/ljg- 里所有更新过的 skills 同步到 github repo (ljg-skills),先推 master 分支(org-mode 输出风格),再切 md 分支(markdown 输出风格)做基础 markdown 化后推。Use when user says '/ljg-push', 'push skills', '推送 skills'…

    7.5k GitHub stars~1.4k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Flow Next Visual

    gmickel/flow-next

    Restate a spec, a task, a diff, or the current topic visually as a compact markdown digest.

    709 GitHub stars~2.4k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Changelog Writer

    jihe520/mindpocket

    A skill your agent uses when the user wants to create or update a changelog, release notes, product updates, or an MDX changelog page from git history or local code changes.

    350 GitHub stars~1.1k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Notcrawl

    openclaw/notcrawl

    A skill your agent uses for local Notion archive search, sync freshness, Markdown/database exports, git-share snapshots, and Notcrawl repo/release work.

    134 GitHub stars~698 tokensUpdated yesterday
    DatabasesAuto-check passed
  • 抓取并汇总"数据库、AI、GitHub、AI 论文"近 1 周新闻,输出图文并茂(含 mermaid 图)的 markdown 周报到当前项目的 markdown/ 目录。覆盖 10 个数据源:postgresweekly.com/issues(自动解析最新 issue…

    8.6k GitHub stars~1.2k tokensUpdated 2 days ago
    DatabasesAuto-check passed

More from ByteDance-Seed/VeOmni

All 10 skills in this repo
  • Create PR

    ByteDance-Seed/VeOmni

    Create a pull request for the current branch. An agent skill from ByteDance-Seed/VeOmni.

    2.2k GitHub stars~1.6k tokensUpdated yesterday
    Auto-check: notes
  • 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…

    2.2k GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed
  • Veomni New Model

    ByteDance-Seed/VeOmni

    A skill your agent uses when adding support for a new model to VeOmni.

    2.2k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Veomni New Op

    ByteDance-Seed/VeOmni

    A skill your agent uses when adding a new optimized kernel or operator to veomni/ops/.

    2.2k GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed
  • 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.

    2.2k GitHub stars~9.6k tokensUpdated yesterday
    Auto-check passed
  • Veomni Profile

    ByteDance-Seed/VeOmni

    A skill your agent uses for performance profiling and optimization.

    2.2k GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Veomni Fix Docs

What does Veomni Fix Docs do?

Audit and correct VeOmni documentation links, Markdown, language, and technical claims against repository sources. Veomni Fix Docs is an agent skill from ByteDance-Seed/VeOmni. Audit and correct VeOmni documentation links, Markdown, language, and technical claims against repository sources.

When should I use Veomni Fix Docs?

Veomni Fix Docs fits situations like: documentation scans; stale instructions in README.

How do I install Veomni Fix Docs in Claude Code?

Run `npx skills add ByteDance-Seed/VeOmni --skill veomni-fix-docs -a claude-code`. Or copy the skill folder (.agents/skills/veomni-fix-docs in ByteDance-Seed/VeOmni) into .claude/skills/veomni-fix-docs in your project. Claude Code loads it when a task matches its description.

How do I install Veomni Fix Docs in Codex?

Run `npx skills add ByteDance-Seed/VeOmni --skill veomni-fix-docs -a codex`. Or copy the skill folder (.agents/skills/veomni-fix-docs in ByteDance-Seed/VeOmni) into .agents/skills/veomni-fix-docs in your project. Codex loads it when a task matches its description.

Can I use Veomni Fix Docs 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-fix-docs -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-fix-docs, .gemini/skills/veomni-fix-docs, .github/skills/veomni-fix-docs and .opencode/skills/veomni-fix-docs in your project.

What does Veomni Fix Docs need to run?

Going by SKILL.md and its folder, Veomni Fix Docs needs the command-line tools its instructions call (git, python and rg). Our summary lists: Python 3.

Does Veomni Fix Docs access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Veomni Fix Docs 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 Fix Docs use?

Veomni Fix Docs 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 Fix Docs use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 Fix Docs?

Skills that share tags, products or a category with Veomni Fix Docs: Cut Release (spiculedata/saiku, 1.3k stars), Ljg Push (lijigang/ljg-skills, 7.5k stars), Flow Next Visual (gmickel/flow-next, 709 stars) and Changelog Writer (jihe520/mindpocket, 350 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Veomni Fix Docs?

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 10, 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.