Agent skill

Video Router

by Orkas-AI in Orkas-AI/Orkas-VideoStudio

Read this FIRST on any video-production request to pick and lock the line — generate (AI footage), compose (designed HTML), edit (cut real footage), or AUTO end-to-end.

MITAuto-check passedMedia & Creative

Install Video Router

skills CLI
$ npx skills add Orkas-AI/Orkas-VideoStudio --skill video-router -a claude-code

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

GitHub CLI
$ gh skill install Orkas-AI/Orkas-VideoStudio video-router --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/Orkas-AI/Orkas-VideoStudio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/skills/video-router .claude/skills/video-router && 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
video-router
GitHub stars
499
Token cost
~1.5k tokens
SKILL.md length
760 words
Files
2 (incl. references)
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Read this FIRST on any video-production request to pick and lock the line — generate (AI footage), compose (designed HTML), edit (cut real footage), or AUTO end-to-end.

  • Works in 5 steps: First distinguish an edit target from a… → Read the brief (topic, aspect ratio,… → Most explainer/animation requests are… → …
  • Classifying a brief and committing to a primary path
  • SKILL.md covers Unavailable Production Runtime, The three capability axes, Decision rules and End-to-end (AUTO) — when the…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Video Router is an agent skill from Orkas-AI/Orkas-VideoStudio. Read this FIRST on any video-production request to pick and lock the line — generate (AI footage), compose (designed HTML), edit (cut real footage), or AUTO end-to-end. Trigger when classifying a brief and committing to a primary path; do NOT trigger for authoring compositions, generating assets, or rendering output (those have their own stage skills).

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/production-method.md`).

It sits in Media & Creative, covering Video production, AI video generation and Motion graphics. The repository describes itself as: Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file. The licence is MIT.

When your agent uses it

  • Classifying a brief and committing to a primary path
  • Do NOT trigger for authoring compositions
  • Generating assets
  • Rendering output (those have their own stage skills)

Example prompts

  • “/video-router”

Workflow steps

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

  1. First distinguish an edit target from a production input. Keeping supplied video or its timeline as the spine remains EDIT, including…
  2. Read the brief (topic, aspect ratio, language, duration) and classify the dominant work object
  3. Most explainer/animation requests are Compose-primary: typographic and motion-graphic scenes assembled as an HTML composition, with AI…
  4. For supplied reference media, classify the requested relationship as reproduce, edit, or guide before choosing execution. Apply the same…
  5. Aspect ratio drives the canvas: 16:9 → 1920×1080, 9:16 → 1080×1920, 1:1 → 1080×1080.

What it can do on your machine

Read from SKILL.md and the folder at commit c0c3c3e. 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.

    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

Video Router loads about 1.5k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 92 tokens; SKILL.md has 760 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

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 Orkas-AI/Orkas-VideoStudio at commit c0c3c3e, republished under its MIT licence (© Orkas-AI). 760 words, ~1,487 tokens.

Download SKILL.mdSave it as .claude/skills/video-router/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
video-router
description
Read this FIRST on any video-production request to pick and lock the line — generate (AI footage), compose (designed HTML), edit (cut real footage), or AUTO end-to-end. Trigger when classifying a brief and committing to a primary path; do NOT trigger for authoring compositions, generating assets, or rendering output (those have their own stage skills).

video-router

Knowledge for picking a video production line and locking it before work begins. This skill is read for guidance; it describes what to decide, not any tool mechanics.

Read production method and current-video checks before deep reference analysis or delivery review. It distinguishes direct provider output from locally assembled output using the current executable plan, not the route label.

Unavailable Production Runtime

If production, rendering, or paid tools are explicitly unavailable, still select the line and return a complete unexecuted production package for a clear brief: assumptions, script/narration, timed storyboard/shotlist, exact visible copy and captions, visual/audio direction, rights-safe asset provenance/fallbacks, export target, preview checklist, and final encoding/playback QA. Clearly distinguish planned from produced media and do not withhold the package behind a direction form.

The three capability axes

A finished video is built from one or more of three orthogonal axes. Decide which dominate, then lock them.

  • Generate (A) — AI-generated footage/imagery: photoreal shots, b-roll, motion, talking-head. Use when the brief needs real-looking or cinematic visuals.
  • Compose (B) — deterministic HTML composition: explainers, kinetic typography, motion graphics, captions / lower-thirds / overlays, data viz, title cards, transitions. Use when the visuals are designed rather than filmed. This is the default for explainer/animation work.
  • Edit (C) — intelligent editing of supplied footage: evidence-based selection/cleanup, deterministic cut/join/reframe/captions/audio work, and semantic AI video editing for bounded pixel-level changes.

Decision rules

  1. First distinguish an edit target from a production input. Keeping supplied video or its timeline as the spine remains EDIT, including captions, overlays, localization and supplied narration. Video used only as a reference, or supplied images/audio/scripts, do not select EDIT. Ask only if the requested output is ambiguous.
  2. Read the brief (topic, aspect ratio, language, duration) and classify the dominant work object:
    • "explain / teach / animate / motion-graphics / kinetic text" → Compose (B) primary, optionally Generate (A) for b-roll.
    • "make footage of / cinematic / a scene of / a character doing" → Generate (A) primary, Compose (B) to overlay captions.
    • "cut / clip / trim / repurpose / make highlights / remove or change something in my video" → Edit (C) primary. Keep EDIT as the route even when a billable operation:"edit" segment is required.
  3. Most explainer/animation requests are Compose-primary: typographic and motion-graphic scenes assembled as an HTML composition, with AI imagery only where a shot genuinely needs it.
  4. For supplied reference media, classify the requested relationship as reproduce, edit, or guide before choosing execution. Apply the same classification regardless of origin. Images can control content/identity/composition/structure/style; videos can additionally control motion/timing/audio through temporal anchors.
  5. Aspect ratio drives the canvas: 16:9 → 1920×1080, 9:16 → 1080×1920, 1:1 → 1080×1080.
Show full SKILL.md (339 more words)Show less

End-to-end (AUTO) — when the job spans lines

Pick a single line when one axis cleanly dominates (just trim a clip; just an explainer; just generate a scene). Route to AUTO end-to-end when the deliverable genuinely needs MORE THAN ONE axis woven into the primary timeline — most often the user supplies their own material AND wants finished framing/voice/motion around it:

  • "use my clip in the middle, author a motion-graphics opener, and add generated b-roll" (edit + compose + generate)
  • "my footage in the middle, generate an opener, compose the stats" (edit + generate + compose)
  • "make a finished video from these assets" where the assets alone are not the deliverable.

AUTO does not abandon the axes — it sequences them through one cross-modal plan (stage-plan builds the EDL, stage-assemble walks it), delegating each segment back to the generate / compose / edit lines. Choosing AUTO is itself the lock: the primary still gets named via the plan's delivery_promise (source_led / motion_led / compose_led / hybrid).

Lock the runtime

  • Decide the primary axis at the brief/proposal stage and state it in the proposal.
  • Once locked, do not silently switch the primary axis mid-run. If a later step reveals the wrong choice, surface it to the user and re-confirm rather than quietly changing course.
  • Layering is fine and expected (e.g. Compose captions over Generated footage); "locking" governs the primary path, not the allowed overlays.

Boundary / non-goals

This skill only routes and locks. Semantic editing is not a silent switch to GENERATE: it remains an EDIT/AUTO job with a signed billable video edit segment and explicit original/preservation boundary.

Runtime handoff

For a fully specified one-shot deterministic edit, state EDIT, probe and execute through stage-edit without a direction artifact or plan. Load stage-decide first only when the content or timing must be located.

For other production work, show two or three direction concepts and the facts already settled by the brief. Do not write a manifest, narration or art direction before that choice. Follow gate-control for the decision and its localized title. The public runtime uses OVS and HyperFrames; do not invent desktop-host operations.

© Orkas-AI, MIT. 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 (references) in packages/skills/video-router of Orkas-AI/Orkas-VideoStudio.

  • SKILL.md
  • references/production-method.md

Open the folder on GitHubat commit c0c3c3e

Compare with similar skills

Video Router 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.

Video Router compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Video Router this skillOrkas-AI/Orkas-VideoStudio499—~1.5kAutomated safety check: PassMIT
HyperFrames Video Entry Pointheygen-com/hyperframes60k3 repos~5.2kAutomated safety check: PassApache-2.0
Lazy Framescosmicstack-labs/lazy-frames163—~2.6kAutomated safety check: PassNone
Tesseract Videomirage-hq/Tesseract130—~1.9kAutomated safety check: PassCustom licence
Paw Cra Agent Video Producerpawbytes/skill-suites113—~2.3kAutomated safety check: PassMIT
AI Video Production Mastercuriositech/some_claude_skills244—~1.7kAutomated safety check: PassMIT

Similar skills

  • HyperFrames Video Entry Point

    heygen-com/hyperframes

    Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.

    60k GitHub starsUsed in 3 repos~5.2k tokens
    Media & CreativeAuto-check passed
  • Lazy Frames

    cosmicstack-labs/lazy-frames

    Turn any input (a website URL, a text brief, existing footage, a music track) into a finished, pixel-perfect MP4 — fully local, byte-stable across renders.

    163 GitHub stars~2.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Tesseract Video

    mirage-hq/Tesseract

    Edit existing footage into finished videos locally with Tesseract.

    130 GitHub stars~1.9k tokensUpdated 9 days ago
    Media & CreativeAuto-check passed
  • Paw Cra Agent Video Producer

    pawbytes/skill-suites

    Video production specialist for short-form, long-form, episodic, and motion graphics video.

    113 GitHub stars~2.3k tokensUpdated 8 days ago
    Media & CreativeAuto-check passed
  • AI Video Production Master

    curiositech/some_claude_skills

    Expert in script-to-video production pipelines for Apple Silicon Macs.

    244 GitHub stars~1.7k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Anything2explainer

    Vincentwei1021/anything2explainer

    给一个主题,产出一条黑底 MG 风格(幕底可选星点或点阵波)、有配音字幕章节进度条的科普讲解视频(中文或英文;Remotion 代码动画;时长由用户定,常用 3–5 分钟)。内含可编译模板、图元库、配音/分镜/渲染工具、风格与动效规范、多 agent 分工协议与 QC 判据,以及一条完整样片(《RAG 与知识库》)作为质量标尺。Turn any topic into a narrated…

    2.4k GitHub stars~2.7k tokensUpdated 23 days ago
    Media & CreativeAuto-check passed

More from Orkas-AI/Orkas-VideoStudio

All 14 skills in this repo
  • Gate Control

    Orkas-AI/Orkas-VideoStudio

    Canonical VideoStudio review authorization and state-transition policy.

    499 GitHub stars~2.7k tokensUpdated 19 days ago
    Auto-check passed
  • Stage Compose

    Orkas-AI/Orkas-VideoStudio

    Authoring knowledge for Orkas/OVS HTML video compositions -- write an index.html, drive animation from a paused timeline, declare canvas + duration, then run the VideoStudio draft gate to render an…

    499 GitHub stars~4.2k tokensUpdated 19 days ago
    Auto-check passed
  • Stage Edit

    Orkas-AI/Orkas-VideoStudio

    Intelligent editing of real user-supplied footage—understand it with transcript/inspected-frame/scene/silence/quality evidence, then choose deterministic timeline operations or a constrained…

    499 GitHub stars~2.4k tokensUpdated 19 days ago
    Auto-check passed
  • Stage Consistency

    Orkas-AI/Orkas-VideoStudio

    Multi-shot narrative & character consistency — a character bible with a locked front-portrait anchor, view-matched reference selection, recent-frame carry-forward, Cameo (a user photo as the lead)…

    499 GitHub stars~1.8k tokensUpdated 19 days ago
    Auto-check passed
  • Stage Plan

    Orkas-AI/Orkas-VideoStudio

    The "ingest + plan" half of end-to-end video orchestration — ingest the user's material from evidence, then decompose intent into ONE cross-modal EDL (plan.json: edit/generate/compose/provided…

    499 GitHub stars~4k tokensUpdated 19 days ago
    Auto-check passed
  • Frontend Design

    Orkas-AI/Orkas-VideoStudio

    Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions.

    499 GitHub stars~4.3k tokensUpdated 19 days ago
    Auto-check passed

Questions about Video Router

What does Video Router do?

Read this FIRST on any video-production request to pick and lock the line — generate (AI footage), compose (designed HTML), edit (cut real footage), or AUTO end-to-end. Video Router is an agent skill from Orkas-AI/Orkas-VideoStudio. Read this FIRST on any video-production request to pick and lock the line — generate (AI footage), compose (designed HTML), edit (cut real footage), or AUTO end-to-end.

When should I use Video Router?

Video Router fits situations like: classifying a brief and committing to a primary path; do NOT trigger for authoring compositions; generating assets; rendering output (those have their own stage skills).

How do I install Video Router in Claude Code?

Run `npx skills add Orkas-AI/Orkas-VideoStudio --skill video-router -a claude-code`. Or copy the skill folder (packages/skills/video-router in Orkas-AI/Orkas-VideoStudio) into .claude/skills/video-router in your project. Claude Code loads it when a task matches its description.

How do I install Video Router in Codex?

Run `npx skills add Orkas-AI/Orkas-VideoStudio --skill video-router -a codex`. Or copy the skill folder (packages/skills/video-router in Orkas-AI/Orkas-VideoStudio) into .agents/skills/video-router in your project. Codex loads it when a task matches its description.

Can I use Video Router 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 Orkas-AI/Orkas-VideoStudio --skill video-router -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/video-router, .gemini/skills/video-router, .github/skills/video-router and .opencode/skills/video-router in your project.

What does Video Router need to run?

SKILL.md names no scripts, command-line tools or credentials: Video Router is instructions for the agent only.

Does Video Router 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 Video Router 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 Video Router use?

Video Router is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Video Router use?

About 1.5k tokens (SKILL.md is roughly 5.9k 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 771 tokens, read only when the agent opens those files.

What are the alternatives to Video Router?

Skills that share tags, products or a category with Video Router: HyperFrames Video Entry Point (heygen-com/hyperframes, 60k stars), Lazy Frames (cosmicstack-labs/lazy-frames, 163 stars), Tesseract Video (mirage-hq/Tesseract, 130 stars) and Paw Cra Agent Video Producer (pawbytes/skill-suites, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Video Router?

Orkas-AI (a GitHub user) maintains it in Orkas-AI/Orkas-VideoStudio, which has 499 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 22, 2026.

Source: Orkas-AI/Orkas-VideoStudio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.