Agent skill

Gate Control

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

Canonical VideoStudio review authorization and state-transition policy.

MITAuto-check passedMedia & Creative

Install Gate Control

skills CLI
$ npx skills add Orkas-AI/Orkas-VideoStudio --skill gate-control -a claude-code

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

GitHub CLI
$ gh skill install Orkas-AI/Orkas-VideoStudio gate-control --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/gate-control .claude/skills/gate-control && 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
gate-control
GitHub stars
498
Token cost
~2.7k tokens
SKILL.md length
1,385 words
Files
2 (incl. references)
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Canonical VideoStudio review authorization and state-transition policy.

  • Works in 5 steps: Identify the locked line: compose, auto,… → Identify the reviewed artifact:… → Classify revision scope → …
  • Ordinary planning
  • SKILL.md covers Canonical review gates, Authority is not the same as…, Required resolution and Invariants, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gate Control is an agent skill from Orkas-AI/Orkas-VideoStudio. Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition. Do not use for ordinary planning or craft decisions before a gate exists.

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/assembled-productions.md`).

It sits in Media & Creative, covering Visual regression testing and AI video generation. 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

  • Ordinary planning
  • Craft decisions before a gate exists

Example prompts

  • “/gate-control”

Workflow steps

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

  1. Identify the locked line: compose, auto, generate, or edit.
  2. Identify the reviewed artifact: composition for COMPOSE (and AUTO child compositions), otherwise production.
  3. Classify revision scope
  4. Set recovery only from deterministic evidence: available, not_available, or unknown. This selects internal control flow, not a new form.
  5. Run ovs gate transition and obey next_action, form, allowed_ops, and prohibited_ops.

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 (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

Gate Control loads about 2.7k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 1,385 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~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). 1,385 words, ~2,680 tokens.

Download SKILL.mdSave it as .claude/skills/gate-control/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
gate-control
description
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with `ovs gate transition`. Do not use for ordinary planning or craft decisions before a gate exists.

gate-control

This is the single authorization policy for every VideoStudio production line. Line skills own artifacts and production craft; they do not invent a second confirmation or recovery state machine.

Resolve the next operation from current facts—plan identity, artifact identity, narration materialization, paid-attempt facts, QA evidence, and explicit user authority—not from a monotonic stage rank. Preview/snapshot work may continue while required narration is missing; complete draft/final delivery may not. Stop the execution horizon at any operation whose returned evidence decides the next branch.

Gate-B identity is the normalized production-intent projection. Stable copy, timing, language, references, provider settings, and voice selection remain approval-bearing; execution-only fields such as produced paths/status and provider catalog display labels do not. Unknown plan fields remain signed so new semantics cannot bypass review.

Canonical review gates

The names below are internal protocol identifiers. In normal user-facing headings and decisions, use plain localized names instead:

Internal identifierEnglishSimplified Chinese
Gate ADirection confirmation制作方向确认
Gate BProduction plan confirmation制作方案确认
Gate CPaid generation confirmation付费素材生成确认
HTML PreviewKeyframe preview关键帧预览
Gate DFinal video confirmation成片确认

Keep Gate A/B/C/D and HTML Preview for tool calls, stored state, and technical diagnostics only. Choose the production language from an explicit user request first, then the current UI/user language when known, otherwise English. Normalize Chinese to zh-CN, English to en, Japanese to ja, Portuguese to pt-BR, and unsupported languages to en; once submitted, keep that choice locked unless the user explicitly changes it.

Every gate shows the current artifact, a concise next-action/cost/QA note, one decision request, and then stops. A new turn, question, or unrelated message is not approval.

GateRequired artifactStable decision fieldApproval authorizes
Gate Bcanonical composition manifest or plan.json summary, including narration profilegate_b_decisionproduction from that exact plan
Gate Cexact billable segment count and exact provider settingsgate_c_decisionthose generation calls only
HTML Previewcurrent contact sheetpreview_decisionovs draft for that preview
Gate Ddraft video plus QA headlinegate_d_decisionhigh-quality finalization of that draft

Decision values are approve and revise; keep free-text adjustments separate. Gate A locks the creative brief but does not authorize production, paid work, rendering, or final delivery.

Gate C is one batch-level decision. A pending or failed paid request is not reusable authority for another request: a user-requested retry needs a fresh Gate C and a new output path. Do not interleave per-shot confirmations.

Authority is not the same as recovery

  • A Preview/Gate D revise authorizes editing the displayed artifact within the requested scope and any required non-billable restart of its visual-QA cycle.
  • approve authorizes only the displayed artifact and next transition.
  • Technical QA exhaustion is not a second user decision and must never create a new recovery form.
  • Legacy visual_recovery_decision=new_visual_revision input remains consumable for old clients, but must not be emitted in a new task.
  • An error that says authorization is required does not itself prove recovery availability; query durable status first.
  • A malformed local payload, missing file, stale evidence, failed check, or write error is system work, not a creative decision. Repair it without creating a gate when approved intent is unchanged.

When production or rendering tools are explicitly unavailable, return a clearly unexecuted production package for an otherwise clear brief: assumptions, complete narration/script, timed storyboard, exact visible copy/captions, visual/audio and rights-safe asset plan, export target, preview checklist, and final playback/encoding QA. Do not claim files exist or withhold the package behind a direction form.

Required resolution

After a gate submission, a post-gate edit, a resumed turn with prior approval, or a visual-revision error:

  1. Identify the locked line: compose, auto, generate, or edit.
  2. Identify the reviewed artifact: composition for COMPOSE (and AUTO child compositions), otherwise production.
  3. Classify revision scope:
    • visual_only: HTML/CSS/SVG/layout/motion/palette/assets; no approved wording, timing, language, narration, delivery, source mapping, role, or provider-setting change.
    • gate_b_payload: approved copy/casing/punctuation, timing, language, narration, delivery, source mapping, semantic roles, or signed provider intent.
    • unknown: inspect the requested files before asking a technical question.
  4. Set recovery only from deterministic evidence: available, not_available, or unknown. This selects internal control flow, not a new form.
  5. Run ovs gate transition and obey next_action, form, allowed_ops, and prohibited_ops.

Always invoke the resolver through the public ovs gate transition command (or the equivalent gate_transition MCP tool). Never execute a resolver by referencing an installed skill or Marketplace path directly. Pass only the decision field present in the current user submission. Never combine a current --decision with a cached --recovery-decision.

bash
ovs gate transition \
  --line compose \
  --artifact composition \
  --gate gate_d \
  --decision revise \
  --scope visual_only \
  --recovery not_available

Pass --origin user|model|unknown for signed amendments, from the actual current user reply. Mixed user instructions plus additional model proposals use model. This pure resolver trusts caller-supplied facts; it does not verify chat history or record approvals. Optional evidence inputs are --error-code, --artifact-state, and --approval-status. --recovery-decision is backward-compatible input for an already-visible old form only. Use unknown when evidence is missing; never guess available.

Show full SKILL.md (582 more words)Show less

Invariants

  • A Preview/Gate D visual_only revision with recovery not_available goes directly to a localized edit and deterministic QA. It emits no recovery question.
  • The same revision with recovery available still emits no form: make the localized edit, then use ovs check, ovs snapshot, and ovs draft. OVS automatically starts a fresh persisted repair cycle after the authored content signature changes.
  • A gate_b_payload revision originating from a model proposal creates exactly one Gate B amendment. A current user-specified change uses --origin user: apply and validate exactly that change without asking for the same instruction again. Its approved signature starts a fresh QA cycle, so recovery from the old signature is irrelevant and must not be combined into the form.
  • An unchanged artifact with recorded approval continues from that approval; never ask again merely because the task resumed.
  • A passing snapshot may create one Preview Gate. A passing draft may create one Gate D. No status check, advisory, retry, or bookkeeping step creates a user gate.
  • A content edit changes the draft signature and starts a fresh bounded repair cycle automatically. There is no public/manual reset operation; do not delete QA state by hand.
  • One user decision may produce at most one follow-up authorization request, and only for authority that decision did not already grant.
  • E_VISUAL_REVISION_EXPLICIT_AUTHORIZATION_REQUIRED never justifies a form. With recovery unknown, query status; with recovery available and no current revise decision, report the blocker and wait for the next real revision request.
  • After final-video approval, a local visual-only revision reuses the approved plan, assets, and narration. Edit only the affected scene, run ovs check and ovs snapshot, then encode the revised final; do not ask for production-plan confirmation again or repeat TTS/generation unless the requested scope changes signed content or provider intent.

Signed amendments

For a Gate B amendment, apply only the approved bounded patch, revalidate the changed plan/artifact, then continue through the real Preview/Gate D path. A current Gate B approval wins over cached approval for the old signature. Do not promise an immediate render when a newly materialized preview still needs review.

Status checks, plan bookkeeping, advisory QA, repair passes that remain, QA-cycle restart, and tool misuse errors never create a gate. Never emit visual_recovery_decision in new VideoStudio output.

Concrete review and recovery

A pending decision is not permission to ask it again. At a stop, show the complete current artifact once, invite the user's changes or go-ahead, then wait. A numbered choice or paraphrase of a displayed option is a decision; mixed approval plus edits means revise. Never use a new turn or a stale reply as approval.

Before COMPOSE plan confirmation, write only the canonical composition manifest and run free narration fit for its spoken windows. Script/shotlist files are legacy optional evidence, not a second required plan. Direction choice comes before authoring that manifest. For a fully specified one-shot deterministic edit, probe and execute the user's operation directly.

After two non-converging repair passes, show the current artifact, the visible unresolved problem and concrete directions for the user to choose. Do not silently create another repair cycle, delete QA state, or treat exhaustion as an unlimited retry. A real requested revision authorizes a bounded new attempt. Do not expose internal counters in ordinary user-facing text.

For AUTO, read assembled productions before preview or a child revision. For narration uncertainty, preserve the existing output, request identity and provider outcome. A failed or unknown billable request does not authorize another charge; present the concrete retry choice when new authorization is needed.

© 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/gate-control of Orkas-AI/Orkas-VideoStudio.

  • SKILL.md
  • references/assembled-productions.md

Open the folder on GitHubat commit c0c3c3e

Compare with similar skills

Gate Control 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.

Gate Control compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gate Control this skillOrkas-AI/Orkas-VideoStudio498—~2.7kAutomated safety check: PassMIT
Video Generationbytedance/deer-flow84k3 repos~1.4kAutomated safety check: PassMIT
Video Cover Imageitwanger/toBeBetterJavaer18k—~3.3kAutomated safety check: PassNone
Seedancesongguoxs/seedance-prompt-skill2.9k1 repos~2.5kAutomated safety check: PassNone
HyperFrames Video Entry Pointheygen-com/hyperframes59k3 repos~5.2kAutomated safety check: PassApache-2.0
Lanshu Create AI Presenter Videocclank/lanshu-create-ai-presenter-video2.6k—~3.6kAutomated safety check: PassMIT

Similar skills

  • Video Generation

    bytedance/deer-flow

    Generates short videos from a structured JSON prompt, optionally guided by a reference image used as the first or last frame.

    84k GitHub starsUsed in 3 repos~1.4k tokens
    Media & CreativeAuto-check passed
  • Video Cover Image

    itwanger/toBeBetterJavaer

    Generate matched 3:4, 16:9, and 4:3 short-video cover images from toBeBetterJavaer video scripts or AI/Java technical topics.

    18k GitHub stars~3.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Seedance

    songguoxs/seedance-prompt-skill

    This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成"…

    2.9k GitHub starsUsed in 1 repo~2.5k tokens
    Media & CreativeAuto-check passed
  • 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.

    59k GitHub starsUsed in 3 repos~5.2k tokens
    Media & CreativeAuto-check passed
  • Lanshu Create AI Presenter Video

    cclank/lanshu-create-ai-presenter-video

    Turn a topic or finished script into a complete, publish-ready explainer video — led by an AI presenter from an authorized adult presenter image, or performed in one of nine visual explainer styles…

    2.6k GitHub stars~3.6k tokensUpdated 3 days ago
    Media & CreativeAuto-check passed
  • Video Shots

    eternityspring/reelbench-skills

    拉片:把一条成片拆成逐镜头的分析表——每个镜头的时长、景别、类别、运镜、画面. An agent skill from eternityspring/reelbench-skills.

    872 GitHub starsUsed in 1 repo~1.8k tokens
    Media & CreativeAuto-check: notes

More from Orkas-AI/Orkas-VideoStudio

All 14 skills in this repo
  • 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…

    498 GitHub stars~4.2k tokensUpdated 17 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…

    498 GitHub stars~2.4k tokensUpdated 17 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)…

    498 GitHub stars~1.8k tokensUpdated 17 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…

    498 GitHub stars~4k tokensUpdated 17 days ago
    Auto-check passed
  • Frontend Design

    Orkas-AI/Orkas-VideoStudio

    Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions.

    498 GitHub stars~4.3k tokensUpdated 17 days ago
    Auto-check passed
  • Video Craft

    Orkas-AI/Orkas-VideoStudio

    The craft standard that makes a video GOOD, not just rendered — hooks, story pacing, visual hierarchy, type & safe zones, motion/easing, captions, audio mix, platform conventions, shot language…

    498 GitHub stars~3.3k tokensUpdated 17 days ago
    Auto-check passed

Questions about Gate Control

What does Gate Control do?

Canonical VideoStudio review authorization and state-transition policy. Gate Control is an agent skill from Orkas-AI/Orkas-VideoStudio. Canonical VideoStudio review authorization and state-transition policy.

When should I use Gate Control?

Gate Control fits situations like: ordinary planning; craft decisions before a gate exists.

How do I install Gate Control in Claude Code?

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

How do I install Gate Control in Codex?

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

Can I use Gate Control 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 gate-control -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gate-control, .gemini/skills/gate-control, .github/skills/gate-control and .opencode/skills/gate-control in your project.

What does Gate Control need to run?

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

Does Gate Control 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 Gate Control 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 Gate Control use?

Gate Control 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 Gate Control use?

About 2.7k tokens (SKILL.md is roughly 11k 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 316 tokens, read only when the agent opens those files.

What are the alternatives to Gate Control?

Skills that share tags, products or a category with Gate Control: Video Generation (bytedance/deer-flow, 84k stars), Video Cover Image (itwanger/toBeBetterJavaer, 18k stars), Seedance (songguoxs/seedance-prompt-skill, 2.9k stars) and HyperFrames Video Entry Point (heygen-com/hyperframes, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gate Control?

Orkas-AI (a GitHub user) maintains it in Orkas-AI/Orkas-VideoStudio, which has 498 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.