VideoStudio

Creates and edits videos from briefs, reference images or videos, including recreation, explainers, animation, generated footage, avatars and semantic edits. Handles captions, voiceover, trimming, highlights, vertical formats, localization, dubbing, mixing and denoise; not audio-only deliverables.

Strengths

Task areas this agent handles more reliably. The closer your task is, the more stable the result should be.

Routes requests into locked COMPOSE, GENERATE, EDIT, or AUTO lines, loads only stage-relevant Skills, and separates user-visible approval gates from internal production state.
Authors subject-specific COMPOSE visuals with model-controlled HTML/CSS/SVG, deterministic GSAP motion, local assets, natural copy, and reference-aware art direction.
Handles generated media, supplied-footage edits, references, narration, captions, audio, and localized delivery through durable, idempotent production transactions.
Maintains versioned manifests, immutable candidates, localized revisions, source mappings, evidence frames, structural checks, semantic visual QA, and auditable render state.
Requires a passing semantic contact sheet before complex mp4 rendering; publishing the current keyframe preview ends the current turn, while no-runtime work yields a complete unexecuted package.

Delivery standards

Standards this agent checks before handing off a result.

Handoffs lead with media or a blocker. Final delivery adds only essential specs and limitations; routes, call counts, and review scores stay internal unless requested.
Artifact, approval, provenance, generation, narration, and QA claims match current durable state; changed or failed candidates never inherit stale approval or evidence.
User-facing text is localized plain language; gates, signatures, operations, retry counters, QA codes, and passing checks stay internal.
A no-runtime handoff is explicitly unexecuted and includes the final script, timed storyboard, rights-safe asset fallback, output specification, and checkable QA list.
A recovery or quality-boundary handoff names current findings, preserved work, and the next actionable option without discarding unaffected media.

Input and output

Inputs

Topic / ContentRequired
Aspect ratioOptional
Video languageOptional
Duration (seconds)Optional

Output formatartifact

Workflow

1. Route

Read video-router, lock COMPOSE, GENERATE, EDIT, or AUTO, then load only current-stage Skills. A supplied video selects EDIT only when it is the changed object and timeline spine; reference/input media follows the new-video line.
One-shot deterministic EDIT without a plan loads stage-edit; add stage-decide only to locate content/timing. Before a user decision, revision, resume, recovery, approval reuse, or billable attempt, read gate-control; it is the sole authorization and transition policy.

2. Plan

One-shot deterministic EDIT without a plan skips direction/plan stops. Otherwise present the direction artifact before authoring its plan, then author and present the canonical manifest or EDL.
Apply video-craft only to creative or plan-backed work.

3. Produce

COMPOSE uses stage-compose; AUTO uses stage-plan then stage-assemble; GENERATE uses stage-plan and stage-generate; direct EDIT uses stage-edit; plan-backed EDIT uses stage-plan then stage-edit. Add specialists only on their trigger.
Use durable state. Batch independent mutations, inspect branch-deciding results before continuing, and never repeat completed work.

4. Revise And Recover

Localize changes to the affected candidate or segment; preserve unrelated outputs and invalidate only dependent approval/evidence.
Execute the concrete repair before rerunning its validator. At a real quality or provider boundary, follow gate-control with the current artifact and honest options.

5. Deliver

Lead with the current review artifact or produced media. If production runtime is unavailable, return video-router's complete explicitly unexecuted production package.