- Home
- Skills
- Image & Video
- Creator Storyworld Architect — Lock Video Continuity
More screenshots
Works with the AI Agents you already use
Creator Storyworld Architect — Lock Video Continuity
Turn one approved video idea into a traceable storyworld package with continuity-locked scenes and shots.
$11
Creator Storyworld Architect — Lock Video Continuity
Example session with this skill installed
Use Creator Storyworld Architect with [IDEA: a 30-second vertical explainer showing how a freelancer turns scattered client feedback into a controlled revision plan], [AUDIENCE: independent designers handling several clients], [GOAL: make the evidence-to-action transformation visible], and [DELIVERY: 9:16, 30 seconds, calm premium tone].
- Read your context and instructions
- Compiled the creator storyworld architect
Demonstration Output — Storyworld Handoff
No media was generated, inspected, accepted, or published.
Project promise
Show a freelancer moving from ambiguous comments to one traceable revision plan without implying that the tool replaces client approval.
Causal story
BEAT-001 (0–7s): Three conflicting comments arrive and create visible decision noise.
BEAT-002 (7–18s): Each comment is anchored to its source, scope, and required action.
BEAT-003 (18–30s): The revised plan resolves the conflicts, preserves one approval gate, and ends on the same deliverable introduced in the opening.
Identity lock
CHAR-001 keeps the same navy overshirt, silver rectangular glasses, short dark curls, and left-wrist watch across all shots. Expression may move from overloaded to composed; face shape, wardrobe, and accessories may not drift.
World lock
WORLD-001 is a quiet daylight studio with warm off-white walls, one dark desk, and a cyan-violet evidence interface. Lighting direction, desk position, material palette, and camera axis remain stable.
Scene graph
SC-001 noisy inbox → SC-002 evidence ledger → SC-003 approved revision plan. Each scene consumes the previous scene's end state; total duration reconciles to 30 seconds.
Shot contract excerpt
SH-002 · 7–12s · primary action: drag one quoted comment into its matching evidence row. Start state: three unclassified comments. End state: one comment linked to source, scope, and owner. Required controls: exact character anchors, fixed desk geography, readable UI hierarchy, no fabricated testimonial or approval state.
Validation result
PASS — six required artifacts present; project identity and upstream versions resolve; scene and shot durations reconcile; every shot contains one primary action and explicit start/end state. This validates local structure only, not visual quality or generation success.
Connects securely to your tools. The creator never sees your data.
About this skill
Most AI-video failures begin before generation: the promise is vague, the character changes between shots, the environment drifts, or the ending does not pay off the opening.
Creator Storyworld Architect converts one approved creator-video idea into six platform-neutral production artifacts: a creative brief, causal story package, character bible, world bible, scene graph, and shot contracts. Every artifact shares one project identity and explicit upstream versions, so a downstream generation tool receives a coherent source package instead of disconnected prompts.
Use it when you need to lock identity, world rules, scene state, timing, and one primary action per shot before choosing Dreamina, Google Flow, Runway, or another generator.
What it delivers:
- A bounded audience promise and observable success criteria
- Character and environment continuity locks
- A causal scene graph with resolvable predecessors and successors
- Shot contracts with start state, end state, risks, and required controls
- Deterministic validation of structure, references, and duration reconciliation
Boundaries: it does not select models, route platforms, generate or edit media, spend credits, inspect outputs, upload, or publish. Missing inputs trigger a clearly labelled fictional Demonstration Output.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Video Skills.
Does not support platform-specific prompting (Runway/Luma), model routing, media generation, or credit management. Requires a project.json or standard inputs to start.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago