Video Spec Builder
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_3c6cb52e/video-spec-builder.
About this skill
Problem Context
Many video projects get stuck between “the idea feels clear” and “production can start.” Users may want a product demo, tutorial, or brand short, but struggle to define shot structure, pacing, material gaps, and visual rules. Vague phrases like “premium,” “techy,” or “high quality” are not actionable for a rendering pipeline and often lead to rework. Video Spec Builder is meant to turn fuzzy video requirements into an executable video-spec.md.
How It Works
The skill does not focus on generating video directly. Its main job is to build a specification document through guided dialogue. On startup, it scans the project directory and chooses between 0-1 mode and iteration mode: if an existing video-spec.md is found, it handles revisions; if not, it collects requirements from scratch.
Key capabilities include:
- Requirement clarification: it probes video purpose, audience, platform, duration, core message, and available materials until they are concrete enough to act on.
- Shot breakdown: it converts scripts, selling points, or story outlines into single-shot granularity and produces a spec with a storyboard table.
- Capability surfacing: when users mention narration, subtitles, 3D, motion, transitions, or other needs, it proactively suggests relevant capabilities instead of recording only vague descriptions.
- Visual rules: it supports selecting a HyperFrames preset or using/generating a design.md file in the project root for a custom theme.
- Spec maintenance: when revising an existing spec, it checks conflicts and updates the document for changes such as shot swaps, pacing adjustments, subtitle changes, or color changes.
Scope and Caveats
This skill is best suited for projects that need to structure video intent first, especially product demos, tutorials, marketing shorts, and other storyboard-driven work. It is not a replacement for a full rendering workflow; after the spec is ready, it may guide the user into HyperFrames to continue. Output quality still depends on the user confirming key decisions, and vague preferences need to be translated into concrete visual, pacing, and material choices.
Use Cases
- Break a launch-event idea into a 30-second storyboard and set platform ratio, frame rate, and theme preset.
- Revise an existing video-spec.md by reordering shots, adjusting pacing, and checking subtitle/color conflicts.
- Turn a script into narration, subtitle, motion, and 3D capability choices, outputting a HyperFrames-ready spec.
- Choose a visual theme for a brand short from HyperFrames presets or a custom design.md specification.
Best For
- Engineers preparing product demo shorts who need to split selling points into shots and confirm assets.
- Creative planners producing brand shorts who need theme, pacing, and reference decisions.
- Operations staff with scripts and audio who want tutorial videos broken into storyboard and subtitle specs.
- Content leads maintaining video-spec.md who need iterative shot edits and conflict checks.
Related Skills
A free matrix publishing assistant for Skill developers, guiding distribution to Tencent SkillHub, XiaLiao, XiaYou SkillHub, GitHub, and ClawHub with create, update, and delete safeguards.
A guide for writing Seedance 2.0 video prompts, covering @ references, camera moves, time segments, audio direction, and common pitfalls.
Collects daily conversations, task logs, and errors, then runs a nine-module review to surface blind spots, generate actions, and update memory.
Local long-term memory for AI agents that appends key facts and daily logs, supports cross-session context and search recall, and auto-archives old diaries to gzip files.