short-drama-assets

Short-Drama Asset Breakdown

Turn script text into reusable, sustainable visual facts, written consistently into 剧集/<EP>/视觉设定.md. Do not turn every appearance into a new asset, and do not take over writing script semantics, camera blocking, or generation prompts.

Quick Start

用 $short-drama-assets 从 EP001 剧本拆完人物、造型、地点、道具和本集状态

Entry and Boundaries

An existing script can be broken down into assets directly. First distinguish:

• Identity: if it is swapped for another, it is no longer the same person, place, or object;
• Variant: the identity stays the same, but clothing, injuries, time period, weather, open/closed state, or held state changes;
• Shot transient: pose, gaze, left/right hand, blocking, and camera angle are owned by the storyboard;
• Story semantics: knowledge, goals, relationships, and emotions are owned by writing/development; only reference visible consequences.

Workflow

1. Read only the script in the current scope and the already-decided visual direction; when the visual direction does not yet have an era anchor, first set the era according to the source material's facts.
2. Go scene by scene to find entities, visible descriptions, state changes, and ambiguous references, without creating assets yet.
3. For each item, decide create new, reuse, add variant, or mark undecided; do not guess ambiguous references.
4. Write the minimum recognizable spec: consistently use 识别锚点, the current episode state, and the reason for change; body-object-spatial relationships that will continuously constrain subsequent actions are written into states with an effective scope, not skipped as a one-off pose.
5. Check looks/injuries, held objects/ownership, prop states, location time period/weather/light state, and cross-episode outgoing.
6. Write one continuity lock for visible facts that appear across shots and that the audience can see are inconsistent; keep the rest as recognition anchors only.
7. When the project prompt language is not Chinese, write one line of 画面代称：<正文里的拼写>for each character entry; if the main text never names it, write 画面代称：无. Locations and props as needed.
8. A whole-episode request automatically processes the complete episode, and at the end reports the key identity decisions and undecided references once.

Content Requirements

• For each item, first write what stays the same so it remains the same asset, then write the changes in this episode.
• Recognition anchors must be visible, generatable, and comparable; do not replace facts with vague quality words.
• Clothing, injuries, wet stains, prop open/closed states, and light states are usually variants, not new identities.
• Do not copy plot summaries; keep only the facts that downstream generation, storyboarding, or continuity truly need.
• Text, logos, and sensitive information follow project policy; do not invent brands or private information without authorization.
• For multi-episode states, state the effective and duration scope clearly; leave in-shot transients to the storyboard.
• Confirmed relationships that continuously constrain the action space (body support, fixation, load-bearing, occupation, or contact with a functional object) are not ordinary shot poses: independently recognizable objects still become assets, while the relationship is written into the state and handed to the storyboard for shot-by-shot projection; it ends only when the script explicitly changes it.
• Continuity locks only lock visible facts that do not change with the plot; write the locked surface as a minimal noun phrase in the prompt language, and leave the changing parts to the state.
• "Screen alias" maps the names in the prompt body back to this entry: the storyboard's mechanical check relies on it to determine who is named in the keyframe. The entry's own Chinese name is always counted as an alias, so the Chinese prompt body usually does not need this line; when the prompt body language is not Chinese, a character entry must give a conclusion—write out the spelling used in the body, or when the body never names it, write 画面代称：无. The same full set of names uses only one spelling, with consistent capitalization (AST-10 the same requirement holds across languages); multiple spellings are separated by 、 . When a name has the same form as a common word (道具「手机」 collides with "phone store"), also write 画面代称：无, so the check does not look for it by name.

On-demand knowledge

By default, read only this SKILL, the current script, and the visual direction. When encountering a corresponding issue, open only one document:

• Phase boundaries and rule levels:Phase contract
• To set the era, write era anchors, or make places, equipment, or clothing look period-appropriate:Era anchors
• To find genuine asset appearance evidence from the script:Appearance extraction
• New identity, reuse, variant, or unresolved:Identity and variants
• Character recognition and design layers:Characters and design
• Location geography, views, and fixed anchors:Locations and views
• Functional props, ownership, state changes, or readable text and signage on screen:Props and states
• Identity and authorization boundaries of voice references:Voice direction
• Cross-scene, cross-shot, cross-episode states:Continuity changes
• Cross-shot costume/prop color or material drift:Cross-shot consistency lock
• To do an asset omission check before completion:Asset review checklist

Completion

All explicit appearances have been reused, created, turned into variants, or marked as genuinely unresolved; the visual facts and state changes that need to be preserved have been written into the single visual design document, and it is complete. Image prompts, storyboards, review, and production do not start automatically. Once the five creative documents are complete, you may turn to $short-drama to do a mechanical check of the cross-document structure; content quality is still reviewed by the creator.

Installation and maintenance

Run only during installation, upgrade, or troubleshooting python3 scripts/selftest.py。