Novel Key-Plot Distillation
Turn user-provided novel material into short-video scenes that are sourced, causally coherent, and production-ready. Here, “distillation” refers to editorial distillation; the output consists of selected segments and production rationale, not model training, video generation, or traffic prediction.
Inputs and Boundaries
Prioritize the chapters, character settings, target duration, adaptation latitude, spoiler scope, and reference materials already provided. By default, target approximately 30 seconds, remain faithful to source events, and allow clearly labeled audiovisual-expression suggestions; adjust when the user specifies otherwise.
- No novel text: You can analyze visual references or produce a materials checklist, but must not claim that novel plot events have been extracted. Original examples must be clearly labeled “Original teaching example.”
- Only a synopsis: You can make an initial event selection, but label it “Based on the synopsis”; do not invent chapter numbers, source quotations, or conclusions about the entire work.
- Insufficient information: Complete only the parts supported by evidence, then ask only for missing information that would change the selection. If no suitable segment exists, explain what is missing rather than padding out the candidate count.
- Keep reference videos separate from the novel. Screenshots can support only judgments about visible composition and state; they cannot establish duration, camera movement, audio, or production provenance.
- Default to a text brief. Generation, uploading, publishing, and paid-product calls follow a separate, explicitly specified task; this Skill does not automatically authorize them.
1. Build an Event Index
Segment by complete events rather than cutting at a fixed word count. Long-form works can be processed chapter by chapter; carry forward necessary character goals, ability conditions, unresolved events, and their sources across batches; record the actual scope of each batch. Use event cards for initial screening; do not write a full storyboard for every chapter of an entire book.
Each event card records:
- Locatable source: chapter or user-paragraph number and a few key source lines; mark paragraph numbers you add yourself as provisional.
- Triggering event, the protagonist’s goal at that moment, obstacle, and key choice or action.
- Change in circumstances before and after, along with results that have already occurred and unresolved issues.
- The ability’s conditions for use, target, limitations, or cost: record only what the text supports; if it is not provided, write “Not specified.”
- Preceding cause required to understand the event and whether adjacent chapters need to be reread.
Distinguish “worldbuilding setting,” “action description,” and “complete event.” A passage containing only words such as imposing pressure or dharma form is not enough to form a usable event. Before finalizing, reread the selected passages and any necessary surrounding context, and check the initial screening summaries for omissions and errors.
2. Compare Candidates
First verify the source, causality, and how much explanation is needed for a short video. Temporarily defer candidates missing a critical antecedent; do not fill the gap with invented rules and then present the result as source material.
Show at most three representative candidates by default. For each dimension below, assign a score of 0, 1, or 2 and provide a one-sentence rationale.
| Dimension | 0 points | 1 point | 2 points |
|---|
| Conflict clarity | No dispute or crisis is visible | Requires substantial background | The immediate conflict can be explained in one sentence |
| Character goal | Unclear from the material | Requires prior context | Motivation is directly clear |
| Situation change | Only a pose or description | The change is weak | The state clearly changes before and after |
| Visual distinctiveness | Generic and abstract | Has one concrete detail | Has a visible feature tied to the character or ability |
| Short-form feasibility | Multiple causal strands cannot be separated | Compression requires substantial explanation | One goal and one turn can stand on their own |
| Production controllability | Complex interaction across multiple locations or people | Can be simplified through a production approach | Few characters or scenes, with clear action relationships |
The total score is only an editorial ranking aid for the current candidates, not a measure of quality or viral-hit probability. Fidelity to the source and user preferences take priority over the total; explain the trade-offs behind the final choice. For non-action genres, look for turns involving discovery, decision, or relationship change; do not force a fight or counter-kill.
3. Compress Without Losing Causality
Write one sentence: Because of ___, in pursuit of ___, the character confronts ___, takes ___, and causes ___.
Build the short video around one primary goal, one primary causal line, and one key turning point; longer durations can accommodate more. When compressing, prioritize removing repeated clashes, names of secondary characters, explanatory realm terminology, and background that does not affect the current event.
Preserve why an action occurs, its object or target, key ability rules, and the information needed to understand the result. If the source explicitly states a cost and that cost determines the character’s choice, preserve it; do not invent a lifespan cost or similar setting for an ability that has no stated cost.
Distinguish between whether the event currently unfolding is understandable and whether later secrets are revealed. You may conceal a future identity, final outcome, or later consequences, but do not erase motivation for the sake of suspense. If removing a line or shot breaks causality, restore it or express it in a shorter alternative.
4. Turn the Text into Observable Images
For each important image, label the following separately:
- F Source fact: Has a verifiable source; preserve the relationships and conditions from the original.
- P Audiovisual presentation suggestion: Camera angle, shot size, pacing, color, sound, or other expressive choices that do not change event facts. Avoid interpreting emotionally charged wording as a new physical ability.
- A Addition or adaptation: Adds or changes an ability, identity, result, sequence, prop, physical phenomenon, or similar element. By default, list these as options and do not mix them into the faithful version; when the user permits adaptation, explicitly state which ones are used.
A single shot may contain F, P, and A, but label each component and its source separately. Mark inferred relationships as “To be verified”; do not present them as F.
Pay particular attention to seemingly ordinary added actions: giving someone an item early, locking a bridge, killing an enemy, and similar events also change the facts or sequence of the story, so classify them as A. Do not check only for newly introduced superpowers. Recheck every completed action in the shot list against the event card; the absence of supernatural adaptation does not mean A=0.
Translate adjectives such as “aura of strength” or “utterly shocking” into specific, visible changes. When a change introduces time stop, flight, or another new capability, classify it as A rather than P. Use domain or dharma-form (法相) concepts only when the source supports them or the user explicitly requests an adaptation.
Potential reference focuses include transitions from normal to abnormal, small motion to large-scale action, grayscale to color, solid form to spectral image, and action-to-environment feedback. Make a fresh selection based on the novel; do not copy entire characters or events from the reference, and do not attribute reference content to the novel’s source text.
5. Create a Production-Ready Scene
First draft the shots, then jointly refine them according to the user-specified tool. For the default target of approximately 30 seconds, consider 6–8 shots initially, but adjust for dialogue length, transitions, and action complexity; exact timing is not a generation guarantee.
For each shot, list the suggested duration, main action and visual change, new information it provides, F/P/A classification and source, sound suggestion, and connection to adjacent shots. Planned durations should sum to the target. Do not ask viewers to perform complex visual interpretation while also carrying information solely through voiceover narration.
Use key states to confirm continuity: character features, clothing, props, which hand holds the weapon, spatial positions, attack direction, and ability form. In dharma-form cases, explicitly define the relationship between the physical body and the dharma form, synchronized movements, and weapon ownership; do not imply that they are one entity solely through matching color effects.
Preserve the source order for “when an item is obtained” and “when a result occurs.” If the order is changed, mark it as A and describe the impact.
When the material leaves the two sides of a bridge, the character’s retreat route, the role of an institution, or similar spatial relationships undetermined, label them “Spatial relationship to be verified,” ask the minimum necessary follow-up question, or clearly mark a provisional P/A plan; do not claim that causality has been fully verified. If the source does not specify which hand holds a knife, the time of day or weather, or similar details, these can be fixed as P, but do not list them among source-immutable elements.
Output and Checks
Depending on the task scale, provide the following, merging or simplifying as needed:
- Material coverage, missing information, and assumptions actually used.
- Candidate event cards, comparison rationale, and reason for selection.
- A one-sentence causal spine for the selected event, retained and removed elements, and source rules that cannot be changed.
- A source-fact-to-audiovisual-suggestion comparison, with additions, adaptations, and items to verify listed separately.
- A storyboard draft, key states, continuity requirements, and suggested duration.
- A production brief that can be copied into the user-selected video tool: objective, audience, plot, assets, permitted changes, prohibited changes, sound and subtitles, deliverables, discussing the plan or style frames before production, and priorities for later revisions. Keep the brief generic when no tool is specified; retain the user’s choice, such as Pexo, and do not switch tools.
Before delivery, check whether sources or reading scope have been fabricated; whether motives, targets, abilities, and results are coherent; whether P/A elements have been confused with F; whether the reference’s abilities have been forcibly imposed; whether the duration and information load are reasonable; whether any shot can be removed without losing information; and whether the ending leaves a meaningful question or a complete result.
Finally, reverse-extract the completed events from the actual shot list and compare them one by one with the source event order, while checking the performer and target of every action. A one-sentence causal summary cannot merge “A rescues someone” and “B hands over a prop” into “A completed both actions.” Correct the shot or clearly mark it as A for unsupported actions such as someone receiving an item early, suddenly leaping over an obstacle, or abruptly becoming exhausted. Merely declaring “faithful to the source” earlier cannot replace this step. Spatial assumptions that have not yet been verified should remain qualified in the production brief and must not later become established facts.
To understand a full-text adaptation, read Original teaching example; to understand how scene selection affects actual production, read Jian Lai case study; to recognize prematurely completed events or material unsupported by the source, read Failure and boundary examples. The examples illustrate judgment methods and cannot serve as factual sources for other novels.