short-drama-develop

Short Drama Development

Turn the creator's intent into something that can continuously generatechoices, costs, and state changesstory system. Preserve the creator's genre, ending, and scale choices; do not treat popular tropes as the answer to the plot.

Quick Start

Offline verification of precise indexing, slicing, and source file change detection for complete multi-episode scripts:

python3 {技能目录}/scripts/selftest.py
python3 {技能目录}/scripts/episode_intake.py index <多集整稿> --out <episode-intake-index.json>

Before starting

This skill can be installed and executed independently. First read the materials explicitly provided by the user and the direct input for this task; if the current directory is a short-drama project and the project tools are available, you may read status and use its release lifecycle, but the absence of core or any other skill is not a blocking condition for development work.Stage contract gives the boundaries of this stage, production form inputs, and rule tables, without needing to read files from other skills.

First determine the entry point

Only an idea, genre, or emotional goal: complete direction exploration, then establish the creative brief and story engine.
Already have a synopsis, novel, adaptation materials, or series notes: preserve the source and first list the committed facts, changeable scope, source fragments, and items to be confirmed. For long materials, first do semantic segmentation, a function ledger, and candidate episodes; do not directly publish episodes or assets based on regex name/noun hits; do not swap out the original meaning.
Direction is set, only episode planning is needed: read the existing brief and engine, and directly produce or revise the episode map.
Already have a single-episode script: do not fabricate development materials just for process completeness. Leave writing/revising the script to $short-drama-write; splitting assets or subsequent production can enter directly from the corresponding skill.
Already have a complete multi-episode script and need to generate or supplement an episode map: keep the original file, only load Complete Multi-Episode Script Intake and Resume from Breakpoint. Let the Agent decide the boundaries and the current batch according to the file's actual structure; the tools only perform precise indexing, single-episode slicing, validation, and resumption, and do not write creative judgments on behalf of the creator.

When information is sufficient, work directly. Only gaps that would change the protagonist, conflict engine, ending promise, or adaptation boundaries need to be asked about.

Each execution

1. Lock the creator contract

Read the creator input and accepted files, and distinguish:

Unchangeable facts, themes, characters, and ending promises;
Blank spaces that can be explored;
Form constraints and production boundaries;
The emotional, informational, or power payoff that the target audience can repeatedly obtain.

For a new project, copy creative-brief.md. If changing accepted facts, first show the semantic differences and downstream impact, and do not directly overwrite.

2. Explore truly different directions

When the direction is undetermined, propose a small number ofmechanically differentCandidates: change the protagonist's strategy, the source of antagonism, the cost, or the mode of sustained conflict, rather than merely swapping the title, profession, and wording. When the direction is clear, deepen it directly; do not manufacture false differences just to fill out options.

For each candidate, state: the dramatic promise, what the protagonist pursues, the mechanism of antagonism, the recurring payoff, the escalatable states, the long-term termination condition, and the main production burden. Let the creator choose or combine, and record the rationale for the trade-offs; options not chosen do not enter established facts.

When the full method is needed, read story-craft.md. Once the genre is determined, you can take from genre-cards.md by indexonegenre card, to calibrate the pressure sources, scene granularity, and production burden more commonly used for that genre; it is a reference that can be overridden by the creator in a single sentence, does not replace the direction choice, and does not enter the deliverables.

If the setup has the protagonist carrying a past experience that has already happened, or having acquired a set of externally authorized abilities, that is a premise devicelayered on top of the genre; also read premise-devices.md—a device cancels resistance, so it must first be given boundaries and costs. A device does not replace the genre card, nor does it warrant building a separate genre for it.

3. Build the story engine

Copy story-engine.md, and write clearly:

how the pressure arises, and how the protagonist usually responds;
how the opponent or system counteracts, and why the protagonist cannot easily exit;
what each round of conflict changes, rather than how it repeats more loudly;
each character's goals, leverage, bottom lines, and relationship pressures;
which character transformation or revelation of fact would end this engine;
visuals, sound, scene scale, and content boundaries.

For serialized drama, long-form adaptations, or when vertical character change is heavier, then read serial-character-and-memory.md: first build a backstory reserve for the author's decisions only, choose the narrative entry window at which the old strategy begins to exact a cost, and then record the beliefs the character defends, the stress tests, information permissions, and cross-episode memory. Do not pour the backstory reserve directly into the first episode's dialogue.

4. Land the series movement into episodes

Read episode-design.md, then copy episode-map.jsonl. For each episode, record the entering state, the opening, that episode's pursuit, resistance, the directional turn, that episode's outcome, information release, the pressure going out, and the facts the next episode must inherit.

First ensure that each episode produces a local dramatic outcome and that adjacent episodes can hand off precisely, and only then discuss the dual-track rhythm of external pressure/emotional load. For the Episode 1 entry, first compare the benefit entry with the cold open; for adaptation projects, first read the original work's analysis of the payoff table, and place the highlights at the earliest point the audience can receive them. The episode count, hook types, whether there is a twist, and the climax position are decided by the creator and the project.

Once the production form is fixed, propose a project rhythm profile based on the defaults in the episode design, write it into the creative brief for the creator to accept; after acceptance, $short-drama writes it into creator_authority.rhythm_profile。

5. Do the owner check and hand off

Before submitting the preview, check:

the referenced episodes, setups, and payoff records can be found, and open items are clearly marked;
the candidates genuinely change the mechanism, and the chosen direction runs through the brief, the engine, and the episode map;
each escalation can point to a change in power, information, relationships, exposure, resources, time, or cost;
each episode first pays off part of that episode's promise, then leaves a specific decision, danger, or question;
in adaptation projects, the core characters' positions, core relationships, and main line have not been rewritten; all additions not present in the original work are registered as add, and list them in the brief;
did not pass off format preferences as universal laws.

These are owner self-checks, not final review. Present a creator-readable summary of additions/changes; ask the creator to accept them before they are used as a downstream source; when a quality conclusion is needed, treat $short-drama-review as a separate follow-up request, preferably executed by a reviewer who did not participate in creating the current version.

If the project needs a director's statement, this skill only produces 项目开发/director-brief.md candidates and marks the visual_direction / production_profile semantic differences they are intended to be written into. After the creator accepts, $short-drama routing promotes the selection to creator authority; the development skill does not directly rewrite that authoritative configuration.

Rule tiers

structural_invariant: locally provable references, IDs, and explicit state contradictions; can be blocked by a validator.
reviewed_invariant: semantic obligations such as whether an escalation is real or whether a promise is fulfilled; judged by a reviewer citing evidence.
craft_default: practices that are usually helpful; the creator may override them after explaining the reason.
taste_option: choices such as hooks, arcs, point of view, and ending tone; must not block on their own.

Do not replace causal judgment with fixed plot points, turning moments, length ratios, or quantity formulas; pacing figures appear only in the project pacing profile accepted by the creator.

Artifacts and boundaries

This skill owns only:

项目开发/creative-brief.md
项目开发/story-engine.md
项目开发/director-brief.md(when the project needs it; creator authority candidates only)
项目开发/adaptation-map.jsonl(when adapting long material; retain only input locators/spans, de-quoted functional summaries, candidate destinations, and open items; do not copy the source text; for examples see adaptation-map.example.jsonl）
项目开发/series-arc.json(when the project needs it)
项目开发/episode-intake-index.json(when integrating multiple episodes of full drafts; a mechanically rebuildable index, not a creative fact)
项目开发/episode-map.jsonl

It does not write scene action or dialogue, does not break down assets, does not write image/video prompts, does not generate media, and does not issue final review conclusions. Script semantics are taken over by $short-drama-write .

Load on demand

promises, engines, character pressure, escalation, and payoff fulfillment：story-craft.md
episode contracts, causal beats, inter-episode handoffs, first-episode entry, threshold episodes, and the project pacing profile：episode-design.md
there are existing complete scripts/loose drafts for multiple episodes, and full drafts must be kept out of context while allowing interruption and resumption： multi-episode-intake.md
character drive, backstory and entry point, cross-episode change, information permissions, dual-track pacing, and recovery memory： serial-character-and-memory.md
there is source material and it needs to be compressed around payoff points, later content moved earlier or given a cold open, characters/scenes merged, and information visualized： adaptation-craft.md
the creator provides benchmark works, sample scripts, or prompts and wants to learn the mechanism rather than imitate the expression： creative-reference-intake.md
the same mechanism is run repeatedly in a unit story, or the middle section starts repeating and gets thinner as it goes： mechanism-loop.md
there is a need to distinguish reveals, reversals, payoffs, and hooks, or to choose pressure mechanisms by genre： reveal-reversal-payoff.md
qualitative case methods for choosing conflict escalation modes by genre, designing openings, or planning end-of-episode hooks： genre-and-hook-playbook.md
the genre is already determined, and the more commonly used pressures, scene granularity, hook orientations, and production difficulties for that genre are needed： genre-cards.md(index and recall specification; read only one card at a time)
the protagonist starts with a known outcome, or gains an externally authorized ability： premise-devices.md(device layer, overlaid on top of the genre card)
draft project-level visual direction and production rules (director's statement)： director-brief-craft.md
what this stage owns, what it inherits, and what it must not exceed authority over：stage-contract.md