short-drama-novel-analyze

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

长篇原著分析

Long-Form Source Novel Analysis

把一部长材料变成能被引用、能被反驳、能被接着用的分析层。目标不是复述剧情，而是找出每一段承担的戏剧功能，并说明它在竖屏短剧里值多少钱。

分析永远是候选。哪条线保留、哪些人合并、从哪里开篇，是创作者的决定，由

$short-drama-develop

立成改编契约。本技能不替它决定，也不批准自己的产物。

Turn a long source material into an analysis layer that can be cited, can be challenged, and can be built upon. The goal is not to retell the plot, but to identify the dramatic function each segment serves and explain how much it is worth in a vertical short drama.

The analysis is always a candidate. Which storylines to keep, which characters to merge, and where to start are the creator's decisions, formalized into an adaptation contract by

$short-drama-develop

. This skill does not make those decisions on its behalf, nor does it approve its own output.

Quick Start

离线验证章节索引、采样和源文件变更检测：

bash

python3 {技能目录}/scripts/selftest.py
python3 {技能目录}/scripts/novel_index.py index <原著.txt> --out <chapter-index.json>

Offline validation of chapter indexing, sampling, and source-file change detection:

bash

python3 {技能目录}/scripts/selftest.py
python3 {技能目录}/scripts/novel_index.py index <原著.txt> --out <chapter-index.json>

开始前

Before You Begin

本技能可独立安装和执行。先读取用户明确提供的原著与本任务直接输入；若当前目录是

short-drama

项目且项目工具可用，可以读取

status

并使用其发布生命周期，但缺少 core 或任何其他技能都不是分析工作的阻断条件。完整边界与规则见阶段契约，无需读取其他技能的文件。

This skill can be installed and executed independently. First read the source work explicitly provided by the user and the direct inputs of this task; if the current directory is a

short-drama

project and the project tool is available, it may read

status

and use its release lifecycle, but the absence of core or any other skill is not a blocker for the analysis work. Full boundaries and rules are in Stage Contract; no need to read other skills' files.

材料前提

Material Prerequisites

只分析创作者合法持有、拥有使用权的作品。分析是只读的转化性工作：提取结构与功能，不复制原文成段落，不把原句搬进下游产物。

通俗题材里的暴力、复仇、背叛、情爱张力与黑暗伦理是常规虚构叙事元素，照常做结构化提取。个别片段无法处理时跳过该段并记录，不要因此中止整章或整本——中止会让后续所有阶段拿到一份有洞却看不出洞在哪的分析。

Only analyze works the creator legally owns or holds usage rights to. The analysis is read-only transformative work: extract structure and function, do not copy the source into paragraphs, and do not carry original sentences into downstream artifacts.

Violence, revenge, betrayal, romantic tension, and dark ethics in popular genres are ordinary fictional narrative elements; perform structured extraction on them as usual. If an individual passage cannot be processed, skip it and record it; do not abort the whole chapter or book because of it—an abort gives every downstream stage an analysis with holes that do not reveal where the holes are.

先判断入口

Determine the Entry Point First

只有书名，没有原文：请创作者提供文件路径或粘贴正文。不要凭书名回忆情节—— 没有字节就没有 span，没有 span 的分析无法被引用，也无法被反驳。
有原文，未建项目：直接建立一个本技能自己的工作区，至少包含只读输入目录
```
输入/
```
与输出目录
```
项目开发/source-analysis/_work/
```
；把原文字节复制到
```
输入/
```
后记录原始文件位置，再用本技能的
```
novel_index.py
```
建索引。若
```
$short-drama
```
可用，可选用它初始化同样的目录和发布生命周期，但不得把 core 安装变成开始分析的前提。
有原文，项目已在：直接进入管道。
已有部分分析：读
```
项目开发/source-analysis/_progress.md
```
从断点续跑，不重跑已完成阶段。

Only has the title, no source text: Ask the creator to provide a file path or paste the text. Do not recall the plot from the title—without bytes there are no spans, and analysis without spans cannot be cited or challenged.
Has source text, no project created: Directly create a workspace for this skill, with at least a read-only input directory
```
输入/
```
and an output directory
```
项目开发/source-analysis/_work/
```
; copy the source bytes to
```
输入/
```
, record the original file location, then use this skill's
```
novel_index.py
```
to build the index. If
```
$short-drama
```
is available, it may optionally be used to initialize the same directories and release lifecycle, but installing core must not become a prerequisite for starting the analysis.
Has source text, project already exists: Go straight into the pipeline.
Already has partial analysis: Read
```
项目开发/source-analysis/_progress.md
```
and resume from the breakpoint; do not rerun completed stages.

管道

Pipeline

输入/

是不可变的创作者输入，本阶段只读它。全部产出落在

项目开发/source-analysis/

。独立工作区与完整项目使用同一套相对路径，因此后续安装 core 时无需迁移分析产物。

阶段	做什么	产出	停靠
S0	建章节索引（脚本）	`_index.json` 、 `_progress.md`	索引有问题就停
S1	改编价值快评（抽样）	`triage.md`	停靠问创作者
S2	逐章功能提取	`chapters/ch-<N>-extract.md`	覆盖率不足就停
S3	剧情单元与节奏聚合	`story-units.md` 、 `rhythm-and-emotion.md`	阈值不达标就复核
S4	人物归并与设定	`characters.md` 、 `world.md`	—
S5	改编价值与分集候选	`adaptation-value.md` 、 `episode-candidates.jsonl`	交接 develop

输入/

is immutable creator input; this stage only reads it. All output lands in

项目开发/source-analysis/

. A standalone workspace and a full project use the same relative paths, so there is no need to migrate analysis artifacts when core is installed later.

Stage	What it does	Output	Gate
S0	Build chapter index (script)	`_index.json` , `_progress.md`	Stop if the index has problems
S1	Adaptation-value triage (sampling)	`triage.md`	Gate: ask the creator
S2	Per-chapter function extraction	`chapters/ch-<N>-extract.md`	Stop if coverage is insufficient
S3	Story-unit and rhythm aggregation	`story-units.md` , `rhythm-and-emotion.md`	Re-check if thresholds are not met
S4	Character consolidation and setting	`characters.md` , `world.md`	—
S5	Adaptation value and episode candidates	`adaptation-value.md` , `episode-candidates.jsonl`	Hand off to develop

S0 章节索引

S0 Chapter Indexing

索引是唯一切片真源，由章节索引脚本建立。每个阶段各跑一次正则，就会切出互相对不上的章节，第 47 章按一种边界分析、按另一种边界聚合，而且没有人会发现。

bash

python3 {技能目录}/scripts/novel_index.py index 输入/{原文文件} \
  --out 项目开发/source-analysis/_work/_index.next.json
python3 {技能目录}/scripts/novel_index.py verify \
  项目开发/source-analysis/_work/_index.next.json 输入/{原文文件}

The index is the only slice source of truth, built by the chapter indexing script. If every stage runs its own regex separately, chapters will be sliced against mismatched boundaries: chapter 47 is analyzed against one boundary and aggregated against another, and nobody notices.

bash

python3 {技能目录}/scripts/novel_index.py index 输入/{原文文件} \
  --out 项目开发/source-analysis/_work/_index.next.json
python3 {技能目录}/scripts/novel_index.py verify \
  项目开发/source-analysis/_work/_index.next.json 输入/{原文文件}

项目工具可用时可选：

python3 {core 技能目录}/scripts/project_tool.py publish {项目根}
--owner short-drama-novel-analyze --artifact-id source-analysis:index
--output 项目开发/source-analysis/_index.json=项目开发/source-analysis/_work/_index.next.json
--input 输入/{原文文件}


脚本识别阿拉伯数字与中文数字章号（含 千 / 两，覆盖千章以上连载），**只认一种编号单位**
（章/回/节里出现最多的那个，其余记进 `ignored_heading_units`），只把**短的独立行**当标题
（以章号开头的正文段落记进 `long_heading_lines_skipped`），剔除开头的目录块，
按卷分段校验编号。它**不做编辑判断**——哪章重要、
讲了什么，是后面阶段的事。

`problems` 非空就停下报告，不要带着错表进 S1。常见四种：章号跳号（缺章或抓错标题）、
同卷内重号、正文极少的章（多半抓到了目录残留或卷首页）、无法解析的章号。
另外确认三个计数：`chapter_unit` 与 `ignored_heading_units`——一本用 `第N章` 分章、
用 `第N节` 分小节的书应当看到 `chapter_unit: 章` 且 `节` 被记入忽略计数，反过来说明分章单位
判断错了；`long_heading_lines_skipped` 明显偏大时，多半是这本书的章节标题确实很长，
需要与创作者确认后手写边界。

原文本身没有章节标题时索引会返回空表，此时与创作者确认按什么切分，把边界写进
`_work/_index.next.json`，通过 `verify` 后再按上面的公开生命周期发布——手写的行也要带齐
`sequence` / `line_start` / `line_end`，`verify` 会逐行检查并报出缺字段的行。

改了原文必须重建索引，不能沿用旧 span。`verify` 核对编号、顺序与行号覆盖，所以插行删行会被报出来；
但同行数的原地改写不会——那一步靠改原文的人自己重建，套件不比对字节。

```bash
python3 {技能目录}/scripts/novel_index.py verify \
  项目开发/source-analysis/_index.json 输入/{原文文件}


The script recognizes Arabic numeral and Chinese numeral chapter numbers (including 千 / 两, covering serials with more than a thousand chapters), **recognizes only one numbering unit** (the most frequent among 章/回/节; the rest are recorded in `ignored_heading_units`), only treats **short standalone lines** as headings (body paragraphs beginning with a chapter number are recorded in `long_heading_lines_skipped`), removes the leading table-of-contents block, and validates numbering segment by volume. It makes **no editorial judgments**—which chapters matter and what they contain is the business of later stages.

If `problems` is non-empty, stop and report; do not carry an error table into S1. Four common types: numbered chapter gaps (missing chapter or wrong heading captured), duplicate numbers within the same volume, chapters with very little content (usually captured table-of-contents residue or volume front page), and unparseable chapter numbers. Also confirm three counts: `chapter_unit` and `ignored_heading_units`—a book divided into `第N章` with `第N节` subsections should show `chapter_unit: 章` with `节` recorded in the ignored count; the reverse indicates the chapter unit was misjudged. When `long_heading_lines_skipped` is conspicuously large, it usually means the book's chapter titles are genuinely long; confirm with the creator and write the boundaries by hand.

When the source text itself has no chapter headings, the index returns an empty table; in that case, confirm with the creator how to segment, write the boundaries into `_work/_index.next.json`, and after passing `verify`, publish through the public lifecycle above—hand-written rows must also carry `sequence` / `line_start` / `line_end`, and `verify` will check each row and report rows with missing fields.

If the source text is changed, the index must be rebuilt; old spans cannot be reused. `verify` checks numbering, order, and line-number coverage, so inserted or deleted lines will be reported; but an in-place edit with the same number of lines will not—that step depends on the person editing the source text to rebuild, because the suite does not compare bytes.

```bash
python3 {技能目录}/scripts/novel_index.py verify \
  项目开发/source-analysis/_index.json 输入/{原文文件}

S1 改编价值快评

S1 Adaptation-Value Triage

回答这本书值不值得花全量拆解的成本。判据是全书的改编密度——

screen_ready

单元占多少、

prose_only

占多少、制作负担压在哪几段——所以快评横跨整本书，用脚本抽样：

bash

python3 {技能目录}/scripts/novel_index.py sample \
  项目开发/source-analysis/_index.json --count 12

抽样确定、可复现、首尾必取，跑第二次引用的是同一批章。按改编价值快评写

triage.md

，覆盖六件事：故事框架、三类判定比例、开篇替换点、制作负担量级、最大的三处改编风险、分集候选量级。第一行写覆盖率（脚本返回的

coverage_ratio

），所有结论限于抽样范围。

这里停靠问创作者：给出快评与全量拆解的预计耗时（按章数粗估），问是否继续。创作者一开始就明确说「一次跑完」时仍写

triage.md

，但不停下等待——它是 S5 要回填对照的第一版假设。

停靠时把

_progress.md

的状态写成

paused_after_triage

，断点写「下一步：S2 逐章提取」。

S1–S5 的 Agent 创作产物同样先写到

source-analysis/_work/

，完成本阶段机械检查后再发布到上表中的正式路径。项目工具可用时用

project_tool.py publish

和稳定 artifact-id；独立运行时原子替换正式文件。不要用半成品覆盖

_index.json

、

_progress.md

、

chapters/*.md

或聚合产物。

_work/

是候选工作区，不是权威分析层，也不进入交付包。

并发子代理写
_work/
，主线程发布到正式路径。子代理只落

_work/chapters/ch-<N>-extract.md

，主线程跑完机械自检后再发布到

chapters/

。覆盖率闸门按正式路径

chapters/

匹配文件名——发布之前跑，每一章都会进

unmatched_files

，那不是缺陷，只是跑早了。

_progress.md

每个阶段都会重写，而发布要求一个路径只有一个 owner，所以它用一个固定 artifact-id：

source-analysis:progress

，owner 是

short-drama-novel-analyze

， S0–S5 每次停靠都用同一个 id 重新发布。

Answer the question whether this book is worth the cost of full decomposition. The criterion is the book's adaptation density—how many units are

screen_ready

, how many are

prose_only

, and where the production burden falls—so the triage spans the entire book and samples via a script:

bash

python3 {技能目录}/scripts/novel_index.py sample \
  项目开发/source-analysis/_index.json --count 12

The sample is deterministic, reproducible, and always includes the first and last chapters; running it a second time references the same set of chapters. Write

triage.md

according to Adaptation-Value Triage, covering six things: story framework, ratio of the three verdict classes, opening replacement point, production burden magnitude, the three biggest adaptation risks, and episode-candidate magnitude. The first line states the coverage rate (

coverage_ratio

returned by the script); all conclusions are limited to the sampled range.

Gate here and ask the creator: provide the estimated time for the triage and full decomposition (roughly by chapter count) and ask whether to continue. If the creator explicitly said 'run it all at once' from the start, still write

triage.md

, but do not stop and wait—it is the first version of assumptions S5 will backfill against.

At the gate, write the status in

_progress.md

paused_after_triage

, and write 'Next step: S2 per-chapter extraction' as the breakpoint.

The Agent-generated artifacts for S1–S5 are also written to

source-analysis/_work/

first, and only published to the official paths in the table above after the stage's mechanical checks. When the project tool is available, use

project_tool.py publish

and stable artifact-ids; when running standalone, atomically replace the official files. Do not overwrite

_index.json

_progress.md

chapters/*.md

, or aggregation artifacts with half-finished products.

_work/

is a candidate workspace, not the authoritative analysis layer, and is not part of the deliverable package.

Concurrent subagents write to
_work/
, and the main thread publishes to the official paths. Subagents only land

_work/chapters/ch-<N>-extract.md

; the main thread runs its mechanical self-checks and then publishes to

chapters/

. The coverage gate matches filenames against the official

chapters/

path—if you run it before publishing, every chapter appears in

unmatched_files

; that is not a bug, it just means the check ran too early.

_progress.md

is rewritten at every stage, and publishing requires one owner per path, so it uses a fixed artifact-id:

source-analysis:progress

, with owner

short-drama-novel-analyze

; every S0–S5 gate republishes with the same id.

S2 逐章功能提取

S2 Per-Chapter Function Extraction

按章节提取处理每一章。能并发子代理就分批并发（每批 5–8 章，等一批落盘再发下一批），不支持就串行——两条路径的写法要求和自检是同一份，只是速度不同。

每章提取完落到

chapters/ch-<N>-extract.md

，

<N>

是索引里的

sequence

，不是原文章号（多卷书的原文章号会重复，sequence 不会）。全部落盘后跑覆盖率：

bash

python3 {技能目录}/scripts/novel_index.py coverage \
  项目开发/source-analysis/_index.json 项目开发/source-analysis/chapters

missing

非空就补跑缺的章；

unmatched_files

非空说明有文件名写歪了——它既不算覆盖，也不会被当成缺章，必须改名而不是重跑。不要在覆盖率不足时进入 S3——聚合会照样产出一份读起来完整的结果，而缺掉的章不会在任何地方留下痕迹。

单章连续失败两次就标记跳过，写进

_progress.md

的失败记录，并在后续每一份聚合产物里注明该章缺失。失败可以接受，失败被藏起来不行。

Process each chapter according to Chapter Extraction. If concurrent subagents are supported, batch them (5–8 chapters per batch; wait for one batch to land before dispatching the next); otherwise run serially—both paths share the same writing requirements and self-checks, only the speed differs.

After each chapter is extracted, land it in

chapters/ch-<N>-extract.md

, where

<N>

is the

sequence

from the index, not the original chapter number (original chapter numbers repeat in multi-volume books;

sequence

does not). After all chapters are on disk, run coverage:

bash

python3 {技能目录}/scripts/novel_index.py coverage \
  项目开发/source-analysis/_index.json 项目开发/source-analysis/chapters

missing

is non-empty, run the missing chapters; if

unmatched_files

is non-empty, a filename was written incorrectly—it is neither counted as coverage nor treated as a missing chapter; rename the file instead of rerunning. Do not enter S3 with insufficient coverage—aggregation will still produce a complete-looking result, while the missing chapters leave no trace anywhere.

If a single chapter fails twice in a row, mark it as skipped, record it in the failure log in

_progress.md

, and note the missing chapter in every subsequent aggregation artifact. Failure is acceptable; hiding failure is not.

S3 剧情单元与节奏

S3 Story Units and Rhythm

从逐章提取聚合，不回头重读原文——原文已经在 S2 被读过一次，再读一次只会得到第二份互相矛盾的事实。按聚合与实体先识别故事框架（框架决定按什么切单元），再产出：

```
story-units.md
```
：把情节点归成有始有终的单元，每个单元记录进入状态、冲突、代价与出去状态；
```
rhythm-and-emotion.md
```
：关键信息如何逐章推进、情绪触动点的铺垫→释放→余波、跨章伏笔与兑现。

聚合完成后跑同一文件里的三条阈值自检（归属置信、覆盖率、重叠率）与散落情节兜底。阈值不是评分，是边界模糊的信号：重叠率过高说明两个单元其实是一个。

Aggregate from the per-chapter extraction; do not go back and reread the source—the source was already read once in S2, and reading it again only produces a second set of mutually contradictory facts. According to Aggregation and Entities, first identify the story framework (the framework determines how units are cut), then produce:

```
story-units.md
```
: group plot points into units with a beginning and an end, each recording entry state, conflict, cost, and exit state;
```
rhythm-and-emotion.md
```
: how key information advances chapter by chapter, the setup → release → aftermath of emotional beats, and cross-chapter foreshadowing and payoff.

After aggregation, run the three threshold self-checks in the same file (assignment confidence, coverage, overlap) and the orphan-plot fallback. Thresholds are not scores; they are signals of fuzzy boundaries: an overlap rate that is too high means two units are actually one.

S4 人物与设定

S4 Characters and Setting

按聚合与实体归并人物（跨章去重、别名归一、分级），并从提及数据归纳世界规则、力量体系与势力。别名只有专名与有同指证据的绰号能合并，描述性称谓与头衔永远不触发合并。

人物归并是候选，不是资产。这里的人物条目带

unresolved

与来源引用，交给

$short-drama-develop

定改编决定、

$short-drama-write

写进剧本之后，才由

$short-drama-assets

从已接受剧本建立真正的资产身份。绕过这条链直接建资产，等于让原著的人物表冒充剧本的出现证据。

Consolidate characters according to Aggregation and Entities (deduplicate across chapters, normalize aliases, classify by prominence), and infer world rules, power systems, and factions from mention data. Aliases can only be merged when they are proper names or nicknames with co-reference evidence; descriptive epithets and titles never trigger a merge.

Character consolidation is a candidate, not an asset. The character entries here carry

unresolved

and source references; only after

$short-drama-develop

makes adaptation decisions and

$short-drama-write

writes them into the script does

$short-drama-assets

build real asset identities from accepted scripts. Bypassing this chain and building assets directly is equivalent to letting the source novel's character table impersonate script appearance evidence.

S5 改编价值与分集候选

S5 Adaptation Value and Episode Candidates

这是本技能与通用拆书的分水岭。按改编价值产出：

```
adaptation-value.md
```
：哪些单元在竖屏短剧里能直接成立、哪些要换载体、哪些是纯文字快感（内心戏、叙述性诡计、长铺垫）在画面上无法兑现；制作负担落在哪里。
```
episode-candidates.jsonl
```
：按局部戏剧结果与精确交接切出的候选集，不按章号或字数平均切。每条带来源 span、承担的功能、以及未决项。

同时回填快评：S1 的哪几条判断被全量结果推翻了，写进

adaptation-value.md

的开头。一个抽样结论被证伪，比它被悄悄忘掉有用得多——下一本书的快评会因此更准。

样例见分集候选样例。

This is the dividing line between this skill and generic book decomposition. Produce, according to Adaptation Value:

```
adaptation-value.md
```
: which units can directly work in a vertical short drama, which need a different medium, and which are pure textual pleasures (inner monologue, narrative tricks, long setups) that cannot be realized on screen; where the production burden falls.
```
episode-candidates.jsonl
```
: candidate sets cut by local dramatic outcome and precise handoff, not averaged by chapter number or word count. Each entry carries source spans, the function it serves, and open items.

At the same time, backfill the triage: which S1 judgments were overturned by the full results, written at the top of

adaptation-value.md

. A sampling conclusion being falsified is far more useful than being silently forgotten—it makes the next book's triage more accurate.

See Episode Candidate Example.

交接

Handoff

S5 完成后展示创作者可读的摘要，说明：拆了多少章、跳过哪些、分了多少个候选集、最大的三处改编风险、以及快评里被推翻的判断。然后交给

$short-drama-develop

—— 由它把候选变成

项目开发/adaptation-map.jsonl

与改编契约。

本技能不写
adaptation-map.jsonl
，那是 develop 的产物。需要质量结论时交给独立的

$short-drama-review

（范围

source_analysis

）。

After S5, present a creator-readable summary stating: how many chapters were decomposed, which ones were skipped, how many candidate sets were produced, the three biggest adaptation risks, and which triage judgments were overturned. Then hand off to

$short-drama-develop

—it turns the candidates into

项目开发/adaptation-map.jsonl

and the adaptation contract.

This skill does not write
adaptation-map.jsonl
; that is develop's artifact. When a quality conclusion is needed, hand it to the independent

$short-drama-review

(scope

source_analysis

规则分级

Rule Levels

structural_invariant
：索引与 span 的可证明性、引用完整性、覆盖率。可由脚本阻断。
reviewed_invariant
：功能提取是否忠于原文、归并是否保住戏剧作用等语义义务。
craft_default
：通常有帮助的做法；创作者说明理由后可覆盖。
taste_option
：从哪里开篇、保留哪条线等选择；不得单独阻断。

不要用固定的章数配方、情节点数量或篇幅比例替代因果判断。

structural_invariant
: provability of the index and spans, citation integrity, coverage. Can be blocked by scripts.
reviewed_invariant
: semantic obligations such as whether the function extraction is faithful to the source and whether consolidation preserves dramatic function.
craft_default
: practices that are usually helpful; can be overridden when the creator provides a reason.
taste_option
: choices such as where to open and which storyline to keep; cannot block on their own.

Do not replace causal judgment with fixed chapter-count formulas, plot-point counts, or section-length ratios.

产物与边界

Artifacts and Boundaries

本技能只拥有

项目开发/source-analysis/

下的文件：

_index.json

、

_progress.md

、

chapters/*.md

、

triage.md

、

story-units.md

、

rhythm-and-emotion.md

、

characters.md

、

world.md

、

adaptation-value.md

、

episode-candidates.jsonl

。

它不改写

输入/

，不写

项目开发/

下其他技能的产物，不建资产、不写场景与台词、不写提示词、不生成媒体，也不签发终审结论。

不把原文成段复制进分析。记录 locator、span 与去引用的功能摘要；需要证据时引用最短的必要片段。交付包不得把原始材料带出边界。

This skill owns only the files under

项目开发/source-analysis/

_index.json

_progress.md

chapters/*.md

triage.md

story-units.md

rhythm-and-emotion.md

characters.md

world.md

adaptation-value.md

episode-candidates.jsonl

It does not rewrite

输入/

, does not write other skills' artifacts under

项目开发/

, does not build assets, write scenes or dialogue, write prompts, generate media, or issue final review conclusions.

Do not copy source text in paragraphs into the analysis. Record locators, spans, and de-referenced functional summaries; when evidence is needed, quote the shortest necessary fragment. The deliverable package must not carry raw material outside the boundary.

语言

Language

分析产物是创作者读的：项目内跟随

short-drama.json#/language

，独立运行时跟随用户使用的语言，不在本技能内硬编码语言。本技能不产生提示词正文，与

#/format/prompt_language

无关。

Analysis artifacts are read by creators: inside a project, follow

short-drama.json#/language

; when running standalone, follow the language the user is using. The skill does not hardcode a language. This skill does not produce prompt text, so it is unrelated to

#/format/prompt_language

按需加载

On-Demand Loading

快评读哪些章、写哪六件事、怎么不冒充全量分析：改编价值快评
逐章提取写法、白描与叙事框架词的界线、机械自检、并发与串行：章节提取
故事框架、剧情单元、节奏情绪、人物归并、阈值与散落兜底：聚合与实体
改编价值评估、载体替换与分集候选切法：改编价值
本阶段拥有什么、继承什么、不越权什么：阶段契约

Which chapters the triage reads, what six things it writes, and how it avoids masquerading as full analysis: Adaptation-Value Triage
Per-chapter extraction style, the line between plain description and narrative-framework words, mechanical self-checks, concurrency and serial execution: Chapter Extraction
Story framework, story units, rhythm and emotion, character consolidation, thresholds, and orphan-plot fallback: Aggregation and Entities
Adaptation-value assessment, medium substitution, and episode-candidate cutting: Adaptation Value
What this stage owns, inherits, and must not overstep: Stage Contract