Agent skill

Novel Outline

by eternityspring in eternityspring/shuohao-skills

把一本小说改编成短剧大纲五件套:改编说明、人物表、爽点表、分集梗概、资产清单, 产出 outline.json + Markdown + 单页评审报告(KPI 带、关键决策、爽点时间轴、调度矩阵、场景概览、质量门)。

Apache-2.0Auto-check: notesWriting & Content

Install Novel Outline

skills CLI
$ npx skills add eternityspring/shuohao-skills --skill novel-outline -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install eternityspring/shuohao-skills novel-outline --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/eternityspring/shuohao-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/novel-outline .claude/skills/novel-outline && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
novel-outline
GitHub stars
4.3k
Token cost
~1.2k tokens
SKILL.md length
220 words
Files
12 (incl. scripts, references, assets)
Skills in repo
6
Repo updated
First seen
Licence
Apache-2.0

At a glance

把一本小说改编成短剧大纲五件套:改编说明、人物表、爽点表、分集梗概、资产清单, 产出 outline.json + Markdown + 单页评审报告(KPI 带、关键决策、爽点时间轴、调度矩阵、场景概览、质量门)。

  • Works in 8 steps: 收参数 ⛔ 缺了不开工 → 定位输入 → 分卷摘要(长文本才需要) → …
  • Asked to 改编大纲、短剧大纲、拆大纲、小说转短剧、adaptation outline
  • SKILL.md covers novel-outline, 体检模式, 联动更新 and 边界, plus 2 more sections
  • Runs JavaScript scripts from its folder; calls node

What it does

Novel Outline is an agent skill from eternityspring/shuohao-skills. 把一本小说改编成短剧大纲五件套:改编说明、人物表、爽点表、分集梗概、资产清单, 产出 outline.json + Markdown + 单页评审报告(KPI 带、关键决策、爽点时间轴、调度矩阵、场景概览、质量门)。 14 道质量门全部由脚本确定性检查(角色分档上限、主场景上限随集数动态、爽点间隔≤3集、每集钩子悬念必填……),不靠模型自觉; 支持体检模式:贴一份现成大纲进来,只跑质量门给诊断。 零依赖、零 API key,用当前会话额度。 Use when asked to 改编大纲、短剧大纲、拆大纲、小说转短剧、adaptation outline。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including scripts, reference files and assets (for example `README.en.md`, `README.md` and `examples/渡口-outline.json`).

It sits in Writing & Content, covering Creative writing and fiction and OKRs and executive reporting. The repository describes itself as: AI 短剧制作的 skill 集合:拆角色、排大纲、出场景与道具设定、写剧本、切分镜 | Agent skills for AI short-drama production — character bibles, adaptation outlines, art bibles, screenplays, storyboards. Runs in… The licence is Apache-2.0.

When your agent uses it

  • Asked to 改编大纲、短剧大纲、拆大纲、小说转短剧、adaptation outline
  • Tasks that involve Creative writing and fiction
  • Tasks that involve OKRs and executive reporting

Example prompts

  • “/novel-outline”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Read, Write, Bash, Task, Glob

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. 收参数 ⛔ 缺了不开工
  2. 定位输入
  3. 分卷摘要(长文本才需要)
  4. 快版骨架 → 用户拍板 ⛔
  5. 细版骨架
  6. 分集梗概(分批)
  7. 校验 ⛔ 不能跳
  8. 输出与汇报

What it can do on your machine

Read from SKILL.md and the folder at commit c27ea0e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Bash
    • Task
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Novel Outline loads about 1.2k tokens when it runs, and up to ~6k if it reads all its reference files. Until then it costs about 74 tokens; SKILL.md has 220 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Bash, Task, Glob

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from eternityspring/shuohao-skills at commit c27ea0e, republished under its Apache-2.0 licence (© eternityspring). 220 words, ~1,200 tokens.

Download SKILL.mdSave it as .claude/skills/novel-outline/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
novel-outline
description
把一本小说改编成短剧大纲五件套:改编说明、人物表、爽点表、分集梗概、资产清单, 产出 outline.json + Markdown + 单页评审报告(KPI 带、关键决策、爽点时间轴、调度矩阵、场景概览、质量门)。 14 道质量门全部由脚本确定性检查(角色分档上限、主场景上限随集数动态、爽点间隔≤3集、每集钩子悬念必填……),不靠模型自觉; 支持体检模式:贴一份现成大纲进来,只跑质量门给诊断。 零依赖、零 API key,用当前会话额度。 Use when asked to 改编大纲、短剧大纲、拆大纲、小说转短剧、adaptation outline。
allowed-tools
Read, Write, Bash, Task, Glob
version
2.0.0
triggers
novel-outline, 改编大纲, 短剧大纲, 拆大纲, 小说转短剧, 大纲体检, adaptation outline
metadata.license
Apache-2.0
metadata.runtimes
claude-code, codex

novel-outline

输入一本小说 + 目标参数,输出短剧改编大纲五件套。四件模型写、一件脚本算(资产清单从分集数据自动汇总)。

{baseDir} = 本文件所在目录。脚本 {baseDir}/scripts/novel-outline.mjs,零依赖,node 直接跑。

边界(不做的事):不写剧本台词、不做分镜、不出图像/TTS 提示词。梗概是叙述体,出现引号对白就是越界——validate 会拦。想从小说拆角色设定(画像/形象提示词/设定图),那是 novel-characters 的活。


Step 0 — 收参数 ⛔ 缺了不开工

一次问完,别轮流盘问。两件必问 + 两件给默认值待确认:

参数处理
总集数 × 单集时长必问,没有合理默认
题材必问,决定爽点类型,猜错整份废
改编幅度默认抽核(忠实 / 抽核 / 借壳),告知即可
已有偏好默认无(想保哪个角色、哪场戏)

平台阈值不同可以带上 params.thresholds 覆盖(默认:主角组 ≤ 5、重要配角 ≤ 10、功能性角色 ≤ 10、爽点间隔 ≤ 3 集)。主场景上限不用配,随集数自动算:4 + ⌈集数/10⌉,夹在 5–15(60 集 → 10)。这是 AI 短剧的数——场景是生成的没有搭景钱,放宽换观赏性;显式给 maxPrimaryScenes 才覆盖。短篇(20–30 集)建议收紧角色档的阈值,默认值是按 60 集以上给的。

人物表从原文拆——大纲是角色设定的上游,characters 块定下的分档、人物线与来源,下游 novel-characters 直接拿去当角色清单,不用再判断一遍谁重要。

例外是用户手上已经有 cast.json(此前单独跑过 novel-characters):那就拿来当人物原料,角色、别名、关系都是现成的,不用重拆原文。分档按 importance 反向映射:protagonist/major → lead,supporting → support,minor → functional。

Step 1 — 定位输入

材料优先级,写死:

  1. 用户点名的精读章节
  2. 章节目录 + 简介
  3. 全文分卷摘要(Step 2)

禁止凭书名脑补内容——一切判断基于给到的文本。落地手段:adaptation.keep 的关键取舍要附 evidence(原文逐字片段)。

直接粘正文的先落成 .txt。输出目录:用户指定就用,没指定用原书同级目录。

Step 2 — 分卷摘要(长文本才需要)

这一步是脚手架,不是交付物——分卷摘要是给没读过原文的模型压缩用的。两种情况直接跳到 Step 3:

  • 短篇,单卷装得下
  • 当前会话已经通读过原文——不用再压缩一遍,也不用事后补档

长篇且没读过原文:

bash
node {baseDir}/scripts/novel-outline.mjs chunk <book.txt> <workdir>

按章节标题分卷(默认每卷 15 章,--per-volume 可调),识别不出章节就按字数切。打印 {"volumes": N, ...};truncated: true 就明确告诉用户尾部没扫到,别闷着。

每卷一个子代理(支持并发就同一条消息里全部发出):读 {baseDir}/references/volume-pass.md,读 <workdir>/vol-NN.txt,把卷摘要写到 <workdir>/summary-NN.json,只回一句「done NN」。

Step 3 — 快版骨架 → 用户拍板 ⛔

读 {baseDir}/references/outline-pass.md 和 {baseDir}/references/schema.md,照着做。产出骨架四块(adaptation / characters / scenes / beats),写成 <workdir>/outline.json。

bash
node {baseDir}/scripts/novel-outline.mjs validate <workdir>/outline.json --stage beats

过了 beats 档,把三件事摆给用户拍板:砍了哪条线、合了哪些人、大爆点落在第几集。不点头不进 Step 4——快版错了只损失一轮骨架,分集写完才发现方向错,全废。

Step 4 — 细版骨架

吸收用户意见改骨架,再过一次 validate --stage beats。用户没意见就直接进 Step 5。

Step 5 — 分集梗概(分批)

每批 ≤ 10 集,能并发就并发。每个子代理拿到:拍板后的骨架四块、自己负责的集数区间、区间内的爽点,读 {baseDir}/references/episode-pass.md 照着写,产出写到 <workdir>/eps-NN.json。

合并时按 ep 排序拼进 outline.json 的 episodes。

Step 6 — 校验 ⛔ 不能跳
bash
node {baseDir}/scripts/novel-outline.mjs validate <输出目录>/<书名>-outline.json

14 道质量门全部是代码,不是给你读的清单:主角组 1–5 人、重要配角 ≤ 10、功能性角色 ≤ 10、主场景不超上限(随集数动态,60 集 → 10)、叙事道具 ≤ 8 件、一次性场景有规避方案、爽点间隔 ≤ 3 集无真空、第 1 集有钩子、大爆点不压最后一集、每集三栏齐全、三人同框有拆解、生成难点进预警、引用完整无失业角色无空转场景无零集道具、叙述体无对白。

有违规逐条修,改完重跑,直到通过。

Step 7 — 输出与汇报
bash
cd <输出目录>
node {baseDir}/scripts/novel-outline.mjs render <书名>-outline.json --md   > <书名>-outline.md
node {baseDir}/scripts/novel-outline.mjs render <书名>-outline.json --html > outline-report.html

报告界面默认中文;用户要英文界面就加 --lang en(或在 outline.json 顶层写 lang 字段,--lang 优先)。只翻译界面文案,数据内容(爽点类型、梗概、质量门文案)原样出。

report 里自带:KPI 带、关键决策(拍板三件事,大爆点列表和角色位统计自动算)、爽点时间轴(空档标在轴上,超阈值变红)、每集调度矩阵、场景概览卡、资产量折算、质量门(✓/✗ 烘进页面,未过弹病灶横幅)、导出 JSON 按钮(下载的就是 outline.json 原样)。

汇报一句话说清:几集、几个角色几个场景、爽点分布、报告路径;被截断或有没过的门要明说。

最终落地:

<输出目录>/
├── <书名>-outline.json
├── <书名>-outline.md
└── outline-report.html            ← 双击就能开

体检模式

用户贴一份已有大纲只想要诊断:转成 outline.json(缺的字段问用户或标注缺失),然后:

bash
node {baseDir}/scripts/novel-outline.mjs checkup <outline.json>   # 终端 ✓/✗
node {baseDir}/scripts/novel-outline.mjs render <outline.json> --html > outline-report.html

质量门面板就是诊断书。未过的门不阻止渲染——要的就是把病灶摆出来看。

联动更新

用户改了上游就跑一次 validate,报错会点名下游哪里断了:合并人物后哪些集还引用着被删的 ID、砍场景后哪些集空转、爽点挪动后哪里出现真空区。不要靠记忆提示联动,靠校验器。

边界

  • 单次上限 60 卷(每卷 15 章约 900 章)。超了明确报 truncated,不静默截断
  • 阈值是参数不是圣旨:平台不同就用 params.thresholds 覆盖,别改代码
  • 报告界面内置中英(--lang,默认中文、或跟 outline.json 的 lang 字段):界面文案与质量门标签翻译,数据内容(爽点类型、梗概、人名)与门的失败详情保持原文
  • 五件套的第五件(资产清单)永远是算出来的,模型手写必漏

自测

bash
node {baseDir}/scripts/selftest.mjs

249 项断言,不调模型、不花额度。14 道质量门每一道都有击穿用例——证明它真的会拦。改完脚本先跑这个。

自带样例

{baseDir}/examples/渡口-outline.json:把短故事《渡口》(novel-characters 的自带样例)改编成 6 集 × 2 分钟的微型大纲,四角色三场景四爽点,全部质量门通过。当质量基准,也是自测夹具。

© eternityspring, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (scripts, references, assets) in skills/novel-outline of eternityspring/shuohao-skills.

  • SKILL.md
  • README.en.md
  • README.md
  • assets/report.webp
  • examples/渡口-outline.json
  • references/episode-pass.md
  • references/outline-pass.md
  • references/report-style.md
  • references/schema.md
  • references/volume-pass.md
  • scripts/novel-outline.mjs
  • scripts/selftest.mjs

Open the folder on GitHubat commit c27ea0e

Compare with similar skills

Novel Outline next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Novel Outline compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Novel Outline this skilleternityspring/shuohao-skills4.3k—~1.2kAutomated safety check: NotesApache-2.0
Reading Guidechingswy/Skill-Research-Figure179—~4.5kAutomated safety check: PassNone
Exec Summarymvschwarz/openrig6.6k—~723Automated safety check: PassApache-2.0
Weekly Ops Reportdavila7/claude-code-templates33k—~861Automated safety check: PassMIT
Product Marketing Contextminhnv0807/ai-business-skills609—~2.1kAutomated safety check: PassMIT
Business Intelligenceericrisco/rsc-harness180—~2.5kAutomated safety check: PassMIT

Similar skills

  • Reading Guide

    chingswy/Skill-Research-Figure

    Structured learning navigator for blog posts and articles. An agent skill from chingswy/Skill-Research-Figure.

    179 GitHub stars~4.5k tokensUpdated 29 days ago
    Writing & ContentAuto-check passed
  • Exec Summary

    mvschwarz/openrig

    Generate a 1-2 page executive summary for a feature — orients sales, leadership, and engineering from a single document.

    6.6k GitHub stars~723 tokensUpdated today
    Writing & ContentAuto-check passed
  • Weekly Ops Report

    davila7/claude-code-templates

    Turn raw operational data into a weekly management report that answers exactly three questions - what changed, where is it concentrated, what needs a decision.

    33k GitHub stars~861 tokensUpdated today
    Writing & ContentAuto-check passed
  • Product Marketing Context

    minhnv0807/ai-business-skills

    Dung khi bat dau lam viec voi mot san pham hoac khach hang moi — skill nay tao FILE CONTEXT ma hon 60 skill khac se doc, gom san pham, khach hang, dinh vi, proof, objection, brand voice va KPI.

    609 GitHub stars~2.1k tokensUpdated 28 days ago
    Writing & ContentAuto-check passed
  • Business Intelligence

    ericrisco/rsc-harness

    A skill your agent uses when a metric (revenue, MRR, margin) needs defining once in a governed semantic layer so every dashboard, report and agent returns the same number, or when an LLM must answer…

    180 GitHub stars~2.5k tokensUpdated today
    Writing & ContentAuto-check passed
  • Linkedin Company Pages

    social-media-skills/skills

    The LinkedIn company-page (LINKEDINPAGES) growth strategy skill -- a separate platform from personal LINKEDIN.

    134 GitHub stars~2k tokensUpdated 8 days ago
    Writing & ContentAuto-check passed

More from eternityspring/shuohao-skills

  • Novel Art

    eternityspring/shuohao-skills

    给 AI 短剧出美术设定集(场景 + 叙事道具):场景的设计意图、一致性锚点、光照时段变体、 空景提示词;道具的戏剧功能、状态变体、尺度参照、白底无手提示词。

    4.3k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check: notes
  • Novel Characters

    eternityspring/shuohao-skills

    从小说或短故事里拆出角色表、人物画像、形象提示词、音色提示词, 其中形象提示词含一张角色设定图的完整版面指令(左半身像 + 右全身三视图 + 细节条), 产出 JSON + Markdown + 可交互的 report.html。

    4.3k GitHub stars~1.6k tokensUpdated yesterday
    Auto-check: notes
  • Character Refs

    eternityspring/shuohao-skills

    给任何故事里的角色真出参考图(小说改编、自己原创的故事、单独设计一个角色都行,不需要小说原文): 一段话描述角色,拆成分层字段、补全后确认, 先出一张正面全身锚点,其余视图(大头照、90° 侧面、背面、细节、45° 大头照)都只参考这张锚点, 按需分档出图。每张图带标识、可单独重出,重出后自动标出哪些图过期。

    4.3k GitHub stars~1.7k tokensUpdated yesterday
    Auto-check: warnings
  • Novel Script

    eternityspring/shuohao-skills

    给 AI 短剧写剧本:把 novel-outline 的分集梗概落成结构化的场次 + 节拍流(动作节拍与台词行交替), 台词逐句带说话人与语气,时长逐集按语速确定性折算。产出 script.json + Markdown + 单页评审报告 (时长仪表 / 分集剧本 / 场次总表 / 按角色聚合的台词本,含导出 JSON)。

    4.3k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check: notes
  • Novel Storyboard

    eternityspring/shuohao-skills

    给 AI 短剧出分镜:三层结构——段(一次视频生成,≤15 秒)→ 分镜(段内 2–5 秒的剪切,认领剧本节拍) → 分镜图(每切一张关键帧:主分镜图钉 0.00 秒,子分镜图钉各自切点)。

    4.3k GitHub stars~1.8k tokensUpdated yesterday
    Auto-check: notes

Questions about Novel Outline

What does Novel Outline do?

把一本小说改编成短剧大纲五件套:改编说明、人物表、爽点表、分集梗概、资产清单, 产出 outline.json + Markdown + 单页评审报告(KPI 带、关键决策、爽点时间轴、调度矩阵、场景概览、质量门)。. Novel Outline is an agent skill from eternityspring/shuohao-skills.

When should I use Novel Outline?

Novel Outline fits situations like: asked to 改编大纲、短剧大纲、拆大纲、小说转短剧、adaptation outline; tasks that involve Creative writing and fiction; tasks that involve OKRs and executive reporting.

How do I install Novel Outline in Claude Code?

Run `npx skills add eternityspring/shuohao-skills --skill novel-outline -a claude-code`. Or copy the skill folder (skills/novel-outline in eternityspring/shuohao-skills) into .claude/skills/novel-outline in your project. Claude Code loads it when a task matches its description.

How do I install Novel Outline in Codex?

Run `npx skills add eternityspring/shuohao-skills --skill novel-outline -a codex`. Or copy the skill folder (skills/novel-outline in eternityspring/shuohao-skills) into .agents/skills/novel-outline in your project. Codex loads it when a task matches its description.

Can I use Novel Outline in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add eternityspring/shuohao-skills --skill novel-outline -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/novel-outline, .gemini/skills/novel-outline, .github/skills/novel-outline and .opencode/skills/novel-outline in your project.

What does Novel Outline need to run?

Going by SKILL.md and its folder, Novel Outline needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read, Write, Bash, Task, Glob.

Does Novel Outline access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Novel Outline safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Novel Outline use?

Novel Outline is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Novel Outline use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.8k tokens, read only when the agent opens those files.

What are the alternatives to Novel Outline?

Skills that share tags, products or a category with Novel Outline: Reading Guide (chingswy/Skill-Research-Figure, 179 stars), Exec Summary (mvschwarz/openrig, 6.6k stars), Weekly Ops Report (davila7/claude-code-templates, 33k stars) and Product Marketing Context (minhnv0807/ai-business-skills, 609 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Novel Outline?

eternityspring (a GitHub user) maintains it in eternityspring/shuohao-skills, which has 4,324 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 8, 2026.

Source: eternityspring/shuohao-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.