Agent skill

story-long-write

长篇网文写作。从大纲到正文,辅助长篇网络小说的创作,包括世界观、人物、情节线管理。触发方式:/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。

pitechen592★ · +23/wk · 2 repos on radarProfile →
claude-codeships scriptsMIT
Install
npx skills add worldwonderer/oh-story-claudecode --skill story-long-write --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 76
SKILL.md size: 37 KB
Bundled scripts: yes
Version: 1.0.0
Path: skills/story-long-write/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 5,024
Language: JavaScript
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# story-long-write:长篇网文写作 你是网络小说创作教练。你的任务是帮用户从零开始写一本长篇网络小说,从选题确认到大纲搭建再到正文输出。 --- > 运行环境兼容性:Claude Code / OpenCode / Codex / ZCode / OpenClaw 是内置适配目标;NarraFork、Web AI、自定义 Agent 等能读取项目文件的环境,可按本 skill 执行长篇流程。检查专业 agent 时按 `.claude/agents/{agent}.md` → `.opencode/agents/{agent}.md` → `.codex/agents/{agent}.toml` 查找;找不到、Codex 返回 `unknown agent_type`,或检测到 `.zcode/`(ZCode 3.3.4 不执行项目 custom agents)时,直接 solo/direct 执行并报告 fallback。 ## 核心方法 我们写网文先抓情绪,再用验证过的方法可靠地交付这个情绪,灵感只做素材来源。 1. **先定情绪,再定故事**。每个场景都必须服务于一个明确的情绪目标。说不清交付什么情绪的场景不该存在。 2. **从验证过的模式出发**。先问"什么被验证过有效,我如何重新交付",少从"我想写什么"直接起步。扫榜找方向,拆文找模块,对标找节奏。 3. **用模块组装,不要重新发明**。每个题材都有验证过的剧情模式——反转怎么铺、爽点怎么爆、感情怎么拉扯。找到对的模块,把对标书的具体角色看成功能位(对手/盟友/催化剂),再映射到你的角色。用你自己的素材填充这些功能位。 4. **只加载必需信息**。写每章时只加载"不知道就会写错"的信息。涉及角色的状态、待回收的伏笔、相关设定。其余留在文件系统里。 5. **契约与推进决策走权威参考文件**。涉及读者契约、主角代理权、利益安全、期待债、终局储备(终局底牌/升级台阶)、机构/势力边界和 契约安全 / 需补强 / 契约破坏 风险判定时,先按 `references/reader-contract-and-progression.md` 校准,不在 SKILL.md 内复制长规则。 | 题材 | 核心情绪 | 重点参考 | |------|---------|---------| | 打脸/逆袭 | 爽感释放 | genre-writing-formulas.md | | 身份反转 | 震撼+痛快 | reversal-toolkit.md | | 感情拉扯 | 意难平 | emotional-methods.md | | 悬疑/惊悚 | 紧张+好奇 | hooks-suspense.md | | 日常装逼 | 期待感 | hooks-chapter.md | > **情绪反查题材*

What's inside
Steps it walks through
  1. 核心方法
  2. 写作流程
  3. 裸调用与停靠点(防失控)
  4. Phase 1:确认选题方向
  5. Phase 2:核心设定
  6. Phase 3:大纲搭建
  7. Phase 4:正文写作辅助
  8. Phase 5:质量检查
  9. 流程衔接
  10. 参考资料索引
  11. Phase 1:选题方向
  12. Phase 4:正文写作
  13. 按主题快速定位(横切主题)
  14. 语言
Ships with 24 files
  • references/anti-ai-writing.md
  • references/artifact-protocols.md
  • references/banned-words.md
  • references/character-basics.md
  • references/character-design-methods.md
  • references/character-relations.md
  • references/commercial-core-methods.md
  • references/cross-book-recall.md
  • references/dialogue-mastery.md
  • references/emotional-arc-design.md
  • references/emotional-methods.md
  • references/female-audience-writing.md
  • references/format-and-structure.md
  • references/genre-catalog.md
  • references/genre-core-mechanics.md
  • references/genre-prose-cards.md
  • references/genre-prose-cards/东方仙侠.md
  • references/genre-prose-cards/传统玄幻.md
  • references/genre-prose-cards/历史古代.md
  • references/genre-prose-cards/历史脑洞.md
  • references/genre-prose-cards/双男主.md
  • references/genre-prose-cards/古言脑洞.md
  • references/genre-prose-cards/古风世情.md
  • references/genre-prose-cards/女频悬疑.md
first 24 of 76
More from oh-story-claudecode
All skills →
About this skill
What does the story-long-write skill do?

长篇网文写作。从大纲到正文,辅助长篇网络小说的创作,包括世界观、人物、情节线管理。触发方式:/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。

How do I install it?

Run `npx skills add worldwonderer/oh-story-claudecode --skill story-long-write --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From worldwonderer/oh-story-claudecode, a repository with 5,024 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going