InkOS Creative Harness
Narcooo/inkos
Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.
Routes a Chinese web-novel writing request to the matching tool in a 13-skill toolbox, covers author habit memory, and can launch a local dashboard for browsing a project.
Install Story Toolbox Router
$ npx skills add zenstory-ai/oh-story-claudecode --skill story -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zenstory-ai/oh-story-claudecode story --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/zenstory-ai/oh-story-claudecode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/story .claude/skills/story && rm -rf skills-srcUse ~/.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/
Install the "story" agent skill from https://github.com/zenstory-ai/oh-story-claudecode/tree/main/skills/story into .claude/skills/story/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/zenstory-ai/oh-story-claudecode/tree/main/skills/storyType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add zenstory-ai/oh-story-claudecode --skill story -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zenstory-ai/oh-story-claudecode story --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/oh-story-claudecode.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/story .agents/skills/story && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "story" agent skill from https://github.com/zenstory-ai/oh-story-claudecode/tree/main/skills/story into .agents/skills/story/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zenstory-ai/oh-story-claudecode --skill story -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zenstory-ai/oh-story-claudecode story --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/oh-story-claudecode.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/story .cursor/skills/story && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "story" agent skill from https://github.com/zenstory-ai/oh-story-claudecode/tree/main/skills/story into .cursor/skills/story/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/zenstory-ai/oh-story-claudecode.git --path skills/story--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add zenstory-ai/oh-story-claudecode --skill story -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zenstory-ai/oh-story-claudecode story --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/oh-story-claudecode.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/story .gemini/skills/story && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "story" agent skill from https://github.com/zenstory-ai/oh-story-claudecode/tree/main/skills/story into .gemini/skills/story/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install zenstory-ai/oh-story-claudecode storyInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add zenstory-ai/oh-story-claudecode --skill story -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zenstory-ai/oh-story-claudecode.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/story .github/skills/story && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "story" agent skill from https://github.com/zenstory-ai/oh-story-claudecode/tree/main/skills/story into .github/skills/story/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zenstory-ai/oh-story-claudecode --skill story -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zenstory-ai/oh-story-claudecode story --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/oh-story-claudecode.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/story .opencode/skills/story && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "story" agent skill from https://github.com/zenstory-ai/oh-story-claudecode/tree/main/skills/story into .opencode/skills/story/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
story- GitHub stars
- 7.4k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 450 words
- Files
- 10 (incl. scripts, references, assets)
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- MIT
At a glance
Routes a Chinese web-novel writing request to the matching tool in a 13-skill toolbox, covers author habit memory, and can launch a local dashboard for browsing a project.
- Works in 5 steps: 把当前工作目录作为默认工作区；用户明确给出目录时改用该目录。目录必须存在。 → 从当前已加载的 story skill 目录定位… → 检查 node 可用后，以长运行进程执行 → …
- Starting or continuing work on a long-form Chinese web novel
- SKILL.md covers 路由表, 作者记忆, Dashboard 工作台 and 路由流程, plus 4 more sections
- Runs JavaScript and Python scripts from its folder; calls gh, node and curl; reaches api.github.com
What it does
As the entry point for a set of web-novel writing skills, this skill matches your intent, such as planning a long serial, writing a short story, analyzing a bestseller's opening chapters, scanning ranking charts for a topic, removing AI-sounding phrasing, reviewing a draft for consistency, generating a cover, or importing an existing manuscript, against a routing table and hands off to the matching slash command. When intent is unclear it offers four plain-language starting choices instead of showing the full routing table, and suggests a setup command first if the project has not been initialized.
A separate author-memory system records writing habits and preferences at two levels, workspace-wide and per-book, through a dedicated commit script, and only reports a preference as remembered once that script confirms a receipt. The skill also launches a local dashboard server for browsing a project's analysis library and files, and can check for and apply updates to the toolbox itself.
When your agent uses it
- Starting or continuing work on a long-form Chinese web novel
- Scanning bestseller charts to decide what topic to write
- Recording a personal writing preference so future chapters follow it
- Opening a local dashboard to browse a novel project's files
Example prompts
- “/story dashboard”
- “/story-setup 搭建新书项目环境”
- “/story-import 把我的旧稿导进来”
Requirements
- Node.js, for the bundled dashboard server script
- Python, for the author-memory commit script
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 把当前工作目录作为默认工作区；用户明确给出目录时改用该目录。目录必须存在。
- 从当前已加载的 story skill 目录定位 scripts/dashboard-server.mjs，不要硬编码仓库路径、
- 检查 node 可用后，以长运行进程执行
- 等待输出出现“本机地址”，把完整 URL 回给用户。工具支持后台进程/PTY 时让服务保持运行；
- Dashboard 默认只监听 127.0.0.1。不要主动增加 --allow-network，不要把工作区暴露到
What it can do on your machine
Read from SKILL.md and the folder at commit 2cf7be6. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (JavaScript and Python), which the agent can run.
Shell commands in SKILL.md call:
ghnodecurlnpx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
api.github.com
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
Story Toolbox Router loads about 1.7k tokens when it runs, and up to ~6.9k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 450 words of instructions outside code blocks.
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 passed
The automated check found no risky patterns in SKILL.md.
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 zenstory-ai/oh-story-claudecode at commit 2cf7be6, republished under its MIT licence (© zenstory-ai). 450 words, ~1,690 tokens.
Download SKILL.mdSave it as
.claude/skills/story/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.- name
- story
- description
- 网络小说工具箱主入口。根据用户需求自动路由到对应 skill，并可管理作者习惯、启动本地 Dashboard。触发方式：/story、$story、/story dashboard、/网文、「我想写小说」「记住我的写作习惯」「打开工作台」「检查更新」。
story：网文工具箱路由
你是网文工具箱的路由入口。用户的请求模糊时由你分发到具体 skill。
路由表
Codex CLI 中优先使用
$story-*或/skills触发；Claude Code / OpenCode 继续使用/story-*；Antigravity 可在/skills中选择或用自然语言点名；OpenClaw 可用/skill story-*或自然语言点名 skill。下表以 slash command 展示，Codex 可将/story-long-write等价替换为$story-long-write，OpenClaw 可将其等价替换为/skill story-long-write。
| 用户意图 | 关键词示例 | 路由到 |
|---|---|---|
| 长篇规划/写作 | 讨论长篇结构、规划剧情、开书、写大纲、补细纲、长篇、连载 | /story-long-write |
| 写短篇 | 短篇、盐言、一万字 | /story-short-write |
| 长篇拆文 | 拆文、分析这本书、黄金三章、灵感库、跨书灵感聚合 | /story-long-analyze |
| 短篇拆文 | 拆短篇、分析这个故事 | /story-short-analyze |
| 长篇扫榜 | 长篇排行、什么火、新书在冒什么、起点/番茄/晋江/七猫长篇 | /story-long-scan |
| 选题决策 | 写什么能爆、帮我选题、选题方向 | /story-long-scan |
| 短篇扫榜 | 短篇排行、知乎盐言排行 | /story-short-scan |
| 去 AI 味 | 去 AI 味、太 AI、去味 | /story-deslop |
| 审查稿件 | 审查、审稿、帮我审一下、一致性检查、看看有没有问题 | /story-review |
| 封面 | 封面、封面图 | /story-cover |
| 环境部署 | 准备写书、搭环境、初始化 | /story-setup |
| 浏览器操控 | 浏览器、抓取、登录态 | /browser-cdp |
| 导入小说 | 导入、反向解析、导入小说、把我的书导进来 | /story-import |
| 工作台 | dashboard、工作台、看拆文库、浏览项目文件、打开项目面板 | 见下方「Dashboard 工作台」 |
| 检查/更新版本 | 检查更新、有新版本吗、升级、更新工具箱 | 见下方「版本更新检查」 |
| 切换/列出书目 | 切书、换书、列出我的书、我在写哪几本、切换项目 | 见下方「多书切换」 |
| 管理作者习惯 | 记住我的写作习惯、作者画像、待确认偏好、忘掉这个偏好 | 见下方「作者记忆」 |
| 查故事资料 | 查角色、查伏笔、查进度、查设定、什么状态、写到哪了 | spawn story-explorer agent（结构化 prompt：项目目录：{dir}\n查询类型：{根据意图选择}\n查询参数：{用户查询}）；agent 不可用时见下方「查询降级」 |
| 查资料 | 查资料、帮我查资料、调研、搜索一下、搜一下 | spawn story-researcher agent；agent 不可用时见下方「查询降级」 |
裸调用与新手
只说 /story、看不出意图时，不贴路由表，给四个白话选项：「开一本长篇或接着写」→ /story-long-write；「写一篇短篇」→ /story-short-write；「把一章改得不那么 AI」→ /story-deslop；「更多（拆书、扫榜、导入旧稿、审稿、封面）」→ 再列进阶项。还没部署过（项目根没有 .story-deployed）时先建议 /story-setup。
导入续写顺序
用户问"导入续写先 setup 还是 import"时，直接回答：推荐先 /story-setup，新开/刷新会话后 /story-import，最后 /story-long-write 日更 或 /story-long-write 写第N章。如果用户已经直接触发 /story-import，按 story-import 自带环境检测继续：未 setup 时让用户选择先去 setup 或继续串行导入。
作者记忆
用户要求记住、查看、确认、替换或忘掉作者习惯时，加载 references/author-memory.md，并只用本 skill 的 scripts/author_memory_commit.py 管理两级 .story/作者记忆/：全局、题材、流程条目在工作区（AP），本书条目在书目录（BP，传 --book-root）。常用变更走单事件 record；工具未返回 ok: true 和 Author Memory Receipt 前，不得声称已记住。告诉作者时先用一句人话说记住了什么（如「记住了：这本书的对话一律用「」」），回执放最后一行，写法见协议「回执怎么告诉作者」。显示画像或待确认项是只读操作；不存在时直接说明尚未建立。
新增习惯必须保留用户原话和适用范围。一次性要求只执行不记录；小说事实写入本书设定/追踪；不从反复修改或成稿推断偏好，只记作者明确说的，原话范围含糊才进待确认；与已生效习惯冲突时显式 replace，不原地改写历史。作者说「整理作者记忆」、回执提示习惯攒得太多、工具报单书布局错误，或项目级画像里还有「本书：」条目（建议对该书运行 migrate --book-root）时，再加载 references/author-memory-maintenance.md。用户没有指定工作区时，按协议定位已有作者记忆的最近祖先或当前创作工作区，禁止默认写到用户主目录。
Dashboard 工作台
用户执行 /story dashboard（Codex 为 $story dashboard），或明确说“打开工作台 / 看项目
文件”时，直接启动随本 skill 分发的本地 Dashboard，不再转发到其他 skill：
把当前工作目录作为默认工作区；用户明确给出目录时改用该目录。目录必须存在。
从当前已加载的
storyskill 目录定位scripts/dashboard-server.mjs，不要硬编码仓库路径、 全局 skill 路径或用户主目录。检查
node可用后，以长运行进程执行：bash node "<story-skill-dir>/scripts/dashboard-server.mjs" --root "<workspace>" --open等待输出出现“本机地址”，把完整 URL 回给用户。工具支持后台进程/PTY 时让服务保持运行； 无法自动拉起浏览器不算失败，仍返回可点击 URL。
Dashboard 默认只监听
127.0.0.1。不要主动增加--allow-network，不要把工作区暴露到 局域网或公网。
工作台会识别标准 拆文库/{书名}/，兼容存量 拆文库-{书名}/。写作项目识别同时支持：
- 长篇目录结构：目录内含
正文/、大纲/、设定/或追踪/任一普通子目录。 - 短篇单文件结构：目录内含普通文件
正文.md，并同时含小节大纲.md或设定.md。
符号链接不作为项目标记，只有单个 正文.md 的普通资料目录也不会被误认。浏览器可编辑
.md、.txt、.json、.yaml、.yml、.toml，保存或确认删除前用修改时间防止
误操作外部更新。
停止服务时终止对应的 Node 长运行进程即可。若用户只问用法，不要替他启动；给出
/story dashboard / $story dashboard 两种平台对应入口。
路由流程
- 分析用户请求，提取意图关键词
- 匹配上表，找到对应的 skill
- 如果能明确匹配，直接调用对应 skill（Claude/OpenCode 可用
Skill("skill-name")或 slash command；Codex 用$skill-name//skills；Antigravity 用/skills或自然语言点名；OpenClaw 用/skill skill-name或自然语言点名） - 如果无法匹配，询问用户想做什么（从上表中选择）
- 如果用户说"我想写小说"但未指定长篇/短篇，询问篇幅类型后再路由
Show full SKILL.md (197 more words)Show less
查询降级
Spawn 版本提示（不阻断 spawn）：先读取项目根
.story-deployed的agents_version。与本版agents_version: 34不一致时（标记缺失、字段缺失/非整数、小于或大于 34）照常按文件存在性检查并 spawn，但只检查当前运行时的 canonical 目录；同时报告Notice: agents bundle 版本不匹配（项目 {N}，本版 34）并提示重新运行/story-setup后新开会话；大于 34 时额外提示先更新 oh-story-claudecode，不要用本地旧版 setup 降级覆盖。只有 agent 文件缺失、或运行时不暴露 custom agent 时才降级 solo/direct，报告Fallback: ... -> solo。
「查故事资料」「查资料」走 agent 前先做轻量可用性检查（路由只做这一层，不承担全局部署策略）：当前不在子代理上下文、当前运行时的 Agent/Task 或 invoke_subagent 工具可用，且对应部署文件存在（Claude .claude/agents/*.md、OpenCode .opencode/agents/*.md、Codex .codex/agents/*.toml、Antigravity .agents/agents/agent-name/agent.md，其中 agent-name 为目标 agent 名）→ 可尝试 spawn。Antigravity 用 invoke_subagent + 同名 TypeName，不得因其他端文件存在而误判。任一不满足，或运行时返回 unknown agent / 未暴露 custom-agent registry，则降级，不硬失败：
story-explorer不可用 → 主会话直接用 Read/Grep 从项目文件检索（角色状态/伏笔/进度/设定），回答前说一句「查资料助手没启用，这次我直接翻项目文件」；项目尚未部署时提示先/story-setup（Codex 中用$story-setup）。story-researcher不可用 → 主会话用现有检索/回答能力完成，或提示用户改用/browser-cdp采集，同样用一句白话说明。
回答作者时讲故事里的事（谁、在哪章、发生了什么）；文件字段名、伏笔/事件编号不单独出现，编号必须跟着故事描述。
项目状态感知
路由前先检查当前项目状态：
- 无项目目录（没有包含
追踪/或设定/的书名目录，也没有同时有正文.md与小节大纲.md（或设定.md）的短篇目录）：- 如果用户要写作，下一步是先运行
/story-setup初始化环境（Codex 中用$story-setup） - 如果用户要扫榜/拆文，直接路由
- 如果用户要写作，下一步是先运行
- 已有项目：检查
.story-deployed标记，如未部署则先运行/story-setup（Codex 中用$story-setup）
多书切换
用户想切换或查看在写的书时（一个项目可同时有多本）：
- 在项目根查找所有书目录：包含
追踪/或设定/子目录的目录，或同时有正文.md与小节大纲.md（或设定.md）的目录（含长篇/、短篇/下的子目录）。 - 列出书名，并标出当前
.active-book指向的那本。 - 让用户选择，把所选书的相对路径写入项目根
.active-book（覆盖原内容）。 - 只发现一本时直接确认为活跃书，无需询问。
版本更新检查
用户问"有没有新版本""检查更新""升级"时执行。只通知，更不更新由用户定，不自动安装。
- 当前版本：读本 skill 同目录的
VERSION文件；缺失则视为未知。 - 最新版本：优先
gh release view --json tagName,name,url -R zenstory-ai/oh-story-claudecode取tagName；无 gh 用curl -fsS --max-time 5 https://api.github.com/repos/zenstory-ai/oh-story-claudecode/releases/latest取.tag_name（jq 或 grep）。查不到 → 告知"暂时拉不到最新版本，可手动看 Releases"，不报错。 - 比较：去掉
v前缀按语义版本比（major.minor.patch）。gh release默认取 latest 稳定版，不含 pre-release。 - 告知：
- 已最新 → 「已是最新版 vX.Y.Z」。
- 有新版 → 列出 当前 vA → 最新 vB + Releases/CHANGELOG（能拿到 release notes 就附本次要点），再用 AskUserQuestion 问「现在更新吗？」：
- 选更新 → 跑
npx skills add zenstory-ai/oh-story-claudecode -y -g（-g全局，去掉则只更当前目录）；完成后提示：已部署过的项目在项目根重跑/story-setup（Codex 中用$story-setup）同步 hooks/agents/references，并新开一个会话让 agents 重新注册。 - 选先不 → 不动，告知随时可再来。
- 选更新 → 跑
© zenstory-ai, MIT. 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 9 other files (scripts, references, assets) in skills/story of zenstory-ai/oh-story-claudecode.
- SKILL.md
- VERSION
- assets/app.js
- assets/index.html
- assets/styles.css
- assets/tokens.css
- references/author-memory-maintenance.md
- references/author-memory.md
- scripts/author_memory_commit.py
- scripts/dashboard-server.mjs
Open the folder on GitHubat commit 2cf7be6
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in zenstory-ai/oh-story-claudecode, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Story Toolbox Router 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Story Toolbox Router this skillzenstory-ai/oh-story-claudecode | 7.4k | — | ~1.7k | Automated safety check: Pass | MIT | |
| InkOS Creative HarnessNarcooo/inkos | 10k | 1 repos | ~1.1k | Automated safety check: Pass | AGPL-3.0 | |
| Novel Arteternityspring/shuohao-skills | 4.3k | — | ~1.1k | Automated safety check: Notes | Apache-2.0 | |
| SepiaNanako0129/sepia | 3.1k | — | ~3.6k | Automated safety check: Pass | MIT | |
| Novel Characterseternityspring/shuohao-skills | 4.3k | — | ~1.6k | Automated safety check: Notes | Apache-2.0 | |
| Webnovel WritingTomsawyerhu/Chinese-WebNovel-Skill | 851 | — | ~1.4k | Automated safety check: Pass | None |
Similar 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。
Sepia
Nanako0129/sepia
Make AI-generated writing read as human-written, in fiction and in professional prose.
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。
Webnovel Writing
Tomsawyerhu/Chinese-WebNovel-Skill
用于根据一段中文小说简介，规划、起稿、续写、改写中文网文。重点覆盖选材、构思、分卷、章纲、开头、节奏、章末、模仿检索、去 AI 味。
Qiaomu Novel Generator
joeseesun/qiaomu-novel-generator
Generate original, complete, highly gripping Chinese short fiction from a story theme, character setup, synopsis, trope, classic-plot inspiration, or draft excerpt.
More from zenstory-ai/oh-story-claudecode
All 13 skills in this repoChrome CDP Browser Control
zenstory-ai/oh-story-claudecode
Drives a Chrome window over the DevTools Protocol with the agent-browser CLI, so the agent can reuse your logged-in sessions, read pages and pull tokens.
Story Multi-Perspective Review
zenstory-ai/oh-story-claudecode
Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.
Short Web Fiction Trend Scan
zenstory-ai/oh-story-claudecode
Scans popular short web-fiction rankings on Chinese platforms such as Dianzhong and Heiyan to surface trending emotional hooks, themes and topic candidates with an expiry warning.
Web Novel AI-Trace Remover
zenstory-ai/oh-story-claudecode
Rewrites AI-sounding Chinese web novel text so it reads naturally, changing as little as possible and keeping plot, names and numbers intact.
Novel Import and Project Rebuild
zenstory-ai/oh-story-claudecode
Reverse-imports an existing novel, half-finished or complete, into the standard project structure so story-long-write or story-short-write can continue it.
Long-Form Web Novel Deconstruction
zenstory-ai/oh-story-claudecode
Breaks down a long Chinese web novel chapter by chapter into plot, rhythm, characters, and style, through a resumable staged analysis.
Related
Categories
Questions about Story Toolbox Router
What does Story Toolbox Router do?
Routes a Chinese web-novel writing request to the matching tool in a 13-skill toolbox, covers author habit memory, and can launch a local dashboard for browsing a project. As the entry point for a set of web-novel writing skills, this skill matches your intent, such as planning a long serial, writing a short story, analyzing a bestseller's opening chapters, scanning ranking charts for a topic, removing AI-sounding phrasing, reviewing a draft for consistency, generating a cover, or importing an existing manuscript, against a routing table and hands off to the matching slash command. When intent is unclear it offers four plain-language starting choices instead of showing the full routing table, and suggests a setup command first if the project has not been initialized.
When should I use Story Toolbox Router?
Story Toolbox Router fits situations like: starting or continuing work on a long-form Chinese web novel; scanning bestseller charts to decide what topic to write; recording a personal writing preference so future chapters follow it; opening a local dashboard to browse a novel project's files.
How do I install Story Toolbox Router in Claude Code?
Run `npx skills add zenstory-ai/oh-story-claudecode --skill story -a claude-code`. Or copy the skill folder (skills/story in zenstory-ai/oh-story-claudecode) into .claude/skills/story in your project. Claude Code loads it when a task matches its description.
How do I install Story Toolbox Router in Codex?
Run `npx skills add zenstory-ai/oh-story-claudecode --skill story -a codex`. Or copy the skill folder (skills/story in zenstory-ai/oh-story-claudecode) into .agents/skills/story in your project. Codex loads it when a task matches its description.
Can I use Story Toolbox Router 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 zenstory-ai/oh-story-claudecode --skill story -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/story, .gemini/skills/story, .github/skills/story and .opencode/skills/story in your project.
What does Story Toolbox Router need to run?
Going by SKILL.md and its folder, Story Toolbox Router needs JavaScript and Python for the scripts in its folder and the command-line tools its instructions call (gh, node, curl and npx). Our summary lists: Node.js, for the bundled dashboard server script; Python, for the author-memory commit script.
Does Story Toolbox Router access the network?
SKILL.md names 1 domain. In commands or code: api.github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Story Toolbox Router safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. 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 Story Toolbox Router use?
Story Toolbox Router is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Story Toolbox Router use?
About 1.7k tokens (SKILL.md is roughly 6.8k 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 5.2k tokens, read only when the agent opens those files.
What are the alternatives to Story Toolbox Router?
Skills that share tags, products or a category with Story Toolbox Router: InkOS Creative Harness (Narcooo/inkos, 10k stars), Novel Art (eternityspring/shuohao-skills, 4.3k stars), Sepia (Nanako0129/sepia, 3.1k stars) and Novel Characters (eternityspring/shuohao-skills, 4.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Story Toolbox Router?
zenstory-ai (a GitHub organization) maintains it in zenstory-ai/oh-story-claudecode, which has 7,424 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 10, 2026.
Source: zenstory-ai/oh-story-claudecode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.