Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ZJU-REAL/Easel --skill novel-writergit clone --depth 1 https://github.com/ZJU-REAL/EaselWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zju-real/easel/novel-writer)<a href="https://agentmods.dev/skills/zju-real/easel/novel-writer"><img src="https://agentmods.dev/badge/skills/zju-real/easel/novel-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zju-real/easel/novel-writer"><img src="https://agentmods.dev/badge/skills/zju-real/easel/novel-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00111 | $0.02223 |
| Opus 5 | $0.00056 | $0.01111 |
| Sonnet 5 | $0.00022 | $0.00445 |
| Haiku 4.5 | $0.00011 | $0.00222 |
Grade A, and why
novel-writer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 小说 / 网文连载创作
一句灵感 → 世界观/人设 → 三级大纲 → 逐章正文。核心是长篇一致性： 用「文件即真相 + 按需加载」——AI 不靠上下文记忆，每写一章只加载相关切片， 状态全落文件、可 diff、可续写。确定性 IO（搭骨架/进度/机械查 AI 味）走
scripts/novel_ops.py，创意（设定/大纲/正文）由你 LLM 完成。
只做单段风格改写见 style-transfer；只做润色去 AI 感见 text-polisher； 只做通用文章见 social-content；发知乎见 skill-zhihu-publisher。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 灵感/题材 | 是 | 一句话创意，或已有设定（没给就问） |
| 平台 | 否 | 知乎盐选 / 番茄 / 起点 / 小红书图文（默认按 Profile 或问） |
| 书名 | 否 | 缺省由题材拟定，用作产物目录名 |
| 本次动作 | 否 | 立项 / 出大纲 / 写第 N 章 / 续写 / 改图文（默认按对话判断） |
产物结构（outputs/书名/）
bible/ world.md characters.md voice.md canon.md ← 硬事实（写每章必读）
outline/ overview.md volumes.md chapters.md ← 三级大纲
state/ summary.md character-state.md plot-arcs.md progress.json/md ← 连载状态
chapters/ 001.md 002.md ... ← 章节正文
脚本路径（相对项目根）：skills/openclaw/novel-writer/scripts/novel_ops.py。
字数校验复用：skills/shared/scripts/wordcount.py。
执行步骤（按对话选对应子流程，不必每次全跑）
A. 立项（首次）
- 搭骨架：
python skills/openclaw/novel-writer/scripts/novel_ops.py scaffold --book "<书名>"（生成 bible/outline/state/chapters 模板，已存在的文件不覆盖）。 - 定世界观 + 人设 + 文风：读
references/web-novel-methodology.md与references/platform-specs.md， 据题材写满bible/world.md（力量体系/规则/硬约束）、bible/characters.md（主角+关键配角：身份/外貌/性格/目标/关系）、bible/voice.md（视角/时态/句式节奏/用词偏好 + 本书禁用词表）。设定要可执行（能约束后续正文），不写空话。
B. 大纲（三级）
- overview → volumes → chapters：写
outline/overview.md（一句话卖点+核心冲突+主线+结局向）、outline/volumes.md（分卷 arc：每卷目标/转折/卷末高潮）、outline/chapters.md（章节目录表：标题+一句话钩子+涉及伏笔）。 大纲底座可参考skill-article-outline，但必须扩成网文三级结构 + 伏笔埋点表（登记进bible/canon.md）。
C. 黄金三章（前 3 章单独强化）
- 按
references/web-novel-methodology.md的黄金三章模板，把前三章的开局钩子、爽点、代入感、追读悬念拉满 （第 1 章 3 秒内给冲突/金手指信号；每章末留强钩子）。这三章决定留存，值得单独打磨。
D. 写单章（连载主循环）
- 只加载相关切片（不塞全书）：读
bible/（全部，是硬约束）+outline/chapters.md里本章那行 +state/summary.md（前情提要）+state/character-state.md里相关角色。 - （可选）先出场景卡：复杂章节按
references/scene-card-schema.md先列场景卡（角色/地点/冲突/story value 涨落/情绪/出口）再写正文。 - 写正文到
chapters/<三位数>.md：遵守bible/voice.md文风、章末强钩子。 - 字数门禁：把正文喂
python3 skills/shared/scripts/wordcount.py check --target <平台目标字数> --tolerance 0.15 -f chapters/<NNN>.md（知乎盐选/番茄单章常 2000–4000，见 platform-specs），不达标按提示增删。 - 去 AI 味：先跑
python skills/openclaw/novel-writer/scripts/novel_ops.py slopcheck -f chapters/<NNN>.md机械扫（AI 味词/过度连接词/重复句首），命中处改写；再整章过一遍 text-polisher（去 AI 感模式）。
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 111 lines · 111 tokens per session scan A 6f90221fd90d
novel-writer is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 111 tokens to every session and 2,223 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
roadtrip-navigator
Generate North American road-trip itineraries as a map-first, offline-friendly single-file HTML page. Plans around daily driving segments, overnight stops, fuel/EV-charging, national-park reservations (Recreation.gov / NPS), seasonal road closures, and timezone/border crossings — for executable, decision-ready trips.…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.