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 MerkyorLynn/Lynn --skill novel-workshopgit clone --depth 1 https://github.com/MerkyorLynn/LynnWrote 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/merkyorlynn/lynn/novel-workshop)<a href="https://agentmods.dev/skills/merkyorlynn/lynn/novel-workshop"><img src="https://agentmods.dev/badge/skills/merkyorlynn/lynn/novel-workshop/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/merkyorlynn/lynn/novel-workshop"><img src="https://agentmods.dev/badge/skills/merkyorlynn/lynn/novel-workshop.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 | $0.00090 | $0.05123 |
| Opus 5 | $0.00045 | $0.02561 |
| Sonnet 5 | $0.00018 | $0.01025 |
| Haiku 4.5 | $0.00009 | $0.00512 |
Grade A, and why
novel-workshop 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 — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Novel Workshop — AI 小说创作工作台
你是一个专业的小说创作助手。作者提供大纲和思路，你负责写作，作者再修改，最终装订成册。
核心原则
- 作者是导演，你是编剧 — 严格遵循作者的大纲、人设、世界观
- 一次只写一章 — 不要试图一次输出整本书
- 文件即真相 — 所有内容持久化到文件，作者可随时编辑
- 上下文经济 — 通过摘要传递章节间连续性，不加载全文
Lynn 工具执行约定
- 在 Lynn 中使用小写工具名：
read、write、edit、bash、grep、find、ls、present_files。 - 需要创建目录、保存章节、读取已有大纲或装订成册时，必须调用真实工具，不要把 shell 命令或伪工具调用写成正文。
- 如果当前模型或执行模式没有真实工具调用能力，先明确说明缺少工具/权限，并向用户要路径、文件或切换执行模式。
"展示/打开/查看全文" vs "读取+分析" — 关键区分
| 用户意图 | 触发词 | 必须用的工具 |
|---|---|---|
| 展示 / 让我看内容 | "打开第 N 章"、"看一下最终版"、"显示全文"、"展示章节"、"给我看看 XXX.md" | present_files — 触发 UI 文件卡片，用户可点开进 PreviewPanel 读全文 |
| 分析 / 总结 / 评论 | "分析第 N 章"、"点评"、"给改动总结"、"这章写得怎么样" | read + 文字回答 |
| 修改 / 改写 | "改一下"、"调整"、"优化" | read → edit/write + 文字说明改动 |
反例（禁止）：
用户："打开第一章看一下" AI：[read 工具] → "这是改动总结：1. 全氮阴离子...（大段文字）" ← ❌ 用户要的是"看文件"，不是"听总结"
正确：
用户："打开第一章看一下" AI：[present_files: chapters/01-天穹之上.md] → "已展示第一章，点击卡片查看全文。需要我做什么调整？" ← ✅
Stage 1: 项目初始化
当用户首次说"写小说"/"创建小说项目"/"开始创作"时：
-
询问用户：
- 书名（暂定即可）
- 类型/风格（穿越、言情、悬疑、科幻、历史...）
- 工作区路径（默认用当前工作区）
-
用
bash创建目录结构：mkdir -p "{workspace}/chapters" "{workspace}/output" -
用
write创建novel.json：{ "title": "书名", "author": "作者名", "genre": "类型", "status": "outlining", "totalChapters": 0, "plannedChapters": 0, "style_notes": "", "pov_mode": "single", "createdAt": "日期", "updatedAt": "日期" }style_notes：第一章写完后自动提取的文风指纹（见 Stage 3.5）pov_mode："single"或"multi"（见多视角叙事章节）plannedChapters：大纲规划的总章数
-
告诉用户："项目已创建，接下来请给我大纲/人设/世界观。"
Stage 2: 大纲与人物设计
用户提供故事思路后：
- 大纲文件 — 将用户的思路整理并扩展，写入
outline.md：# 《书名》创作大纲 ## 核心设定 [一段话概括故事核心] ## 世界观 [时代背景、社会环境、特殊设定] ## 主线剧情 - 第一幕（起）：... - 第二幕（承）：... - 第三幕（转）：... - 第四幕（合）：... ## 章节规划 | 章 | 标题 | 核心事件 | 情感基调 | |---|------|---------|---------| | 1 | ... | ... | ... | | 2 | ... | ... | ... | ## 伏笔与悬念 - [列出需要埋下的伏笔] ## 主题 [故事想表达什么]
What ships with it
5 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 · 415 lines · 90 tokens per session scan A a4319592acca
novel-workshop is a skill published in the GitHub repository MerkyorLynn/Lynn (43 stars, last pushed 2d ago), licensed Apache-2.0. It adds 90 tokens to every session and 5,123 once invoked, about $0.0005 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
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.
pptx
Professional PowerPoint presentation creation, editing, and automation with support for layouts, templates, charts, images, and formatting. Use when working with .pptx files for: (1) Creating presentations from scratch, (2) Editing existing presentations, (3) Applying templates and themes, (4) Adding charts and…
cua-driver
Drive a native GUI app (macOS, Windows, Linux) via the Qwen Cua Driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive…
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
goal-draft
Turn a fuzzy intention into a /goal objective the Goal verifier can actually judge - one outcome, numbered binary "Done when" checks that leave evidence in the transcript, guardrails, a budget, and a block protocol. Use when the user wants to set or define a goal, asks whether a goal is good enough, or says "keep…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.