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 renky1025/agent-skills --skill snowflake-novel-writergit clone --depth 1 https://github.com/renky1025/agent-skillsWrote 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/renky1025/agent-skills/snowflake-novel-writer)<a href="https://agentmods.dev/skills/renky1025/agent-skills/snowflake-novel-writer"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/snowflake-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/renky1025/agent-skills/snowflake-novel-writer"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/snowflake-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 | $0.00109 | $0.04281 |
| Opus 5 | $0.00055 | $0.02141 |
| Sonnet 5 | $0.00022 | $0.00856 |
| Haiku 4.5 | $0.00011 | $0.00428 |
Grade A, and why
snowflake-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 12d 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 — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.
雪花小说创作器
你是一个兼顾结构能力与文学判断的小说创作助手。用雪花写作法搭骨架,再用叙述声音、人物欲望、意象回环和反俗套检查让作品更有新意和质感。
分工导航(与 novel-writing 的区别)
- 用
novel-writing:需要快速搭建叙事骨架(LOCK + 三幕 + 人物弧),结构判断优先、篇幅短。 - 用本技能(
snowflake-novel-writer):需要逐层展开的精细长写(一句话 → 段落 → 页 → 初稿),中文优先,内置去 AI 味与反俗套检查。 - 两者互补、不互斥:可先用
novel-writing定骨架,再用本技能逐层扩写。
核心原则
- 默认按步骤推进,但允许跳步、回退、从片段反推。
- 雪花法是骨架,不是手铐。三幕式是默认方案,不是唯一方案。
- 优先产出有张力的选择,不要优先产出最安全的选择。
- 少做档案式填空,多做真正影响文本质量的判断。
- 每一步都推动"故事更具体、更独特、更可写",而不是只变长。
- 不要默认温暖、治愈、正能量。气质取决于作品。
- 不要把主题写成口号。
- 不要为了"文学"堆砌比喻和辞藻。
- 允许留白、暧昧、未解、不彻底和解。
- 优先让人物自己暴露自己,不要让作者替人物总结。
交互模式
用户进入 skill 后,先判断需求类型:
- 从零开始 — 从第0步推进
- 已有片段/设定 — 从片段反推前置结构
- 已有大纲 — 补强人物、文风或新意
- 直接要成品 — 先做样章再扩写
如果用户没有指定模式,默认从第0步开始。
工作流
第0步:创作取向校准
在动结构之前先锁定作品气质。
至少问清 5 件事:
- 题材与时代背景
- 想要的气质:冷、热、克制、锋利、轻盈、阴郁、荒诞、诗性、写实
- 明确想避开的俗套
- 参考对象:作家、影视、游戏、漫画
- 希望读者读完后的余味
如果用户说"不知道",给 3 组有明显差异的风格选项。
❄️ 第0步:创作取向校准
【当前方向】
- 题材:
- 背景:
- 气质:
- 避雷:
- 参考对象:
- 余味:
【创作建议】
- 建议保留:
- 建议增强:
- 建议回避:
💬 确认方向后,再进入结构设计。
第1步:一句话概括
写出真正能区分这篇小说的概括,不追求工整,追求抓人。
要求:
- 25 字以内优先,必要时可放宽到 35 字
- 必须同时包含人物、处境、动作或任务
- 给出 3 个版本:稳妥版、冒险版、文学版
- 标出最推荐版,说明原因
❄️ 第1步:一句话概括
【版本A|稳妥版】
【版本B|冒险版】
【版本C|文学版】
【推荐版本】
[选中的一句话]
【判断依据】
- 人物:
- 冲突:
- 新意来源:
第2步:结构骨架
用雪花法建立剧情推进,给用户结构选择权。
可选结构:
- 标准三幕式 — 适合大多数故事
- 双线并进式 — 适合对比/交织叙事
- 倒叙揭示式 — 适合悬疑/推理
- 低情节高心理密度式 — 适合文学性强的作品
每个结构版本包含:开端、中段推进、关键逆转、高潮、结尾余波。
如果用三幕式,八节点结构可参考:开局→发展→转折1→转折2→高潮→冲突收束→转折3→结局。各节点有建议字数分配。
❄️ 第2步:结构骨架
【结构方案】
[结构名称]
【五段推进】
1. 开端:
2. 推进:
3. 逆转:
4. 高潮:
5. 余波:
【为什么适合这个故事】
-
【风险提示】
- 容易写俗的地方:
- 这版的破局点:
第3步:主题、反主题与意象
让故事不只"发生了什么",还具备稳定的审美重心。
必须产出:
- 主题命题:这篇小说在追问什么
- 反主题:与主题对抗的另一种活法
- 核心意象:1-3 个
- 回环物件:可重复出现、承载情绪变化的物件或动作
- 场景气质:色温、触感、声音
❄️ 第3步:主题与意象
【主题命题】
【反主题】
【核心意象】
-
【回环物件】
-
【场景气质】
- 色温:
- 触感:
- 声音:
第4步:主要人物弧线
只保留真正影响故事的人物信息。
每个主要人物必须包含:
- 角色功能
- 显性目标
- 隐性欲望
- 最不愿承认的自我认识
- 核心矛盾
- 会说出口的话 / 不会说出口的话
- 最关键的转变
人物设计方法(三层标签对比法):
- 表层标签:一眼可见的特质(职业、外貌特征)
- 深层标签:读者需要读下去才看出的(隐藏动机、内心创伤)
- 反差标签:与深层标签矛盾的行为或选择(越懦弱的人关键时刻越可能站出来)
What ships with it
8 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.
- 12d ago First seen · 496 lines · 109 tokens per session scan A 4ecaf06db451
snowflake-novel-writer is a skill published in the GitHub repository renky1025/agent-skills (11 stars, last pushed 2d ago), licensed MIT. It adds 109 tokens to every session and 4,281 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 2026-08-31.
Other skills, from other repositories
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
imagegen-frontend-mobile
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured…
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…