Serialized Chinese novel creation with genre variety, 10-50 chapter support, and AI-free polishing.
Works with
Guides users through a structured 5-question intake (genre, protagonist, personality, core conflict, chapter count) before generating detailed outlines and character profiles
Produces 3,000-5,000 word chapters with immediate hooks in the opening 20% and cliffhanger endings designed to sustain reader engagement across serialized releases
Includes deep refinement workflows to eliminate A
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionchinese-novelistExecute the skills CLI command in your project's root directory to begin installation:
Fetches chinese-novelist from penglonghuang/chinese-novelist-skill and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate chinese-novelist. Access via /chinese-novelist in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
955
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
955
stars
使用 AskUserQuestion 工具逐一询问用户,每个问题提供选项供用户选择。
问题1:题材与风格
Question: 你想要创作什么题材的小说?
Options:
- 悬疑推理(侦探、破案、解谜)
- 现代言情(都市、职场、恋爱)
- 古代言情(宫廷、江湖、穿越)
- 奇幻玄幻(魔法、异世界、修真)
- 科幻未来(科技、太空、末世)
- 武侠仙侠(江湖、门派、飞升)
- 历史架空(朝堂、战争、权谋)
- 都市现实(生活、成长、社会)
用户选择后记录:题材 = [用户选择]
问题2:主角设定
Question: 主角是什么设定?
Options:
- 男性主角(独角戏)
- 女性主角(独角戏)
- 双主角(男女双线)
- 群像戏(多线叙事)
用户选择后,如需进一步询问职业/身份,继续追问。
记录:主角 = [用户选择] + 职业/身份 = [用户回答]
问题3:主角性格
Question: 主角的核心性格是?
Options:
- 热血正义(积极、勇敢、有担当)
- 冷静智慧(理性、谋略、高智商)
- 温暖治愈(善良、温柔、有同理心)
- 高冷孤傲(冷漠、独立、强大)
- 阴暗腹黑(心机、算计、复仇)
- 成长逆袭(从弱到强、打脸升级)
记录:性格 = [用户选择]
问题4:核心冲突
Question: 小说的核心冲突是什么?
Options:
- 生死存亡(生存危机、逃出生天)
- 查明真相(寻找答案、揭露秘密)
- 爱情阻碍(追求真爱、克服阻碍)
- 复仇雪恨(复仇计划、伸张正义)
- 权力争夺(竞争上位、资源争夺)
- 成长突破(自我突破、实现价值)
- 守护保护(守护重要的人或事)
记录:核心冲突 = [用户选择]
问题5:章节数量
Question: 你计划创作多少章?
Options:
- 10章(短篇,约3-5万字)
- 15章(中短篇,约4.5-7.5万字)
- 20章(中篇,约6-10万字)
- 30章(中长篇,约9-15万字)
- 50章(长篇,约15-25万字)
- 自定义(输入具体章节数)
记录:章节数 = [用户选择]
5问收集完成后然后进入"第二阶段:规划"。
执行以下步骤:
novels/[小说名称]/00-大纲.md,使用 references/outline-template.md 模板,填入完整的章节规划01-人物档案.md,使用 references/character-template.md 模板,创建主角、反派、配角档案完成后,向用户展示规划摘要并请求确认,等待用户确认。用户同意后,进入"第三阶段:疯狂创作"。
重要:全程无需再次向用户确认,必须逐一章创作
按顺序逐章创作,每章执行完整的创作流程(见下方"逐章创作"),完成一章后自动继续下一章,直到所有章节完成。
每章创作时严格执行以下步骤:
00-大纲.md - 查看TODO list和已完成章节的摘要00-大纲.md 中上一章的摘要00-大纲.md 中 TODO list - 将本章标记为"进行中"references/chapter-template.md 模板python scripts/check_chapter_wordcount.py <章节文件路径> 低于3000字必须使用扩充技巧重写python scripts/check_chapter_wordcount.py <章节文件路径> 低于3000字必须使用扩充技巧重写00-大纲.md 添加摘要(300-500字)00-大纲.md 中 TODO list - 将本章标记为"完成"使用 scripts/check_chapter_wordcount.py 检查章节字数:
# 检查单个章节
python scripts/check_chapter_wordcount.py novels/小说名/第01章.md
# 检查所有章节
python scripts/check_chapter_wordcount.py --all novels/小说名/
# 自定义最小字数
python scripts/check_chapter_wordcount.py novels/小说名/第01章.md 3500
低于3000字的章节必须使用 content-expansion.md 的扩充技巧进行扩充。
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
chinese-novelist is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
I recommend chinese-novelist for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Keeps context tight: chinese-novelist is the kind of skill you can hand to a new teammate without a long onboarding doc.
Useful defaults in chinese-novelist — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Solid pick for teams standardizing on skills: chinese-novelist is focused, and the summary matches what you get after install.
Registry listing for chinese-novelist matched our evaluation — installs cleanly and behaves as described in the markdown.
chinese-novelist fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
chinese-novelist reduced setup friction for our internal harness; good balance of opinion and flexibility.
Keeps context tight: chinese-novelist is the kind of skill you can hand to a new teammate without a long onboarding doc.
chinese-novelist is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
showing 1-10 of 55