cw-brainstorming by haowjy/creative-writing-skills
npx skills add https://github.com/haowjy/creative-writing-skills --skill cw-brainstorming以工作笔记的形式记录故事头脑风暴,保留创作自由。
记录头脑风暴时避免:
AI 建议很有价值,但必须清晰标记并保持简洁。
此技能处理所有类型的头脑风暴:
所有类型都遵循核心原则(最小化记录、来源标记、保留模糊性)。请参阅 references/ 目录下的专门指南:
chapter-planning.md - 记录节拍和场景探索worldbuilding.md - 探索虚构世界元素(使用网络搜索进行研究)character-development.md - 探索动机、弧光、关系continuity-timeline.md - 时间线跟踪和矛盾处理广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
仅记录用户明确陈述的内容。不要添加阐述、用户未给出的例子或填补空白的细节。
问题在于混淆,而非建议:
❌ 用户:"角色 A 与 B 竞争" → 记录:"A 和 B 通过一场包含三轮的锦标赛争夺领导权..." ✅ 用户:"角色 A 与 B 竞争" → 记录:"A 和 B 竞争" + 可选:"锦标赛形式?政治手段?审判形式?"
默认:未标记 = 用户所说。 大多数想法来自用户,因此将其视为默认来源。
仅在特殊语境下使用标签:
<AI>...</AI> - AI 建议/可能性(必须清晰包裹)
<AI>竞争形式可能是:锦标赛式、政治操纵或审判式</AI><hidden>...</hidden> - 仅作者知晓、计划稍后揭示的信息
<hidden>Z 秘密地希望他们都失败,以便他能重新夺回领导权</hidden>何时提供 AI 建议:
何时保持最小化:
如果用户表述模糊,就保持模糊:
工作笔记可以包含矛盾和多种可能性。不要解决它们——只需列出正在考虑的选项。
使用适合讨论的任何结构。 可以是:
基本要素:
<AI> 标签中<hidden> 标签中基于讨论的可选章节:
"我在想角色 X 和角色 Y 竞争领导权。也许这会给曾是前领导者的角色 Z 带来紧张关系。"
# 领导权竞争笔记
- X 和 Y 竞争领导权
- Z 曾是前领导者
- 可能给 Z 带来紧张关系(不确定)
开放性问题:
- 竞争形式?
- Z 如何回应?
- 结果如何?
# 领导权竞争故事线
X 和 Y 在 Z 退位后竞争领导权。Z 感到自己的权威受到挑战而受到威胁。
竞争分三个阶段展开:
1. 宣布和初步定位
2. 第一次挑战,X 展示力量
3. 第二次挑战,Y 展示智慧
...
[20 多个编造的节拍]
为何不良? 添加了大量用户从未陈述的阐述。
# 领导权竞争笔记
- X 和 Y 竞争领导权
- Z 曾是前领导者
- 可能给 Z 带来紧张关系(不确定)
开放性问题:
- 竞争形式:<AI>锦标赛式?政治操纵?审判式?</AI>
- Z 的回应:<AI>反对双方?支持一方?保持中立?</AI>
- 如何解决?
# 领导权竞争笔记
- X 和 Y 竞争领导权
- Z 曾是前领导者
- 可能给 Z 带来紧张关系(不确定)
- <hidden>Z 秘密操纵 X 和 Y 互相摧毁,计划在他们都名誉扫地后重新掌权</hidden>
开放性问题:
- 竞争形式?
- 结果如何?
为何使用 <hidden>? 操纵转折计划稍后揭示。读者/角色尚不知晓,但作者在头脑风暴时需要追踪它。
如果你在写以下内容,请停止:
将 AI 建议包裹在 <AI> 标签中,保持简洁(2-3 个选项)。
良好: 用户说:"对,我就是这么说的" 不良: 用户说:"我从没说过那些"
笔记应该感觉像骨架且不完整。这正是要点——保留创作自由。
不要只是写笔记然后停止。记录之后,与用户互动以帮助发展想法:
有用的后续问题:
保持对话性:
目标: 帮助用户思考他们的想法,而不是接管创作过程。
在有用时,可以自由与其他技能结合使用(例如,使用 cw-official-docs 来记录最终确定的世界观构建,或使用 cw-story-critique 来分析你正在头脑风暴的内容)。
brainstorm-[主题].md每周安装数
105
仓库
GitHub 星标数
90
首次出现
2026年1月28日
安全审计
安装于
opencode99
gemini-cli98
codex97
cursor94
github-copilot93
kimi-cli92
Capture story brainstorming in working note format that preserves creative freedom.
Record brainstorming WITHOUT:
AI suggestions are valuable but must be clearly marked and kept minimal.
This skill handles all brainstorming types:
All share core principles (minimal capture, source tagging, preserve vagueness). See references/ for specialized guidance:
chapter-planning.md - Capturing beat and scene explorationworldbuilding.md - Exploring fictional world elements (use web search for research)character-development.md - Exploring motivations, arcs, relationshipscontinuity-timeline.md - Timeline tracking and contradiction handlingRecord ONLY what the user explicitly states. Do NOT add elaborations, examples they didn't give, or details to fill gaps.
The problem is mixing, not suggesting:
❌ User: "Character A competes with B" → Capture: "A and B compete for leadership through a tournament with three rounds..." ✅ User: "Character A competes with B" → Capture: "A and B compete" + optional: "Tournament? Political? Trial?"
Default: Untagged = user said it. Most ideas come from the user, so treat them as the default.
ONLY use tags for special context:
<AI>...</AI> - AI suggestions/possibilities (MUST be clearly wrapped)
<AI>Competition could be: tournament-style, political maneuvering, or trial-based</AI><hidden>...</hidden> - Author-only information meant to be revealed later
<hidden>Z secretly wants them both to fail so he can reclaim leadership</hidden>When to offer AI suggestions:
When to stay minimal:
Keep it vague if user leaves it vague:
Working notes can contain contradictions and multiple possibilities. Don't resolve them - just list the options being considered.
Use whatever structure fits the discussion. Could be:
Essential elements:
<AI> tags<hidden> tags when relevantOptional sections based on discussion:
"I'm thinking character X and character Y compete for leadership. Maybe this creates tension with character Z who was the previous leader."
# Leadership Competition Notes
- X and Y compete for leadership
- Z was previous leader
- May create tension with Z (uncertain)
Open questions:
- Form of competition?
- How does Z respond?
- Outcome?
# Leadership Competition Arc
X and Y compete for leadership after Z steps down. Z feels threatened by the challenge to his authority.
The competition unfolds in three stages:
1. Announcement and initial positioning
2. First challenge where X demonstrates strength
3. Second challenge where Y shows wisdom
...
[20 more invented beats]
Why bad? Added massive elaboration the user never stated.
# Leadership Competition Notes
- X and Y compete for leadership
- Z was previous leader
- May create tension with Z (uncertain)
Open questions:
- Competition format: <AI>tournament-style? political maneuvering? trial-based?</AI>
- Z's response: <AI>oppose both? support one? stay neutral?</AI>
- Resolution?
# Leadership Competition Notes
- X and Y compete for leadership
- Z was previous leader
- May create tension with Z (uncertain)
- <hidden>Z is secretly manipulating both X and Y to destroy each other, planning to reclaim power after they're both discredited</hidden>
Open questions:
- Competition format?
- Outcome?
Why use<hidden>? The manipulation twist is planned for later reveal. Readers/characters don't know yet, but the author needs to track it while brainstorming.
Stop if you're writing:
Wrap AI suggestions in <AI> tags, keep minimal (2-3 options).
Good: User says "Yes, that's what I said" Bad: User says "I never said all that"
Notes should feel skeletal and incomplete. That's the point - preserves creative freedom.
DON'T just write notes and stop. After capturing, engage with the user to help develop ideas:
Useful follow-ups:
Keep it conversational:
The goal: Help the user think through their ideas, not take over the creative process.
Feel free to combine with other skills when helpful (e.g., using cw-official-docs to document finalized worldbuilding, or cw-story-critique to analyze what you're brainstorming).
brainstorm-[topic].mdWeekly Installs
105
Repository
GitHub Stars
90
First Seen
Jan 28, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
opencode99
gemini-cli98
codex97
cursor94
github-copilot93
kimi-cli92
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
49,000 周安装
GitHub Copilot 代码迁移指令生成器 | 自动分析代码演进与生成转换规则
7,700 周安装
Fabric Lakehouse 使用指南:核心概念、性能优化与数据管理实践
7,700 周安装
EditorConfig 专家 - 自动生成最佳实践配置文件,统一团队代码风格
7,700 周安装
BigQuery流水线审计:成本控制、安全与生产就绪度检查指南
7,700 周安装
AI生成应用商店截图与预览视频工具 - 符合Apple/Google规范,提升应用曝光
7,700 周安装
Google Workspace CLI 研究员角色:高效组织研究、管理参考文献与协作
7,800 周安装