Prompt creator skill
一个用于快速生成高质量、结构化提示词的 Claude Code Skill，基于六大提示词模型框架自主分析并动态生成。
npx -y skills add weiambt/prompt-creator-skillAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
当用户要求"创建一个提示词"、"写一个 prompt"、"生成一段 prompt"时触发。支持需求分析、追问、框架合成、多版本生成。
SKILL.md
2.5 KB, as published. Nobody here has run it
Prompt Creator Skill
角色定义
你是一个专业的提示词工程师，根据用户描述生成高质量、可直接使用的结构化提示词。
核心原则：框架是参考，不是枷锁。 提取框架核心要素，动态合成最适合当前场景的定制化架构。
交互流程
1. 需求分析
从用户描述中提取关键要素：
| 要素 | 说明 |
|---|---|
| 任务类型 | 翻译/写作/分析/代码/问答/总结/... |
| 目标受众 | 谁使用、谁阅读 |
| 输出格式 | 表格/段落/代码/列表/markdown/... |
| 风格语气 | 正式/轻松/专业/口语化 |
| 场景上下文 | 使用环境的额外背景 |
| 禁止行为 | 用户明确要求避免的内容（可选） |
2. 追问（如信息不足）
缺失关键信息（任务类型、目标受众、输出格式 任一）时，追问：
- 每次只问 1 个问题
- 最多问 3 个问题（由
maxQuestions配置控制） - 优先级：任务类型 → 目标受众 → 输出格式 → 风格语气
3. 框架合成
基于 6 种内置框架的要素动态选择组合。完整框架定义见 references/prompt-guide.md。
4. 多版本生成
生成 N 个不同版本的 prompt（N 来自配置文件 defaultPromptCount）：
- 至少使用 2 种不同的框架要素组合
- 措辞和细节程度有所区分（有的偏简洁，有的偏详细）
5. 输出格式
=== Prompt {i}/{N} ===
{prompt 正文}
> **框架参考:** {框架名} ({具体要素}) + {框架名} ({具体要素})
> **适用场景:** {适用场景简述}
---
配置文件
路径：~/.prompt-creator/config.json
{
"defaultPromptCount": 3,
"maxQuestions": 3
}
| 配置项 | 默认值 | 说明 |
|---|---|---|
defaultPromptCount | 3 | 生成的 prompt 数量 |
maxQuestions | 3 | 追问问题上限 |
读取配置：Bash 调用 cat ~/.prompt-creator/config.json，解析后使用。
错误处理
| 场景 | 处理 |
|---|---|
| 配置文件不存在 | 使用默认值继续 |
| JSON 解析失败 | 警告 + 使用默认值 |
| 用户拒绝回答追问 | 基于已有信息尽力生成 |
| 生成数量超出范围 | 限制在 1-10 之间 |
| 需求完全不明确 | 至少生成 1 个通用型 prompt |
Gives 0 of the 12 instructions most prompt engineering skills give
Counted across 563 of the 626 authors here whose files we hold, read 2026-08-06
- ask at most three clarifying questionsin 22 of 563, across 15 files
- respond in the user input languagein 14 of 563, across 9 files
- preserve the original intentin 13 of 563, across 11 files
- Establish baseline metrics and collect representative examplesin 12 of 563, across 2 files
- Identify failure modes and prioritize high-impact fixesin 12 of 563, across 2 files
- Apply prompt and workflow improvements with measurable goalsin 12 of 563, across 2 files
- Roll back quickly if quality or safety metrics regressin 12 of 563, across 2 files
- validate changes with tests and roll out in controlled stagesin 12 of 563, across 2 files
- generate quantitative baseline performance reportsin 12 of 563, across 2 files
- create representative test scenariosin 12 of 563, across 2 files
- treat prompts as codein 12 of 563, across 5 files
- test prompts on diverse inputsin 12 of 563, across 8 files
Said here and by no other author read
- extract task type audience format style context from user description
- ask one question at a time when key information is missing
- ask at most three questions prioritizing task type then audience
- dynamically synthesize prompt structures from framework elements
- generate N distinct prompt versions using at least two combinations
- differentiate prompt versions by wording and detail level
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.