Golden quote miner
搞钱学姐团队播客工作流:大纲、逐字稿剪辑、标题、宣发、ShowNote 与视觉风格 Skills
npx -y skills add carpo9984/GQXJ --skill golden-quote-minerAssembled 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.
- 0 stars0 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
从播客逐字稿、文章、演讲稿等文本中提取最具传播力和启发性的金句。触发条件:用户提到"金句"、"挖掘金句"、"找金句"、"提取金句"、"quote mining"、"golden quotes",或在播客/内容制作流程中需要精选引用语句时。
SKILL.md
3.7 KB, ~1.4k tokens by cl100k_base, as published. Nobody here has run it
金句挖掘
从用户提供的文本中精准识别并提取最富有启发性、总结性和传播力的"金句"。所有提取必须 100% 忠于原文。
第一步:获取源文本
- 飞书链接 → 优先使用当前 AI 已连接的飞书工具读取;如果没有飞书权限,请用户导出文件、上传逐字稿或直接粘贴正文
- 直接粘贴 → 接收用户粘贴的文本
- 本地文件 → Read 读取
第二步:金句筛选标准
按以下四个维度严格判断一句话是否为金句:
- 观点精辟:一针见血地指出问题本质,引发深度思考
- 高度概括:用简短话语总结复杂概念或核心思想
- 表达独特:语言生动、比喻恰当,具有记忆点和传播潜力
- 情感共鸣:能触动人心,引发强烈情感共鸣
严格筛选规则:
- 每条金句必须至少同时满足两条及以上标准,宁缺毋滥
- 只满足一条的句子直接淘汰,不要因为"还不错"就降低门槛
- 如果某位说话人确实没有合格金句,可以缺位,不要强行凑数
第三步:提取金句
最重要规则:100% 原句提取
- 提取的句子必须是文本中的完整原话
- 绝对禁止任何形式的删减、修改、重组或意译
- 必须逐字逐句提取,即使原句在语法上不完美,也不得修改
- 当用户说"我要原句"时,严格对照原文逐字重新核对
首次提取
主动挑选 10-15 条最精彩的金句,优先选择同时满足多条筛选标准的句子。
必须为每条金句标注所属维度,格式为在句末加标注,如:(观点精辟 + 情感共鸣)。维度组合常见的包括:
- 观点精辟 + 高度概括 → 适合做标题、摘要
- 观点精辟 + 表达独特 → 适合做传播金句
- 表达独特 + 情感共鸣 → 适合做情绪钩子
响应追问
理解并执行用户的细化要求:
- "再为[某人]挑一些" → 聚焦该说话人
- "再多找几句" → 降低阈值,扩充到 20+ 条
- "找关于[主题]的金句" → 按主题筛选
- "我要原句" → 重新逐字核对原文
第四步:输出格式
基础输出(按说话人分组):
**[说话人姓名/身份]:**
1. (时间点) 完整的原句内容(维度A + 维度B)
2. (时间点) 完整的原句内容(维度A + 维度B)
**[另一位说话人姓名/身份]:**
1. (时间点) 完整的原句内容(维度A + 维度B)
进阶输出(按维度组合分类):当用户要求严格筛选或按标准分类时,用此格式:
### 观点精辟 + 高度概括
...该类金句
### 表达独特 + 情感共鸣
...该类金句
### 观点精辟 + 表达独特
...该类金句
每条金句末尾必须标注 (满足维度 + 满足维度),便于用户快速判断用途。
格式规则
- 如果原文有时间戳,必须标注时间点
- 如果原文标明说话人,必须注明身份;无法确定说话人时用"说话人A/说话人B"区分
- 如果没有时间戳,写
(--:--) - 保持输出格式清晰一致,按说话人分组
注意事项
- 不要输出分析、点评或推荐理由,只输出金句本身
- 不要对金句排序(除非用户要求),保持原文出现顺序
- 当用户指出有修改时,立即重新核对原文并提供准确的原句,不要辩解
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most sales audience skills give in ~1.4k tokens
Counted across 401 of the 401 authors here whose files we hold, read 2026-08-07
- Read product marketing context before asking questionsin 21 of 401, across 11 files
- Acknowledge competitor strengths honestlyin 18 of 401, across 7 files
- Start every page with a summaryin 15 of 401, across 4 files
- Use a single, low-friction call to actionin 15 of 401, across 7 files
- Create a single source of truth for each competitorin 14 of 401, across 3 files
- Make each follow-up email add new valuein 11 of 401, across 5 files
- Cut any sentence that does not drive a replyin 10 of 401, across 4 files
- Tie personalization directly to the problemin 10 of 401, across 4 files
- Write paragraph comparisons for each dimensionin 9 of 401, across 3 files
- Link between related competitor pagesin 9 of 401, across 3 files
- Keep subject lines short and lowercasein 9 of 401, across 3 files
- Define ideal customer profile from top customersin 9 of 401, across 3 files
Said here and by no other author read
- extract quotes verbatim
- select 10 to 15 best quotes initially
- require each quote to meet two criteria
- append matched criteria tags to each quote
- group output by speaker
- include timestamps if present
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.