zach22-1999/generic-skills / skills/zach-term-miner
zach-term-miner
Verified术语挖掘:做一件事之前,先弄清楚这个领域里 AI 听得懂的专业术语,再用这些术语改写你的 prompt。 输入三句话(要做什么 / 已经知道什么 / 哪个领域),产出一个离线 HTML:5 个核验过来源的必要术语、 每个术语对应的「大白话 prompt → 术语版 prompt」前后对照、以及一条 30 分钟学习顺序。 用户说"术语挖掘""我要做 X,需要懂哪些术语才能跟你讲清楚""AI 总是理解偏""这个 prompt 怎么写得更专业" "帮我看看我该学什么术语"时使用。普通词义查询、已有完整 prompt 只想执行、或用户明确要求直接开始做原任务时不要触发。 本 skill 只出术语和 prompt 改写,不执行原任务;不编造术语和来源。
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 60 B |
| LICENSE | other | 1.0 KB |
| README.md | markdown | 5.0 KB |
| SKILL.md | skill md | 5.7 KB |
| examples/listing-bullets.html | other | 20.5 KB |
| examples/non-ecommerce.html | other | 20.3 KB |
| examples/review-mining.html | other | 21.3 KB |
| references/prompt-rewrite-guide.md | markdown | 3.3 KB |
| references/term-prompt-pack.schema.json | config | 4.8 KB |
| references/term-selection-rubric.md | markdown | 2.7 KB |
| scripts/fixtures/listing-bullets.json | config | 7.5 KB |
| scripts/fixtures/non-ecommerce.json | config | 7.5 KB |
| scripts/fixtures/review-mining.json | config | 8.0 KB |
| scripts/render_pack.py | script | 12.9 KB |
| scripts/test_pipeline.py | script | 6.5 KB |
| scripts/validate_pack.py | script | 15.0 KB |
examples/listing-bullets.html
View on GitHub<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta http-equiv="Content-Security-Policy" content="default-src 'none'; style-src 'unsafe-inline'; script-src 'unsafe-inline'; img-src data:; connect-src 'none'; form-action 'none'; base-uri 'none'">
<title>电商卖点文案:用 FABE 和 COSMO 让 AI 从堆参数切换到讲场景</title>
<style>
:root{color-scheme:light dark;--bg:#f6f4ee;--card:#fffdf8;--ink:#1c1f1d;--muted:#5f6663;--line:#d9d4c7;--accent:#1f6f5c;--accent-soft:#e3efe9;--warn:#8a5a12;--warn-soft:#f6e8cf;--code:#f0ede4;--shadow:0 10px 30px rgba(20,30,25,.08)}
@media (prefers-color-scheme:dark){:root{--bg:#161a18;--card:#1f2523;--ink:#eef1ec;--muted:#a3aca6;--line:#36403b;--accent:#7cc8b0;--accent-soft:#213a32;--warn:#e0a85a;--warn-soft:#3f3118;--code:#252c29;--shadow:0 10px 30px rgba(0,0,0,.35)}}
*{box-sizing:border-box}html{scroll-behavior:smooth}
body{margin:0;background:var(--bg);color:var(--ink);font-family:ui-sans-serif,-apple-system,"PingFang SC","Noto Sans SC","Segoe UI",sans-serif;line-height:1.7;font-size:16px}
main{max-width:860px;margin:0 auto;padding:32px 20px 80px}
h1{font-size:1.75rem;line-height:1.3;margin:0 0 12px}h2{font-size:1.2rem;margin:0 0 14px;padding-top:6px}h3{font-size:1.02rem;margin:0 0 6px}
p{margin:0 0 10px}.muted{color:var(--muted)}
.eyebrow{font-size:.78rem;letter-spacing:.12em;text-transform:uppercase;color:var(--accent);font-weight:700;margin:0 0 6px}
section{margin:0 0 36px}
.badges{display:flex;flex-wrap:wrap;gap:8px;margin:14px 0 0}
.badge{display:inline-block;padding:3px 10px;border-radius:999px;font-size:.8rem;border:1px solid var(--line);background:var(--card)}
.badge.accent{background:var(--accent-soft);border-color:transparent;color:var(--accent);font-weight:600}
.banner{background:var(--warn-soft);color:var(--warn);border:1px solid color-mix(in srgb,var(--warn) 40%,transparent);border-radius:12px;padding:12px 16px;margin:18px 0 0;font-weight:600}
.card{background:var(--card);border:1px solid var(--line);border-radius:14px;padding:18px 20px;margin:0 0 14px;box-shadow:var(--shadow);break-inside:avoid}
.card .head{display:flex;justify-content:space-between;gap:12px;align-items:flex-start;flex-wrap:wrap}
.status{font-size:.78rem;padding:2px 9px;border-radius:999px;border:1px solid var(--line);white-space:nowrap}
.status.verified{background:var(--accent-soft);color:var(--accent);border-color:transparent}
.status.private,.status.unverified{background:var(--warn-soft);color:var(--warn);border-color:transparent}
dl{display:grid;grid-template-columns:max-content 1fr;gap:6px 14px;margin:0}dt{color:var(--muted);font-size:.9rem}dd{margin:0}
.sources{margin:10px 0 0;padding:0;list-style:none;font-size:.88rem;color:var(--muted)}.sources li{margin:2px 0}
.compare{display:grid;grid-template-columns:1fr 1fr;gap:12px;margin:10px 0}
@media (max-width:640px){.compare{grid-template-columns:1fr}dl{grid-template-columns:1fr}dt{margin-top:6px}}
.prompt{background:var(--code);border:1px solid var(--line);border-radius:10px;padding:12px 14px;position:relative}
.prompt .label{font-size:.78rem;color:var(--muted);margin:0 0 6px;display:flex;justify-content:space-between;align-items:center}
.prompt pre{margin:0;white-space:pre-wrap;word-break:break-word;font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:.9rem;line-height:1.6}
.prompt.term{border-color:var(--accent)}
button.copy{font:inherit;font-size:.76rem;padding:2px 9px;border-radius:8px;border:1px solid var(--line);background:var(--card);color:var(--ink);cursor:pointer}
button.copy:focus-visible{outline:2px solid var(--accent);outline-offset:2px}
ul.dims{margin:8px 0 0;padding-left:20px}ul.dims li{margin:3px 0}
ol.path{margin:0;padding-left:22px}ol.path li{margin:0 0 10px}.minutes{color:var(--accent);font-weight:600;margin-right:6px}
.assump{margin:8px 0 0;padding-left:20px;color:var(--muted);font-size:.92rem}
footer{color:var(--muted);font-size:.82rem;border-top:1px solid var(--line);padding-top:14px}
@media print{body{background:#fff;color:#000}main{padding:0;max-width:none}.card{box-shadow:none;border-color:#bbb}button.copy{display:none}section{break-inside:auto}h2{break-after:avoid}.prompt{border-color:#999}}
</style>
</head>
<body>
<main id="zach-term-miner-root">
<section>
<p class="eyebrow">术语挖掘 · 30 秒摘要</p>
<h1>电商卖点文案:用 FABE 和 COSMO 让 AI 从堆参数切换到讲场景</h1>
<p>你要写能被平台收录、又能配合广告拿自然排名的卖点描述。FABE 定每条卖点的骨架,COSMO 解释平台为什么按场景和人群理解商品,搜索意图和长尾关键词决定词放哪,关键词堆砌是底线。</p>
<div class="badges"><span class="badge accent">5 个术语</span><span class="badge">已核验 3</span><span class="badge">有来源 2</span><span class="badge">待核验 0</span><span class="badge">3 组 prompt 对照</span></div>
</section>
<section>
<h2>你的任务</h2>
<div class="card"><dl>
<dt>要做什么</dt><dd>为一款产品写一组电商平台卖点描述,兼顾收录、可读性和自然排名</dd>
<dt>已经知道什么</dt><dd>有产品资料和一份关键词表,知道平台在按场景和人群做推荐</dd>
<dt>哪个领域</dt><dd>电商运营与商品文案</dd>
</dl><p><strong>我的假设(你没说、我补的)</strong></p><ul class="assump"><li>目标平台是亚马逊类综合电商平台</li><li>已有关键词表来自第三方工具,未按意图分组</li></ul></div>
</section>
<section>
<h2>必要术语</h2>
<p class="muted">只列会改变 AI 输出方式的词。定义来自来源,「为什么影响这个任务」是本次判断。</p>
<article class="card" id="term-fabe"><div class="head"><h3>1. FABE <span class="muted">· 特征-优势-利益-证据框架</span></h3><span class="status source_defined">有来源</span></div><dl><dt>一句话定义</dt><dd>写卖点时按四步走:产品特征(Feature)、由此带来的优势(Advantage)、对用户的利益(Benefit)、支撑利益的证据(Evidence)。</dd><dt>为什么影响这个任务</dt><dd>AI 会强制每条卖点走完四步,不再只罗列参数;最后一步会主动向你要数据、认证或对比作证据。</dd></dl><ul class="sources"><li>销售培训与营销教材中的通行框架,FAB 部分可追溯到销售方法论著作,FABE 的原始出处不统一(二手解释)</li></ul></article><article class="card" id="term-cosmo"><div class="head"><h3>2. COSMO <span class="muted">· 亚马逊常识知识系统</span></h3><span class="status verified">已核验</span></div><dl><dt>一句话定义</dt><dd>亚马逊发表的电商常识知识生成与服务系统,用大模型从用户行为里挖「什么人在什么场景下为什么买」这类常识关系,用于搜索和推荐。</dd><dt>为什么影响这个任务</dt><dd>知道这个词,AI 写文案会主动以使用场景和人群切入,而不是只堆产品参数,因为平台在按场景和意图理解商品。</dd></dl><ul class="sources"><li>COSMO: A Large-Scale E-commerce Common Sense Knowledge Generation and Serving System at Amazon(论文/标准,Changlong Yu 等,2024)</li></ul></article><article class="card" id="term-search-intent"><div class="head"><h3>3. Search Intent <span class="muted">· 搜索意图</span></h3><span class="status verified">已核验</span></div><dl><dt>一句话定义</dt><dd>用户输入一个查询背后想达成的目的,经典分法是导航型、信息型和交易型。</dd><dt>为什么影响这个任务</dt><dd>AI 会区分哪些关键词是买家准备下单时搜的,哪些是还在比较时搜的,文案和关键词布局会按意图分配。</dd></dl><ul class="sources"><li>A Taxonomy of Web Search(论文/标准,Andrei Broder,2002)</li></ul></article><article class="card" id="term-keyword-stuffing"><div class="head"><h3>4. Keyword Stuffing <span class="muted">· 关键词堆砌</span></h3><span class="status verified">已核验</span></div><dl><dt>一句话定义</dt><dd>为了操纵排名,在页面里塞入大量重复或无关关键词,损害可读性;搜索引擎的垃圾内容政策明确反对。</dd><dt>为什么影响这个任务</dt><dd>AI 知道这个词,就会在「覆盖关键词」和「不牺牲可读性」之间自己找平衡,你不用反复提醒它别写成关键词列表。</dd></dl><ul class="sources"><li>Google Search Essentials:Spam policies(关键词堆砌条目)(官方文档,Google)</li></ul></article><article class="card" id="term-long-tail"><div class="head"><h3>5. Long-tail Keyword <span class="muted">· 长尾关键词</span></h3><span class="status source_defined">有来源</span></div><dl><dt>一句话定义</dt><dd>搜索量低但更具体、竞争更小、意图更明确的多词查询;大量长尾词加起来的流量可观。</dd><dt>为什么影响这个任务</dt><dd>AI 会把核心词和长尾词分开布局,核心词进标题,长尾词进卖点和描述,而不是把所有词往标题里挤。</dd></dl><ul class="sources"><li>The Long Tail(长尾理论),SEO 中的长尾关键词是该概念的引申用法(著作,Chris Anderson,2006)</li></ul></article>
</section>
<section>
<h2>prompt 前后对照</h2>
<p class="muted">左边是不懂术语时的写法,右边是加了术语之后的写法。右边可以直接复制去用。</p>
<article class="card"><h3>对照 1:用上 FABE、COSMO</h3><div class="compare"><div class="prompt plain"><p class="label"><span>大白话版</span><button class="copy" type="button">复制</button></p><pre>附件是产品资料,请帮我写一组电商平台的卖点描述。写的时候要考虑内容能被平台收录,在能收录的情况下,配合我的广告投放,拿到更好的自然排名,最好每条都能打动买家,别只写参数。</pre></div><div class="prompt term"><p class="label"><span>术语版</span><button class="copy" type="button">复制</button></p><pre>附件是产品资料和核心关键词表。请用 FABE 框架写卖点描述:每条以使用场景或人群切入(对齐 COSMO 的场景与意图理解),特征、优势、利益、证据四步齐全。</pre></div></div><p><strong>AI 会多补的维度</strong></p><ul class="dims"><li>每条卖点强制四段,不会只写参数</li><li>以场景和人群开头,而不是以产品开头</li><li>会主动向你要证据:数据、认证、对比</li></ul></article><article class="card"><h3>对照 2:用上 Search Intent、Long-tail Keyword</h3><div class="compare"><div class="prompt plain"><p class="label"><span>大白话版</span><button class="copy" type="button">复制</button></p><pre>这是我整理的关键词表,请帮我把这些词合理地放进标题和卖点里,重要的词放前面,别漏掉,但也别让人一看就是在堆关键词。</pre></div><div class="prompt term"><p class="label"><span>术语版</span><button class="copy" type="button">复制</button></p><pre>附件是关键词表。请按搜索意图分组,交易型核心词进标题,信息型长尾关键词分布到卖点和描述,避免关键词堆砌。</pre></div></div><p><strong>AI 会多补的维度</strong></p><ul class="dims"><li>关键词先按意图分组,再决定位置</li><li>核心词与长尾词分开布局</li><li>可读性有明确底线,不用你再提醒</li></ul></article><article class="card"><h3>对照 3:用上 Keyword Stuffing</h3><div class="compare"><div class="prompt plain"><p class="label"><span>大白话版</span><button class="copy" type="button">复制</button></p><pre>请检查一下这段文案,看看关键词是不是放得太多太密了,读起来会不会不自然,如果有问题帮我改得自然一点但关键词别丢。</pre></div><div class="prompt term"><p class="label"><span>术语版</span><button class="copy" type="button">复制</button></p><pre>请检查这段文案是否存在关键词堆砌,按可读性优先重写,保留核心关键词的自然覆盖。</pre></div></div><p><strong>AI 会多补的维度</strong></p><ul class="dims"><li>用平台反垃圾政策的标准判断,不是凭感觉</li><li>改写时会区分核心词和可删的重复词</li></ul></article>
</section>
<section>
<h2>30 分钟学习顺序</h2>
<p class="muted">合计约 29 分钟</p><ol class="path"><li><span class="minutes">8 分钟</span><strong>FABE</strong><span class="muted"> · 特征-优势-利益-证据框架</span><br>决定每条卖点的骨架,先学它,后面的词都是往骨架里填。</li><li><span class="minutes">8 分钟</span><strong>COSMO</strong><span class="muted"> · 亚马逊常识知识系统</span><br>理解平台为什么按场景和意图看商品,你的切入角度就定了。</li><li><span class="minutes">6 分钟</span><strong>Search Intent</strong><span class="muted"> · 搜索意图</span><br>关键词怎么分组的依据。</li><li><span class="minutes">4 分钟</span><strong>Long-tail Keyword</strong><span class="muted"> · 长尾关键词</span><br>分组之后决定每组放哪里。</li><li><span class="minutes">3 分钟</span><strong>Keyword Stuffing</strong><span class="muted"> · 关键词堆砌</span><br>最后一道底线,知道边界在哪就够。</li></ol>
</section>
<section>
<h2>待核验</h2>
<p class="muted">没有待核验的术语。</p>
<ul class="assump"><li>FABE 只找到教材级二手来源,标为有来源而非已核验。</li><li>COSMO 来源为亚马逊 2024 年论文,已核验。</li></ul>
</section>
<footer>由 zach-term-miner 生成 · 2026-09-07 · listing-copy-fabe · 单文件离线页面,不联网</footer>
</main>
<script type="application/json" id="term-pack-data">{"artifact_kind":"term_prompt_pack","schema_version":1,"artifact_id":"listing-copy-fabe","generated_at":"2026-09-07","locale":"zh-CN","title":"电商卖点文案:用 FABE 和 COSMO 让 AI 从堆参数切换到讲场景","summary":"你要写能被平台收录、又能配合广告拿自然排名的卖点描述。FABE 定每条卖点的骨架,COSMO 解释平台为什么按场景和人群理解商品,搜索意图和长尾关键词决定词放哪,关键词堆砌是底线。","task":{"goal":"为一款产品写一组电商平台卖点描述,兼顾收录、可读性和自然排名","known":"有产品资料和一份关键词表,知道平台在按场景和人群做推荐","domain":"电商运营与商品文案","assumptions":["目标平台是亚马逊类综合电商平台","已有关键词表来自第三方工具,未按意图分组"]},"terms":[{"id":"fabe","term":"FABE","chinese_name":"特征-优势-利益-证据框架","definition":"写卖点时按四步走:产品特征(Feature)、由此带来的优势(Advantage)、对用户的利益(Benefit)、支撑利益的证据(Evidence)。","why_for_this_task":"AI 会强制每条卖点走完四步,不再只罗列参数;最后一步会主动向你要数据、认证或对比作证据。","source_status":"source_defined","sources":[{"title":"销售培训与营销教材中的通行框架,FAB 部分可追溯到销售方法论著作,FABE 的原始出处不统一","kind":"secondary"}]},{"id":"cosmo","term":"COSMO","chinese_name":"亚马逊常识知识系统","definition":"亚马逊发表的电商常识知识生成与服务系统,用大模型从用户行为里挖「什么人在什么场景下为什么买」这类常识关系,用于搜索和推荐。","why_for_this_task":"知道这个词,AI 写文案会主动以使用场景和人群切入,而不是只堆产品参数,因为平台在按场景和意图理解商品。","source_status":"verified","sources":[{"title":"COSMO: A Large-Scale E-commerce Common Sense Knowledge Generation and Serving System at Amazon","kind":"paper","author":"Changlong Yu 等","year":2024}]},{"id":"search-intent","term":"Search Intent","chinese_name":"搜索意图","definition":"用户输入一个查询背后想达成的目的,经典分法是导航型、信息型和交易型。","why_for_this_task":"AI 会区分哪些关键词是买家准备下单时搜的,哪些是还在比较时搜的,文案和关键词布局会按意图分配。","source_status":"verified","sources":[{"title":"A Taxonomy of Web Search","kind":"paper","author":"Andrei Broder","year":2002}]},{"id":"keyword-stuffing","term":"Keyword Stuffing","chinese_name":"关键词堆砌","definition":"为了操纵排名,在页面里塞入大量重复或无关关键词,损害可读性;搜索引擎的垃圾内容政策明确反对。","why_for_this_task":"AI 知道这个词,就会在「覆盖关键词」和「不牺牲可读性」之间自己找平衡,你不用反复提醒它别写成关键词列表。","source_status":"verified","sources":[{"title":"Google Search Essentials:Spam policies(关键词堆砌条目)","kind":"official","author":"Google"}]},{"id":"long-tail","term":"Long-tail Keyword","chinese_name":"长尾关键词","definition":"搜索量低但更具体、竞争更小、意图更明确的多词查询;大量长尾词加起来的流量可观。","why_for_this_task":"AI 会把核心词和长尾词分开布局,核心词进标题,长尾词进卖点和描述,而不是把所有词往标题里挤。","source_status":"source_defined","sources":[{"title":"The Long Tail(长尾理论),SEO 中的长尾关键词是该概念的引申用法","kind":"book","author":"Chris Anderson","year":2006}]}],"prompt_rewrites":[{"id":"rw-fabe-cosmo","term_ids":["fabe","cosmo"],"plain_prompt":"附件是产品资料,请帮我写一组电商平台的卖点描述。写的时候要考虑内容能被平台收录,在能收录的情况下,配合我的广告投放,拿到更好的自然排名,最好每条都能打动买家,别只写参数。","term_prompt":"附件是产品资料和核心关键词表。请用 FABE 框架写卖点描述:每条以使用场景或人群切入(对齐 COSMO 的场景与意图理解),特征、优势、利益、证据四步齐全。","added_dimensions":["每条卖点强制四段,不会只写参数","以场景和人群开头,而不是以产品开头","会主动向你要证据:数据、认证、对比"]},{"id":"rw-intent-longtail","term_ids":["search-intent","long-tail"],"plain_prompt":"这是我整理的关键词表,请帮我把这些词合理地放进标题和卖点里,重要的词放前面,别漏掉,但也别让人一看就是在堆关键词。","term_prompt":"附件是关键词表。请按搜索意图分组,交易型核心词进标题,信息型长尾关键词分布到卖点和描述,避免关键词堆砌。","added_dimensions":["关键词先按意图分组,再决定位置","核心词与长尾词分开布局","可读性有明确底线,不用你再提醒"]},{"id":"rw-stuffing","term_ids":["keyword-stuffing"],"plain_prompt":"请检查一下这段文案,看看关键词是不是放得太多太密了,读起来会不会不自然,如果有问题帮我改得自然一点但关键词别丢。","term_prompt":"请检查这段文案是否存在关键词堆砌,按可读性优先重写,保留核心关键词的自然覆盖。","added_dimensions":["用平台反垃圾政策的标准判断,不是凭感觉","改写时会区分核心词和可删的重复词"]}],"learning_path":[{"term_id":"fabe","minutes":8,"why_this_order":"决定每条卖点的骨架,先学它,后面的词都是往骨架里填。"},{"term_id":"cosmo","minutes":8,"why_this_order":"理解平台为什么按场景和意图看商品,你的切入角度就定了。"},{"term_id":"search-intent","minutes":6,"why_this_order":"关键词怎么分组的依据。"},{"term_id":"long-tail","minutes":4,"why_this_order":"分组之后决定每组放哪里。"},{"term_id":"keyword-stuffing","minutes":3,"why_this_order":"最后一道底线,知道边界在哪就够。"}],"unverified":[],"evidence_summary":{"verified":3,"source_defined":2,"private":0,"unverified":0,"online_verification":true,"notes":["FABE 只找到教材级二手来源,标为有来源而非已核验。","COSMO 来源为亚马逊 2024 年论文,已核验。"]}}</script>
<script>
document.addEventListener('click',function(e){var b=e.target.closest('button.copy');if(!b)return;var pre=b.closest('.prompt').querySelector('pre');var text=pre.textContent;var done=function(){b.textContent='已复制';setTimeout(function(){b.textContent='复制';},1500);};
if(navigator.clipboard&&navigator.clipboard.writeText){navigator.clipboard.writeText(text).then(done,function(){fallback();});}else{fallback();}
function fallback(){var r=document.createRange();r.selectNodeContents(pre);var s=window.getSelection();s.removeAllRanges();s.addRange(r);try{document.execCommand('copy');done();}catch(err){b.textContent='请手动复制';}}});
</script>
</body>
</html>
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |