Agent skill

Yao Geo Intent Miner

by yaojingang in yaojingang/yao-geo-skills

A skill your agent uses when a user asks for GEO 意图拓词、AI 搜索意图挖掘、AI 搜索问题集、问题簇、追问链路、查询重写、内容选题库、FAQ 题库、监测 Prompt 库, or AI Intent Miner.

MITAuto-check passedSales & Support

Install Yao Geo Intent Miner

skills CLI
$ npx skills add yaojingang/yao-geo-skills --skill yao-geo-intent-miner -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install yaojingang/yao-geo-skills yao-geo-intent-miner --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/yaojingang/yao-geo-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/yao-geo-intent-miner .claude/skills/yao-geo-intent-miner && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
yao-geo-intent-miner
GitHub stars
871
Token cost
~500 tokens
SKILL.md length
96 words
Files
34 (incl. scripts, references)
Skills in repo
24
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a user asks for GEO 意图拓词、AI 搜索意图挖掘、AI 搜索问题集、问题簇、追问链路、查询重写、内容选题库、FAQ 题库、监测 Prompt 库, or AI Intent Miner.

  • Works in 12 steps: 归一化输入对象:主对象、品牌、产品线、行业、竞品、区域、人群、预算、场景、痛点、资… → 判断真实数据模式:未接入 / 用户提供 / 工具或连接器导入 /… → 做事实与证据校准:品牌、产品、价格、合规、竞品和行业事实必须标注来源状态,未校准信… → …
  • A user asks for GEO 意图拓词、AI 搜索意图挖掘、AI 搜索问题集、问题簇、追问链路、查询重写、内容选题库、FAQ 题库、监测 Prompt 库
  • SKILL.md covers 使用场景, 必读资料, 执行流程 and 输出契约
  • AI Intent Miner

What it does

Yao Geo Intent Miner is an agent skill from yaojingang/yao-geo-skills. Use when a user asks for GEO 意图拓词、AI 搜索意图挖掘、AI 搜索问题集、问题簇、追问链路、查询重写、内容选题库、FAQ 题库、监测 Prompt 库, or AI Intent Miner.

Its SKILL.md is about 500 tokens, which your agent loads only when the skill is triggered. The skill folder holds 39 other files, including scripts and reference files (for example `agents/interface.yaml`, `evals/expected_artifacts.json` and `evals/failure_cases.md`).

It sits in Sales & Support, covering Help center and FAQ content. The repository describes itself as: An open-source Skill collection for GEO content and workflows, continuously updated. The licence is MIT.

When your agent uses it

  • A user asks for GEO 意图拓词、AI 搜索意图挖掘、AI 搜索问题集、问题簇、追问链路、查询重写、内容选题库、FAQ 题库、监测 Prompt 库
  • AI Intent Miner

Example prompts

  • “/yao-geo-intent-miner”

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. 归一化输入对象:主对象、品牌、产品线、行业、竞品、区域、人群、预算、场景、痛点、资质、规模、时效和材料来源。
  2. 判断真实数据模式:未接入 / 用户提供 / 工具或连接器导入 / 已采样校准。没有真实数据时,必须输出数据缺口和采样计划,不能伪造真实平台回答、搜索量或转化数据。
  3. 做事实与证据校准:品牌、产品、价格、合规、竞品和行业事实必须标注来源状态,未校准信息只能作为假设或待确认项。
  4. 建立双层意图:先映射到信息、导航/验证、交易/行动任务层,再扩展为九类 GEO 操作意图。
  5. 按角色、场景、决策阶段、约束条件、证据需求和内容资产用途生成完整自然语言问题,不能只堆短关键词。
  6. 输出五段式重写:口语问法、独立重写、检索短语、证据查询、标题输入。
  7. 保留多轮追问链路:root_question_id / parent_question_id / standalone_rewrite / context_dependency / platform_fit。
  8. 聚类去重,按问题目标、用户角色、约束条件、资产用途和合规等级合并同义问题。
  9. 十维评分:商业价值、AI 答案触发概率、内容缺口、品牌植入空间、证据可得性、竞争难度、对话延展价值、决策阶段价值、平台覆盖度、合规风险。若有真实数据,按搜索量、AI 采样、客服/销售频次和转化信号校准分数。
  10. 映射资产:文章、页面模块、FAQ、知识库条目、监测 Prompt、标题生成输入包、证据补采任务和 30/60/90 天落地路线。
  11. 报告正文必须覆盖 references/report-module-contract.md 的系统模块;允许按项目删减,但删减原因要写入质检说明。
  12. 输出 Word/PDF/HTML/Markdown 时必须遵守 references/four-format-output.md。HTML 使用 kami 长文档排版语言:暖纸底、油墨蓝、暖灰边框、serif 标题、sticky 菜单;Word 宽表必须横向…

What it can do on your machine

Read from SKILL.md and the folder at commit d21bfc1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • x.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Yao Geo Intent Miner loads about 500 tokens when it runs, and up to ~4.7k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 96 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~500
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from yaojingang/yao-geo-skills at commit d21bfc1, republished under its MIT licence (© yaojingang). 96 words, ~500 tokens.

Download SKILL.mdSave it as .claude/skills/yao-geo-intent-miner/SKILL.md (or your agent's skills folder). This skill also uses 33 other files; get the full folder from GitHub.
name
yao-geo-intent-miner
description
Use when a user asks for GEO 意图拓词、AI 搜索意图挖掘、AI 搜索问题集、问题簇、追问链路、查询重写、内容选题库、FAQ 题库、监测 Prompt 库, or AI Intent Miner.
<!--
Copyright © 2026 姚金刚. All rights reserved.
Project: yao-geo-intent-miner
Created by: 姚金刚
Date: 2026-05-16
X: https://x.com/yaojingang
-->

Yao GEO Intent Miner

使用场景

  • 把种子词、品牌、产品、竞品、区域、人群和业务材料扩展成 AI 搜索问题集。
  • 先于内容生产建立问题底座,输出意图簇、追问链路、查询重写、内容选题、FAQ、知识库和监测 Prompt。
  • 面向 DeepSeek、豆包、千问、Kimi、元宝适配国内 AI 平台的口语、多轮、场景和复杂决策问法。

必读资料

  • references/research-foundation.md
  • references/intent-mining-method.md
  • references/cn-platform-adaptation.md
  • references/scoring-and-mapping.md
  • references/real-data-ingestion.md
  • references/report-module-contract.md
  • references/four-format-output.md
  • references/quality-gates.md

执行流程

  1. 归一化输入对象:主对象、品牌、产品线、行业、竞品、区域、人群、预算、场景、痛点、资质、规模、时效和材料来源。
  2. 判断真实数据模式:未接入 / 用户提供 / 工具或连接器导入 / 已采样校准。没有真实数据时,必须输出数据缺口和采样计划,不能伪造真实平台回答、搜索量或转化数据。
  3. 做事实与证据校准:品牌、产品、价格、合规、竞品和行业事实必须标注来源状态,未校准信息只能作为假设或待确认项。
  4. 建立双层意图:先映射到信息、导航/验证、交易/行动任务层,再扩展为九类 GEO 操作意图。
  5. 按角色、场景、决策阶段、约束条件、证据需求和内容资产用途生成完整自然语言问题,不能只堆短关键词。
  6. 输出五段式重写:口语问法、独立重写、检索短语、证据查询、标题输入。
  7. 保留多轮追问链路:root_question_id / parent_question_id / standalone_rewrite / context_dependency / platform_fit。
  8. 聚类去重,按问题目标、用户角色、约束条件、资产用途和合规等级合并同义问题。
  9. 十维评分:商业价值、AI 答案触发概率、内容缺口、品牌植入空间、证据可得性、竞争难度、对话延展价值、决策阶段价值、平台覆盖度、合规风险。若有真实数据,按搜索量、AI 采样、客服/销售频次和转化信号校准分数。
  10. 映射资产:文章、页面模块、FAQ、知识库条目、监测 Prompt、标题生成输入包、证据补采任务和 30/60/90 天落地路线。
  11. 报告正文必须覆盖 references/report-module-contract.md 的系统模块;允许按项目删减,但删减原因要写入质检说明。
  12. 输出 Word/PDF/HTML/Markdown 时必须遵守 references/four-format-output.md。HTML 使用 kami 长文档排版语言:暖纸底、油墨蓝、暖灰边框、serif 标题、sticky 菜单;Word 宽表必须横向 A4、固定表格布局、表格总宽不超过页面可用宽度;PDF 默认横向 A4,宽表自动换行且不向右溢出。
  13. 自 review:检查四个报告是否存在、格式是否有效、内容是否一致、HTML/Word/PDF 是否符合 kami 版式且表格不溢出。

输出契约

  • AI 搜索问题集与意图地图。
  • 问题聚类、追问链路和查询重写清单。
  • 评分矩阵与优先级排序。
  • 内容选题、FAQ 题库、知识库条目建议。
  • 监测 Prompt 库。
  • 证据缺口、合规边界和落地路线。
  • 真实数据接入状态、AI 平台采样计划、数据校准动作。
  • 默认四件套:Markdown、HTML、Word、PDF。

© yaojingang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 33 other files (scripts, references) in skills/yao-geo-intent-miner of yaojingang/yao-geo-skills.

  • SKILL.md
  • agents/interface.yaml
  • evals/expected_artifacts.json
  • evals/failure_cases.md
  • evals/quality_cases.json
  • evals/rubric.md
  • evals/trigger_cases.json
  • examples/README.md
  • examples/hubspot-cn-demo/expected-output/hubspot-cn-ai-intent-miner-demo.docx
  • examples/hubspot-cn-demo/expected-output/hubspot-cn-ai-intent-miner-demo.html
  • examples/hubspot-cn-demo/expected-output/hubspot-cn-ai-intent-miner-demo.md
  • examples/hubspot-cn-demo/expected-output/hubspot-cn-ai-intent-miner-demo.pdf
  • examples/hubspot-cn-demo/expected-output/index.html
  • examples/hubspot-cn-demo/expected-output/quality-report.json
  • examples/hubspot-cn-demo/input/report_input.json
  • … and 19 more

Open the folder on GitHubat commit d21bfc1

Compare with similar skills

Yao Geo Intent Miner next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Yao Geo Intent Miner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Yao Geo Intent Miner this skillyaojingang/yao-geo-skills871—~500Automated safety check: PassMIT
Brand Product Knowledge Builderlimecloud/lime1.5k—~709Automated safety check: PassApache-2.0
Cc10x Guideromiluz13/cc10x165—~2.2kAutomated safety check: PassMIT
Faq CollectorCherryHQ/cherry-studio53k—~154Automated safety check: PassAGPL-3.0
Eol Internal Enablementdeanpeters/Product-Manager-Skills7.2k—~3.1kAutomated safety check: PassCustom licence
Satisfaction FeedbackHarryoung/efka104—~346Automated safety check: PassApache-2.0

Similar skills

  • 将品牌产品资料、规格参数、卖点证据、FAQ、价格权益、竞品区别和合规边界,整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的产品资料知识库。适用于用户要求“整理产品知识库”“沉淀产品 FAQ”“把品牌产品资料变成项目资料”“维护产品资料包”的场景。

    1.5k GitHub stars~709 tokensUpdated yesterday
    Sales & SupportAuto-check passed
  • Cc10x Guide

    romiluz13/cc10x

    Answers questions about cc10x itself — what it is, how to install and configure it, how the router, workflows, memory, and hooks operate, and how to troubleshoot.

    165 GitHub stars~2.2k tokensUpdated 3 days ago
    Sales & SupportAuto-check passed
  • Faq Collector

    CherryHQ/cherry-studio

    将成功解决的用户问题收录到 FAQ 知识库。问题解决后自动判断是否收录。也可以在用户说"收录到 FAQ"、"记录这个问题"、"add to FAQ"时手动触发。

    53k GitHub stars~154 tokensUpdated today
    Sales & SupportAuto-check passed
  • Eol Internal Enablement

    deanpeters/Product-Manager-Skills

    Build the support FAQ, sales talking points, and objection handling teams need before an EOL announcement.

    7.2k GitHub stars~3.1k tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed
  • Satisfaction Feedback

    Harryoung/efka

    Handle user satisfaction feedback. An agent skill from Harryoung/efka.

    104 GitHub stars~346 tokensUpdated 6 mo ago
    Sales & SupportAuto-check passed
  • Summary Faq Workflow

    ArmDeveloperEcosystem/arm-learning-paths

    Generate, style-review, and patch AI-assisted Learning Path summaries and FAQs for one path, a path subset, a category, or the repository.

    154 GitHub stars~1.5k tokensUpdated yesterday
    Sales & SupportAuto-check passed

More from yaojingang/yao-geo-skills

All 24 skills in this repo
  • Yao Geo Knowledge Base Builder

    yaojingang/yao-geo-skills

    Build evidence-backed GEO brand knowledge bases from official sites, product pages, help centers, white papers, sales materials, media releases, certifications, and trusted third-party sources.

    871 GitHub stars~1.8k tokensUpdated 10 days ago
    Auto-check passed
  • Yao Geo Title Optimizer

    yaojingang/yao-geo-skills

    A skill your agent uses when Chinese content teams need GEO title candidates, scoring, compliance review, or title-to-article mapping for articles, pages, FAQs, comparisons, and topic hubs.

    871 GitHub stars~2k tokensUpdated 10 days ago
    Auto-check passed
  • Yao Geo Tracking

    yaojingang/yao-geo-skills

    Build a company-specific GEO backend tracking plan from a company name plus optional supporting information, using authoritative retrieval anchored on the official website, business-feature…

    871 GitHub stars~1.5k tokensUpdated 10 days ago
    Auto-check passed
  • Yao Deepseek Crawler

    yaojingang/yao-geo-skills

    A skill your agent uses when a user provides DeepSeek web AI-search keywords, repeat count, target entity, and entity type, then needs repeated fresh-window crawls aggregated into JSON plus a Kami…

    871 GitHub stars~624 tokensUpdated 10 days ago
    Auto-check passed
  • Yao Geo Execution Roadmap

    yaojingang/yao-geo-skills

    当用户需要把 GEO 全景诊断、机会地图、AI 平台采样结论或品牌事实底座转成 30/60/90 天综合实施方案时使用,输出页面技术、内容矩阵、标题体系、知识库、外部证据、监测闭环、角色分工、验收指标和四格式报告;覆盖 DeepSeek、豆包、千问、Kimi、元宝;不用于从零做全景采样诊断或只写单篇内容。

    871 GitHub stars~646 tokensUpdated 10 days ago
    Auto-check passed
  • Yao Geo Page Blueprint

    yaojingang/yao-geo-skills

    A skill your agent uses when the user needs a GEO-friendly page blueprint for a specific product, topic, article, ranking, comparison, FAQ, knowledge-base, or case page, especially when the work…

    871 GitHub stars~789 tokensUpdated 10 days ago
    Auto-check passed

Categories

Questions about Yao Geo Intent Miner

What does Yao Geo Intent Miner do?

A skill your agent uses when a user asks for GEO 意图拓词、AI 搜索意图挖掘、AI 搜索问题集、问题簇、追问链路、查询重写、内容选题库、FAQ 题库、监测 Prompt 库, or AI Intent Miner. Yao Geo Intent Miner is an agent skill from yaojingang/yao-geo-skills. Use when a user asks for GEO 意图拓词、AI 搜索意图挖掘、AI 搜索问题集、问题簇、追问链路、查询重写、内容选题库、FAQ 题库、监测 Prompt 库, or AI Intent Miner.

When should I use Yao Geo Intent Miner?

Yao Geo Intent Miner fits situations like: A user asks for GEO 意图拓词、AI 搜索意图挖掘、AI 搜索问题集、问题簇、追问链路、查询重写、内容选题库、FAQ 题库、监测 Prompt 库; AI Intent Miner.

How do I install Yao Geo Intent Miner in Claude Code?

Run `npx skills add yaojingang/yao-geo-skills --skill yao-geo-intent-miner -a claude-code`. Or copy the skill folder (skills/yao-geo-intent-miner in yaojingang/yao-geo-skills) into .claude/skills/yao-geo-intent-miner in your project. Claude Code loads it when a task matches its description.

How do I install Yao Geo Intent Miner in Codex?

Run `npx skills add yaojingang/yao-geo-skills --skill yao-geo-intent-miner -a codex`. Or copy the skill folder (skills/yao-geo-intent-miner in yaojingang/yao-geo-skills) into .agents/skills/yao-geo-intent-miner in your project. Codex loads it when a task matches its description.

Can I use Yao Geo Intent Miner in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yaojingang/yao-geo-skills --skill yao-geo-intent-miner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/yao-geo-intent-miner, .gemini/skills/yao-geo-intent-miner, .github/skills/yao-geo-intent-miner and .opencode/skills/yao-geo-intent-miner in your project.

What does Yao Geo Intent Miner need to run?

SKILL.md names no scripts, command-line tools or credentials: Yao Geo Intent Miner is instructions for the agent only.

Does Yao Geo Intent Miner access the network?

SKILL.md names 1 domain. As links in the text: x.com. This is read from the text; nothing was executed.

Is Yao Geo Intent Miner safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Yao Geo Intent Miner use?

Yao Geo Intent Miner is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Yao Geo Intent Miner use?

About 500 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.2k tokens, read only when the agent opens those files.

What are the alternatives to Yao Geo Intent Miner?

Skills that share tags, products or a category with Yao Geo Intent Miner: Brand Product Knowledge Builder (limecloud/lime, 1.5k stars), Cc10x Guide (romiluz13/cc10x, 165 stars), Faq Collector (CherryHQ/cherry-studio, 53k stars) and Eol Internal Enablement (deanpeters/Product-Manager-Skills, 7.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Yao Geo Intent Miner?

yaojingang (a GitHub user) maintains it in yaojingang/yao-geo-skills, which has 871 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 1, 2026.

Source: yaojingang/yao-geo-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.