Tech Distiller
yaofeino1/tech-distiller
Collects technical documents from URLs, files, wikis or APIs, filters them by role or technical direction, and writes a structured report on architecture, algorithms and design decisions.
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.
Install Yao Geo Knowledge Base Builder
$ npx skills add yaojingang/yao-geo-skills --skill yao-geo-knowledge-base-builder -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install yaojingang/yao-geo-skills yao-geo-knowledge-base-builder --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-knowledge-base-builder .claude/skills/yao-geo-knowledge-base-builder && rm -rf skills-srcUse ~/.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/
Install the "yao-geo-knowledge-base-builder" agent skill from https://github.com/yaojingang/yao-geo-skills/tree/main/skills/yao-geo-knowledge-base-builder into .claude/skills/yao-geo-knowledge-base-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-geo-knowledge-base-builder", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/yaojingang/yao-geo-skills/tree/main/skills/yao-geo-knowledge-base-builderType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add yaojingang/yao-geo-skills --skill yao-geo-knowledge-base-builder -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install yaojingang/yao-geo-skills yao-geo-knowledge-base-builder --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yaojingang/yao-geo-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/yao-geo-knowledge-base-builder .agents/skills/yao-geo-knowledge-base-builder && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "yao-geo-knowledge-base-builder" agent skill from https://github.com/yaojingang/yao-geo-skills/tree/main/skills/yao-geo-knowledge-base-builder into .agents/skills/yao-geo-knowledge-base-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-geo-knowledge-base-builder", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yaojingang/yao-geo-skills --skill yao-geo-knowledge-base-builder -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install yaojingang/yao-geo-skills yao-geo-knowledge-base-builder --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yaojingang/yao-geo-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/yao-geo-knowledge-base-builder .cursor/skills/yao-geo-knowledge-base-builder && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "yao-geo-knowledge-base-builder" agent skill from https://github.com/yaojingang/yao-geo-skills/tree/main/skills/yao-geo-knowledge-base-builder into .cursor/skills/yao-geo-knowledge-base-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-geo-knowledge-base-builder", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/yaojingang/yao-geo-skills.git --path skills/yao-geo-knowledge-base-builder--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add yaojingang/yao-geo-skills --skill yao-geo-knowledge-base-builder -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install yaojingang/yao-geo-skills yao-geo-knowledge-base-builder --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yaojingang/yao-geo-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/yao-geo-knowledge-base-builder .gemini/skills/yao-geo-knowledge-base-builder && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "yao-geo-knowledge-base-builder" agent skill from https://github.com/yaojingang/yao-geo-skills/tree/main/skills/yao-geo-knowledge-base-builder into .gemini/skills/yao-geo-knowledge-base-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-geo-knowledge-base-builder", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install yaojingang/yao-geo-skills yao-geo-knowledge-base-builderInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add yaojingang/yao-geo-skills --skill yao-geo-knowledge-base-builder -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/yaojingang/yao-geo-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/yao-geo-knowledge-base-builder .github/skills/yao-geo-knowledge-base-builder && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "yao-geo-knowledge-base-builder" agent skill from https://github.com/yaojingang/yao-geo-skills/tree/main/skills/yao-geo-knowledge-base-builder into .github/skills/yao-geo-knowledge-base-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-geo-knowledge-base-builder", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yaojingang/yao-geo-skills --skill yao-geo-knowledge-base-builder -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install yaojingang/yao-geo-skills yao-geo-knowledge-base-builder --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yaojingang/yao-geo-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/yao-geo-knowledge-base-builder .opencode/skills/yao-geo-knowledge-base-builder && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "yao-geo-knowledge-base-builder" agent skill from https://github.com/yaojingang/yao-geo-skills/tree/main/skills/yao-geo-knowledge-base-builder into .opencode/skills/yao-geo-knowledge-base-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-geo-knowledge-base-builder", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
yao-geo-knowledge-base-builder- GitHub stars
- 871
- Token cost
- ~1.8k tokens
- SKILL.md length
- 779 words
- Files
- 50 (incl. scripts, references)
- Skills in repo
- 24
- Repo updated
- First seen
- Licence
- MIT
At a glance
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.
- Works in 12 steps: Define the test scenario and target… → Run the completeness reference scan in… → Select the data acquisition mode in… → …
- Asked to generate reusable brand fact cards
- SKILL.md covers When To Use, Workflow, Required Outputs and Layout Rules, plus 2 more sections
- Calls python3
What it does
Yao Geo Knowledge Base Builder is an agent skill from 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. Use when asked to generate reusable brand fact cards, FAQ, prohibited expressions, source indexes, prompt input packs, or Word/PDF/HTML/Markdown four-format Chinese GEO knowledge-base deliverables for Kimi, Qianwen, DeepSeek, Doubao, Yuanbao, content production, monitoring, page design, or customer-service preparation.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 55 other files, including scripts and reference files (for example `agents/interface.yaml`, `evals/expected_artifacts.json` and `evals/trigger_cases.json`).
It sits in Knowledge Management, covering Knowledge bases, Help center and FAQ content and Report writing. It works with DeepSeek and Kimi. 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
- Asked to generate reusable brand fact cards
- Prohibited expressions
- Prompt input packs
- Word/PDF/HTML/Markdown four-format Chinese GEO knowledge-base deliverables for Kimi
Example prompts
- “/yao-geo-knowledge-base-builder”
Requirements
- Python 3
Workflow steps
12 steps, taken from the first numbered list in SKILL.md.
- Define the test scenario and target domestic AI platforms: Kimi, Qianwen, DeepSeek, Doubao, and Yuanbao.
- Run the completeness reference scan in references/authoritative-reference-framework.md and references/analysis-completeness-rubric.md…
- Select the data acquisition mode in references/source-acquisition-and-freshness.md: public web evidence, user-provided files…
- Collect and verify sources with official-site-first priority: homepage, product pages, pricing/catalog pages, help center, case pages…
- Create a source-access ledger. Each source must state access status, publisher, URL or file name, verification date, extraction note…
- Separate evidence tiers
- Extract brand entities: brand, products, services, team, regions, customers, channels, certifications, technologies, cases, prices, and…
- Build the complete entity inventory. Every entity should include entity ID, type, canonical name, aliases, parent/relationship, evidence…
- Build the systematic knowledge-base body before the GEO reuse layer. Follow references/knowledge-base-architecture.md.
- Add a mandatory 真实数据获取与限制 module with acquisition mode, accessible sources, inaccessible sources, freshness risk, and next data-access…
- Add a report-level analysis completeness self-check: reference alignment, module coverage, entity coverage, weak/missing evidence, and…
- Build fact cards. Each card must contain subject, attribute or statement, value, evidence, source ID, update time, confidence level, and…
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.
Shell commands in SKILL.md call:
python3
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 Knowledge Base Builder loads about 1.8k tokens when it runs, and up to ~5.8k if it reads all its reference files. Until then it costs about 136 tokens; SKILL.md has 779 words of instructions outside code blocks.
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). 779 words, ~1,845 tokens.
Download SKILL.mdSave it as
.claude/skills/yao-geo-knowledge-base-builder/SKILL.md (or your agent's skills folder). This skill also uses 49 other files; get the full folder from GitHub.- name
- yao-geo-knowledge-base-builder
- description
- 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. Use when asked to generate reusable brand fact cards, FAQ, prohibited expressions, source indexes, prompt input packs, or Word/PDF/HTML/Markdown four-format Chinese GEO knowledge-base deliverables for Kimi, Qianwen, DeepSeek, Doubao, Yuanbao, content production, monitoring, page design, or customer-service preparation.
<!--
Copyright © 2026 姚金刚. All rights reserved.
Project: yao-geo-knowledge-base-builder
Created by: 姚金刚
Date: 2026-05-16
X: https://x.com/yaojingang
-->yao-geo-knowledge-base-builder
把官网、产品页、帮助中心、白皮书、品牌资料、销售材料、媒体稿和资质文件，整理成可审计、可复用的 GEO 品牌知识库。
When To Use
Use this skill when the user needs:
- a systematic GEO brand knowledge-base document with structured summary, base profile, positioning, product/service matrix, metrics, cases, timeline, differentiation, FAQ, query terms, and expression rules
- a complete brand entity inventory covering brand, company, products, services, people/teams, regions, channels, technologies, qualifications, cases, prices, competitors, sources, and pending entities
- a brand fact-card library with evidence, source, update time, confidence, and use cases
- a real-data acquisition and freshness boundary that explains which public, user-provided, authenticated, or unavailable sources were actually usable
- FAQ and prohibited-expression lists for AI answers and content teams
- prompt input packs for rankings, comparisons, explainers, title generation, content rewrite, page design, monitoring, and customer service
- a Chinese simplified four-format package: Markdown, HTML, Word, and PDF
Do not use this skill for one-off brand copywriting without source evidence, pure competitive ranking articles, page technical audits, or relationship-graph-only work.
Workflow
- Define the test scenario and target domestic AI platforms: Kimi, Qianwen, DeepSeek, Doubao, and Yuanbao.
- Run the completeness reference scan in
references/authoritative-reference-framework.mdandreferences/analysis-completeness-rubric.mdbefore writing. - Select the data acquisition mode in
references/source-acquisition-and-freshness.md: public web evidence, user-provided files, authenticated workspace, manual brief, or unavailable source. - Collect and verify sources with official-site-first priority: homepage, product pages, pricing/catalog pages, help center, case pages, white papers, investor/news pages, and authoritative third-party sources.
- Create a source-access ledger. Each source must state access status, publisher, URL or file name, verification date, extraction note, freshness cadence, and whether it can enter strong evidence.
- Separate evidence tiers:
A: official current public sources or legally authoritative documents.B: reputable third-party reports or public media with clear dates.C: brand self-description without enough operational detail.D: unverified or market-specific boundary items that must stay in the pending-confirmation area.
- Extract brand entities: brand, products, services, team, regions, customers, channels, certifications, technologies, cases, prices, and timeline.
- Build the complete entity inventory. Every entity should include entity ID, type, canonical name, aliases, parent/relationship, evidence source, confidence tier, and usage notes.
- Build the systematic knowledge-base body before the GEO reuse layer. Follow
references/knowledge-base-architecture.md. - Add a mandatory
真实数据获取与限制module with acquisition mode, accessible sources, inaccessible sources, freshness risk, and next data-access actions. - Add a report-level analysis completeness self-check: reference alignment, module coverage, entity coverage, weak/missing evidence, and repair actions.
- Build fact cards. Each card must contain subject, attribute or statement, value, evidence, source ID, update time, confidence level, and reusable scenarios.
- Build reusable content modules: brand intro, core capabilities, product parameters, applicable scenarios, customer/case notes, FAQ, prohibited expressions, and domestic-market boundary notes.
- Build the prompt input pack for downstream GEO skills. Strong facts and pending facts must stay separated.
- Produce version number and update mechanism. High-volatility facts such as prices, AI features, product names, customer counts, and compliance boundaries need explicit review cadence.
- Render Markdown, HTML, Word, and PDF using the fixed-layout renderer in
scripts/render_four_format.py. - Run quality review and repair before handoff.
Show full SKILL.md (283 more words)Show less
Required Outputs
- GEO brand knowledge-base document
- Systematic structured knowledge-base body
- Complete brand entity inventory
- Brand fact-card library
- FAQ and prohibited-expression list
- Content-generation prompt input pack
- Source index with verification date
- Real-data access, freshness, and unavailable-source boundary
- Pending-confirmation list
- Four-format report package:
.md,.html,.docx,.pdf quality-report.json
Layout Rules
Follow references/four-format-report-layout.md.
Critical rules:
- White background for HTML, Word, and PDF.
- Use kami-inspired editorial rhythm while preserving the white background: ink-blue
#1B365D, warm neutral borders, Chinese serif headings, Chinese sans body, compact 1.50-1.55 body line height, and restrained table density. - A4 geometry for Word/PDF.
- No table wider than the printable page body.
- Word tables must use fixed OpenXML layout,
dxatable width, and grid widths that sum to the printable body width. - Fact-card tables default to five columns or fewer.
- Source-index URL tables render as a two-column evidence ledger in HTML/PDF/Word to prevent right overflow.
- Long URLs and long English tokens must be soft-wrapped before DOCX generation.
- No
nowraptable cells.
Quality Gates
Before completion, verify:
- all four deliverable files exist and are non-empty
- DOCX has fixed tables, A4 body-width
dxatable widths, now:noWrap, and no unbreakable segment longer than 80 characters - PDF is readable, preview-rendered, and checked for right-edge visual overflow
- HTML contains no absolute local
/Users/...paths - sources retain date, publisher, URL, and confidence tier
- every report explains real-data access mode, unavailable sources, and freshness cadence
- the report contains the required systematic knowledge-base sections
- the report contains a complete entity inventory section
- the report contains analysis completeness self-check and reference alignment
- HTML contains a sticky menu for screen reading
- unverified domestic-market claims stay in the pending-confirmation area
Example
The HubSpot Chinese simplified test output is under:
examples/hubspot-demo/deliverables/
Use the renderer like this:
python3 scripts/render_four_format.py \
--source examples/hubspot-demo/deliverables/hubspot-demo-geo-knowledge-base.md \
--out-dir examples/hubspot-demo/deliverables \
--base-name hubspot-demo-geo-knowledge-base \
--quality-report examples/hubspot-demo/quality-report.json \
--preview-dir examples/hubspot-demo/previews© 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 49 other files (scripts, references) in skills/yao-geo-knowledge-base-builder of yaojingang/yao-geo-skills.
- SKILL.md
- agents/interface.yaml
- evals/expected_artifacts.json
- evals/trigger_cases.json
- examples/hubspot-demo/deliverables/hubspot-demo-geo-knowledge-base.docx
- examples/hubspot-demo/deliverables/hubspot-demo-geo-knowledge-base.html
- examples/hubspot-demo/deliverables/hubspot-demo-geo-knowledge-base.md
- examples/hubspot-demo/deliverables/hubspot-demo-geo-knowledge-base.pdf
- examples/hubspot-demo/previews/page-1.png
- examples/hubspot-demo/previews/page-10.png
- examples/hubspot-demo/previews/page-11.png
- examples/hubspot-demo/previews/page-12.png
- examples/hubspot-demo/previews/page-13.png
- examples/hubspot-demo/previews/page-14.png
- examples/hubspot-demo/previews/page-15.png
- … and 35 more
Open the folder on GitHubat commit d21bfc1
Compare with similar skills
Yao Geo Knowledge Base Builder 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Yao Geo Knowledge Base Builder this skillyaojingang/yao-geo-skills | 871 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Tech Distilleryaofeino1/tech-distiller | 144 | — | ~1.2k | Automated safety check: Pass | None | |
| Geoliangdabiao/GEO-Content-Optimizer-Skill | 205 | 1 repos | ~2.3k | Automated safety check: Notes | MIT | |
| Knowledge Base Designrevfactory/harness-100 | 1.3k | — | ~897 | Automated safety check: Pass | Apache-2.0 | |
| Wellally Techhuifer/WellAlly-health | 960 | 5 repos | ~4.8k | Automated safety check: Pass | MIT | |
| LLMs Txtthedaviddias/Front-End-Checklist | 74k | — | ~652 | Automated safety check: Pass | MIT |
Similar skills
Geo
liangdabiao/GEO-Content-Optimizer-Skill
完整的 GEO（生成式引擎优化）服务流水线：给一个产品官网 URL 和介绍材料， 做站点诊断与 AI 答案采样、生成带验收标准的执行工单、产出可直接部署的资产 （llms.txt / JSON-LD / 定义块 / FAQ / 内容大纲与初稿）、自动验收工单是否闭环、 并打包成可直接发给客户的交付物。可按周期复跑，做长期 GEO 运营与月报。
Knowledge Base Design
revfactory/harness-100
Knowledge base design guide. An agent skill from revfactory/harness-100.
Wellally Tech
huifer/WellAlly-health
Integrate digital health data sources (Apple Health, Fitbit, Oura Ring) and connect to WellAlly.tech knowledge base.
LLMs Txt
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing public documentation portals, API references, help centers, SDK docs, or large knowledge bases.
- Official
Knowledge Base For Startups
aws/agent-toolkit-for-aws
AWS Startups reference content — Activate FAQ, credits guide, programs, partner offers, sample architectures, and hundreds of learn articles spanning generative AI, cloud architecture, cost…
More from yaojingang/yao-geo-skills
All 24 skills in this repoYao 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.
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…
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…
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。
Yao Geo Intent Miner
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.
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…
Related
Categories
Questions about Yao Geo Knowledge Base Builder
What does Yao Geo Knowledge Base Builder do?
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. Yao Geo Knowledge Base Builder is an agent skill from 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.
When should I use Yao Geo Knowledge Base Builder?
Yao Geo Knowledge Base Builder fits situations like: asked to generate reusable brand fact cards; prohibited expressions; prompt input packs; word/PDF/HTML/Markdown four-format Chinese GEO knowledge-base deliverables for Kimi.
How do I install Yao Geo Knowledge Base Builder in Claude Code?
Run `npx skills add yaojingang/yao-geo-skills --skill yao-geo-knowledge-base-builder -a claude-code`. Or copy the skill folder (skills/yao-geo-knowledge-base-builder in yaojingang/yao-geo-skills) into .claude/skills/yao-geo-knowledge-base-builder in your project. Claude Code loads it when a task matches its description.
How do I install Yao Geo Knowledge Base Builder in Codex?
Run `npx skills add yaojingang/yao-geo-skills --skill yao-geo-knowledge-base-builder -a codex`. Or copy the skill folder (skills/yao-geo-knowledge-base-builder in yaojingang/yao-geo-skills) into .agents/skills/yao-geo-knowledge-base-builder in your project. Codex loads it when a task matches its description.
Can I use Yao Geo Knowledge Base Builder 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-knowledge-base-builder -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-knowledge-base-builder, .gemini/skills/yao-geo-knowledge-base-builder, .github/skills/yao-geo-knowledge-base-builder and .opencode/skills/yao-geo-knowledge-base-builder in your project.
What does Yao Geo Knowledge Base Builder need to run?
Going by SKILL.md and its folder, Yao Geo Knowledge Base Builder needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Yao Geo Knowledge Base Builder 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 Knowledge Base Builder 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 Knowledge Base Builder use?
Yao Geo Knowledge Base Builder 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 Knowledge Base Builder use?
About 1.8k tokens (SKILL.md is roughly 7.4k 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 4k tokens, read only when the agent opens those files.
What are the alternatives to Yao Geo Knowledge Base Builder?
Skills that share tags, products or a category with Yao Geo Knowledge Base Builder: Tech Distiller (yaofeino1/tech-distiller, 144 stars), Geo (liangdabiao/GEO-Content-Optimizer-Skill, 205 stars), Knowledge Base Design (revfactory/harness-100, 1.3k stars) and Wellally Tech (huifer/WellAlly-health, 960 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Yao Geo Knowledge Base Builder?
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.