yao-expert-skill
Create expert-level learning reports and tutorials from any domain, industry, technology, role, market, product idea, or vague field question
Install / Use
npx skills add yaojingang/yao-open-skills --skill yao-expert-skillInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Content & MediaSupported Platforms
Our assessment of yao-expert-skill
yao-expert-skill scores 85/100 on our quality scale, 798th of 1,155 Content & Media skills we index.
Its SKILL.md is 6.8 KB long, well organised into 8 sections and no code examples: a thorough specification that gives an agent plenty to work with.
With 1,318 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 3 months ago, so yao-expert-skill is actively maintained.
- Our last check on 2026-11-04 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-04. Automated pattern scan on 2026-10-04. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
yao-expert-skill compared with similar skills
All 4 of these similar skills score higher than yao-expert-skill; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| yao-expert-skill (this skill)by yaojingang | 85 | 1.3k | 3mo ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| Claude-Code-Game-Studiosby Donchitos | 100 | 39.7k | 7d ago | CLAUDE.md |
| siyuanby siyuan-note | 100 | 47.3k | today | MCP Server |
| x402by browser-use | 100 | 121.0k | 3d ago | SKILL.md |
Frequently asked questions
- How do I install yao-expert-skill?
- Run
npx skills add yaojingang/yao-open-skills --skill yao-expert-skill. The install tabs above show the steps for each supported agent. - Which AI agents does yao-expert-skill work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is yao-expert-skill safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is yao-expert-skill still maintained?
- The repository was last updated about 3 months ago, so yao-expert-skill is actively maintained.
Skill content
View source on GitHubname: yao-expert-skill description: Create expert-level learning reports and tutorials from any domain, industry, technology, role, market, product idea, or vague field question. Use when the user wants to quickly build domain expertise, understand an industry, generate a structured expert study report, build a keyword library, design Feynman self-tests, or export the result as Markdown, DOCX, PDF, and HTML. Do not use for short factual answers, pure business model diagnosis, standalone beginner tutorials with no domain-structure research, simple file conversion, or unsourced opinion writing. metadata: author: Yao Team maturity_tier: production artifact_family: expert-learning-report
Yao Expert Skill
Turn a domain, industry, technology, role, product direction, or fuzzy idea into an expert learning packet: one structured report, one tutorial path, a keyword system, Feynman tests, and four polished export formats.
Own The Following Job
- Normalize the user's topic into domain, region, purpose, audience, time horizon, output depth, and exclusions.
- Build domain expertise from structure first: boundary, classifications, value chain, actors, demand, supply, competition, lifecycle, policy, technology, capital, risks, and change variables.
- Use authority-first research and separate
fact,inference,hypothesis, andunknown. - Generate
50-100keyword teaching cards. Each keyword must include a plain-language one-liner, concept explanation, bottom logic, real example, practical application, role/effect, related people/companies/institutions when relevant, common misconception, and evidence. - Explain difficult concepts and underlying logic with simple analogies plus real domain examples, so a newcomer can understand how the field works rather than only memorize terms.
- Begin every report with a reader-facing
导读摘要that introduces the learning material, highlights, reading path, and structural logic before the formal report sections. - Write each major module with a natural introductory paragraph and transitions before tables, so the report reads as coherent learning material instead of a hard glossary or matrix dump.
- Generate
10Feynman questions with reference answers and a scoring rubric. - Produce Markdown, Word, PDF, and HTML artifacts, with layout checks for tables, borders, overflow, anchors, fixed left-side navigation, and local-path leakage.
Inputs
Expect one or more of:
- a domain, industry, technology, market, role, company direction, or vague idea
- geography, language, audience, use case, time horizon, and desired depth
- existing notes, links, papers, reports, screenshots, or source constraints
- requested output formats, naming, style, deadline, and privacy constraints
When the user gives only a topic, do not stall. Use the defaults in references/domain-expert-method.md, state the assumptions, and continue unless a missing input would materially change the package.
Do Not Route Here
- one-off factual answers or quick explanations
- generic web research that does not produce an expert learning packet
- pure business model work; use a business model skill instead
- beginner tutorial creation with no industry/domain structure; use a tutorial skill instead
- finished-file conversion with no report or tutorial design
- legal, medical, financial, or safety advice as a final recommendation; keep those as educational research with source and uncertainty notes
Default Workflow
- Read
references/domain-expert-method.md; capture assumptions and the expert-learning brief. - Read
references/research-and-source-quality.md; build a source plan and verify current facts when the domain is time-sensitive. - Draft the canonical report in Markdown using
templates/expert-report-template.md. - Add the tutorial path, keyword teaching cards, concept map, representative people/company/case map, Feynman tests, evidence register, and uncertainty log.
- Read
references/report-and-tutorial-contract.md; check section coverage, evidence labels, and learning sufficiency. - Read
references/export-and-layout-quality.md; runscripts/export_expert_report.pyfor Markdown, DOCX, PDF, and HTML. - Run
scripts/validate_artifacts.pyand fix layout, table, anchor, overflow, citation, and local-path issues before delivery.
Output Contract
The normal output set is:
{basename}.md: canonical expert learning report and tutorial packet{basename}.docx: Word document export with readable tables and restrained report styling{basename}.pdf: PDF export checked for page layout and table overflow risk{basename}.html: standalone HTML report with a fixed left-side numbered navigation menu and section anchors- a short delivery note with assumptions, source coverage, uncertainty, validation result, and next learning steps
Quality Gates
- The topic boundary includes wide, narrow, exclusion, and data/source scope.
- The report begins with
导读摘要, including introduction, highlights, reading path, and logic overview; Markdown, DOCX, PDF, and HTML exports must all preserve this opening summary. - Every major module has a reader-facing introduction before dense tables or matrices.
- Key claims are backed by source tier, date, and confidence.
- Every major judgment is labeled as fact, inference, hypothesis, or unknown.
- Keyword teaching cards cover demand, product, technology, value chain, business model, competition, policy, finance, operations, risks, and trends.
- Every keyword teaching card explains: what it means, how to understand it in one sentence, why it exists, how it works, where it appears in the real domain, how to apply it, what role it plays, which people/companies/institutions are associated with it when relevant, and what beginners often misunderstand.
- Representative people, companies, institutions, products, and cases are included as learning anchors, with role labels and source notes rather than unsupported rankings.
- The tutorial can take a beginner from orientation to self-check, not just list terms.
- HTML contains a fixed left-side navigation tree with ordered indices, compact four-character Chinese anchor labels, transparent background, and no standalone sidebar panel styling.
- PDF exports remove the HTML navigation node before printing and hide browser print chrome; no navigation labels,
file://paths, dates, or browser page footers should appear. - DOCX/PDF/HTML exports exist and pass
scripts/validate_artifacts.py, or remaining failures are named precisely.
Reference Map
references/domain-expert-method.mdreferences/research-and-source-quality.mdreferences/report-and-tutorial-contract.mdreferences/export-and-layout-quality.mdtemplates/expert-report-template.mdtemplates/expert-report.csstemplates/report-html-shell.htmlscripts/export_expert_report.pyscripts/validate_artifacts.pyevals/trigger_cases.json
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
Claude-Code-Game-Studios
39.7kTurn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
siyuan
47.3kAn open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间,让人与智能体在此协作
x402
121.0kSet up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
