skill-from-masters
Help users create high-quality skills by discovering and incorporating proven methodologies from domain experts. Use this skill BEFORE skill-creator when users want to create a new skill - it enhances skill-creator by first identifying expert frameworks and best practices to incorporate. Triggers on requests like "help me create a skill for X" or "I want to make a skill that does Y". This skill guides methodology selection, then hands off to skill-creator for the actual skill generation.
Best use case
skill-from-masters is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Help users create high-quality skills by discovering and incorporating proven methodologies from domain experts. Use this skill BEFORE skill-creator when users want to create a new skill - it enhances skill-creator by first identifying expert frameworks and best practices to incorporate. Triggers on requests like "help me create a skill for X" or "I want to make a skill that does Y". This skill guides methodology selection, then hands off to skill-creator for the actual skill generation.
Help users create high-quality skills by discovering and incorporating proven methodologies from domain experts. Use this skill BEFORE skill-creator when users want to create a new skill - it enhances skill-creator by first identifying expert frameworks and best practices to incorporate. Triggers on requests like "help me create a skill for X" or "I want to make a skill that does Y". This skill guides methodology selection, then hands off to skill-creator for the actual skill generation.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "skill-from-masters" skill to help with this workflow task. Context: Help users create high-quality skills by discovering and incorporating proven methodologies from domain experts. Use this skill BEFORE skill-creator when users want to create a new skill - it enhances skill-creator by first identifying expert frameworks and best practices to incorporate. Triggers on requests like "help me create a skill for X" or "I want to make a skill that does Y". This skill guides methodology selection, then hands off to skill-creator for the actual skill generation.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/skill-from-masters/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How skill-from-masters Compares
| Feature / Agent | skill-from-masters | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Help users create high-quality skills by discovering and incorporating proven methodologies from domain experts. Use this skill BEFORE skill-creator when users want to create a new skill - it enhances skill-creator by first identifying expert frameworks and best practices to incorporate. Triggers on requests like "help me create a skill for X" or "I want to make a skill that does Y". This skill guides methodology selection, then hands off to skill-creator for the actual skill generation.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Skill From Masters Create skills that embody the wisdom of domain masters. This skill helps users discover and incorporate proven methodologies from recognized experts before generating a skill. ## Core Philosophy Most professional domains have outstanding practitioners who have codified their methods through books, talks, interviews, and frameworks. A skill built on these proven methodologies is far more valuable than one created from scratch. The goal is not just "good enough" — it's reaching the highest level of human expertise in that domain. ## Workflow ### Step 1: Understand the Skill Intent Ask the user: - What skill do they want to create? - What specific tasks should it handle? - What quality bar are they aiming for? ### Step 2: Identify Relevant Domains Map the skill to one or more methodology domains. A single skill may span multiple domains. Example mappings: - "Sales email skill" → Sales, Writing, Persuasion - "User interview skill" → User Research, Interviewing, Product Discovery - "Presentation skill" → Storytelling, Visual Design, Persuasion - "Code review skill" → Software Engineering, Feedback, Communication ### Step 3: Surface Expert Methodologies **Layer 1: Local Database** Consult `references/methodology-database.md` for known frameworks. **Layer 2: Web Search for Experts** Search the web to discover additional experts and methodologies: - Search: "[domain] best practices expert" - Search: "[domain] framework methodology" - Search: "[domain] master practitioner" **Layer 3: Deep Dive on Selected Experts** For promising experts, search for their original content: - Search: "[expert name] methodology interview" - Search: "[expert name] [domain] transcript" - Search: "[expert name] framework explained" Fetch and read primary sources when available (articles, talk transcripts, blog posts). For each relevant domain, present: - Key experts and their core contributions - Specific frameworks, principles, or processes - Source materials (books, talks, interviews) ### Step 4: Find Golden Examples Before finalizing methodology selection, search for exemplary outputs: - Search: "best [output type] examples" - Search: "[output type] template [top company]" - Search: "award winning [output type]" Understanding what excellence looks like helps define the quality bar. ### Step 5: Collaborative Selection Present the methodologies to the user and discuss: - Which frameworks resonate with their goals? - Are there conflicts between methodologies to resolve? - Should they combine multiple approaches? - Any specific principles they want to emphasize or exclude? Guide the user to select 1-3 primary methodologies that will form the skill's foundation. ### Step 6: Extract Actionable Principles For each selected methodology, search for and distill: **The Why (Core Principles)** - Search: "[methodology] core principles" - Search: "why [methodology] works" **The How (Concrete Process)** - Search: "[methodology] step by step" - Search: "[methodology] implementation guide" **The What (Quality Criteria)** - Search: "[methodology] checklist" - Search: "[methodology] evaluation criteria" **The Pitfalls (Common Mistakes)** - Search: "[domain] common mistakes" - Search: "[methodology] pitfalls avoid" Fetch primary sources to get exact wording and nuance, not just summaries. ### Step 7: Cross-Validate Compare insights across multiple sources: - What principles appear consistently? (high confidence) - Where do experts disagree? (flag for user) - What's unique to each approach? (differentiation) Synthesize a coherent framework that takes the best from each source. ### Step 8: Generate the Skill With methodologies confirmed, use the **skill-creator** skill to generate the final skill. The generated skill should: 1. Credit the methodology sources in a comment (documenting provenance) 2. Translate expert wisdom into actionable instructions 3. Include concrete examples derived from golden examples found 4. Capture quality criteria as explicit checkpoints 5. Include "don't do this" anti-patterns from pitfall research 6. Match the quality bar of the best human practitioners ## Quality Checklist Before finalizing, verify: - [ ] Did we search beyond the local database? - [ ] Did we find primary sources, not just summaries? - [ ] Did we find golden examples of the output? - [ ] Did we identify common mistakes to avoid? - [ ] Did we cross-validate across multiple experts? - [ ] Does the skill encode specific, actionable steps (not vague principles)? ## Example Interaction **User**: I want to create a skill for writing product requirement documents. **Assistant**: Great choice. Let me search for the best methodologies on PRD writing. [Searches: "PRD best practices expert", "product requirements document methodology", "best PRD examples"] I found several strong frameworks: **Product Management**: - Marty Cagan (SVPG): Emphasizes problem-first PRDs, separating problem space from solution space - Teresa Torres: Continuous discovery, outcome-focused requirements **Business Writing**: - Barbara Minto: Pyramid Principle - lead with conclusion, MECE structure - Amazon: Working backwards from press release, 6-pager narrative format **Golden Examples Found**: - Intercom's public PRD template - Linear's product spec format **Common Mistakes** (from my search): - Jumping to solutions before defining the problem - Writing for engineers instead of for alignment - Missing success metrics Which of these approaches resonates? Or should I search deeper into any of them? **User**: I like Amazon's approach combined with Cagan's problem-first thinking. Can you find more details on Amazon's method? **Assistant**: [Searches: "Amazon 6-pager template", "Amazon working backwards methodology", "Amazon PR FAQ process"] [Fetches relevant articles and synthesizes key principles] Here's what I found from primary sources... [Continues to Step 6, 7, and 8]
Related Skills
azure-quotas
Check/manage Azure quotas and usage across providers. For deployment planning, capacity validation, region selection. WHEN: "check quotas", "service limits", "current usage", "request quota increase", "quota exceeded", "validate capacity", "regional availability", "provisioning limits", "vCPU limit", "how many vCPUs available in my subscription".
raindrop-io
Manage Raindrop.io bookmarks with AI assistance. Save and organize bookmarks, search your collection, manage reading lists, and organize research materials. Use when working with bookmarks, web research, reading lists, or when user mentions Raindrop.io.
zlibrary-to-notebooklm
自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式,自动转换,一键创建知识库。
discover-skills
当你发现当前可用的技能都不够合适(或用户明确要求你寻找技能)时使用。本技能会基于任务目标和约束,给出一份精简的候选技能清单,帮助你选出最适配当前任务的技能。
web-performance-seo
Fix PageSpeed Insights/Lighthouse accessibility "!" errors caused by contrast audit failures (CSS filters, OKLCH/OKLAB, low opacity, gradient text, image backgrounds). Use for accessibility-driven SEO/performance debugging and remediation.
project-to-obsidian
将代码项目转换为 Obsidian 知识库。当用户提到 obsidian、项目文档、知识库、分析项目、转换项目 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入规则(默认到 00_Inbox/AI/、追加式、统一 Schema) 3. 执行 STEP 0: 使用 AskUserQuestion 询问用户确认 4. 用户确认后才开始 STEP 1 项目扫描 5. 严格按 STEP 0 → 1 → 2 → 3 → 4 顺序执行 【禁止行为】: - 禁止不读 SKILL.md 就开始分析项目 - 禁止跳过 STEP 0 用户确认 - 禁止直接在 30_Resources 创建(先到 00_Inbox/AI/) - 禁止自作主张决定输出位置
obsidian-helper
Obsidian 智能笔记助手。当用户提到 obsidian、日记、笔记、知识库、capture、review 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入三条硬规矩(00_Inbox/AI/、追加式、白名单字段) 3. 按 STEP 0 → STEP 1 → ... 顺序执行 4. 不要跳过任何步骤,不要自作主张 【禁止行为】: - 禁止不读 SKILL.md 就开始工作 - 禁止跳过用户确认步骤 - 禁止在非 00_Inbox/AI/ 位置创建新笔记(除非用户明确指定)
internationalizing-websites
Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content. Use when adding new languages, setting up i18n, optimizing for international SEO, or when user mentions localization, translation, multi-language, or specific languages like Japanese, Korean, Chinese.
google-official-seo-guide
Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation
github-release-assistant
Generate bilingual GitHub release documentation (README.md + README.zh.md) from repo metadata and user input, and guide release prep with git add/commit/push. Use when the user asks to write or polish README files, create bilingual docs, prepare a GitHub release, or mentions release assistant/README generation.
doc-sync-tool
自动同步项目中的 Agents.md、claude.md 和 gemini.md 文件,保持内容一致性。支持自动监听和手动触发。
deploying-to-production
Automate creating a GitHub repository and deploying a web project to Vercel. Use when the user asks to deploy a website/app to production, publish a project, or set up GitHub + Vercel deployment.