π‘ Summary
This skill helps create AI skills by leveraging proven methodologies from domain experts.
π― Target Audience
π€ AI Roast: βPowerful, but the setup might scare off the impatient.β
The skill may access external web resources, posing risks like data leakage or exposure to malicious content. Ensure proper validation and sanitization of inputs to mitigate these risks.
Skill From Masters
Stand on the shoulders of giants β Create AI skills built on proven methodologies from domain experts.
A skill that helps you discover and incorporate frameworks, principles, and best practices from recognized masters before generating any new skill. Works with Claude Code, Codex, and other AI agent platforms.
Why This Skill?
The hard part of creating a skill isn't the format β it's knowing the best way to do the thing.
Most professional domains have masters who spent decades figuring out what works:
- Jobs on product, hiring, and marketing
- Bezos on writing (6-pager) and decision-making
- Munger on mental models
- Chris Voss on negotiation
This skill surfaces their methodologies before you write a single line, so your skill embodies world-class expertise from day one.
How It Works
1. You: "I want to create a skill for user interviews"
2. Skill-from-masters:
βββ Checks local methodology database
βββ Searches web for additional experts
βββ Finds golden examples of great outputs
βββ Identifies common mistakes to avoid
βββ Cross-validates across sources
3. Surfaces experts:
- Rob Fitzpatrick (The Mom Test)
- Steve Portigal (Interviewing Users)
- Nielsen Norman Group best practices
4. You select which methodologies to incorporate
5. Extracts actionable principles from primary sources
6. Hands off to skill-creator to generate the final skill
Key Features
| Feature | Description | |---------|-------------| | 3-Layer Search | Local database β Web search for experts β Deep dive on primary sources | | Golden Examples | Finds exemplary outputs to define quality bar | | Anti-Patterns | Searches for common mistakes to encode "don't do this" | | Cross-Validation | Compares multiple experts to find consensus and flag disagreements | | Quality Checklist | Verifies completeness before generating |
Methodology Database
The skill includes a curated database covering 15+ domains:
| Domain | Example Experts | |--------|-----------------| | Writing | Barbara Minto, William Zinsser, Amazon 6-pager | | Product | Marty Cagan, Teresa Torres, Gibson Biddle | | Sales | Neil Rackham (SPIN), Challenger Sale, MEDDIC | | Hiring | Laszlo Bock, Geoff Smart, Lou Adler | | User Research | Rob Fitzpatrick, Steve Portigal, JTBD | | Engineering | Martin Fowler, Robert Martin, Kent Beck | | Leadership | Kim Scott, Ray Dalio, Andy Grove | | Negotiation | Chris Voss, Fisher & Ury | | Startups | Eric Ries, Paul Graham, YC | | Decision Making | Jeff Bezos, Charlie Munger, Annie Duke |
Plus an "Oral Tradition" section for experts who share primarily through talks and interviews (Steve Jobs, Elon Musk, Jensen Huang, Patrick Collison, etc.)
Installation
Option 1: Clone directly (Recommended)
# Navigate to your skills directory cd ~/.claude/skills # Claude Code # or your platform's skills path # Clone this skill git clone https://github.com/anthropics/skill-from-masters.git
Option 2: Manual installation
- Download the
skill-from-mastersfolder - Place it in your skills directory
Dependency
This skill works with skill-creator. Make sure skill-creator is available in your environment.
Usage
The skill automatically activates when you ask to create a new skill. It runs before skill-creator to ensure your skill is built on proven methodologies.
Example Session
You: "Help me create a skill for writing product requirement documents"
Skill-from-masters:
Let me search for the best methodologies on PRD writing.
[Searches: "PRD best practices expert", "product requirements document methodology"]
I found several strong frameworks:
Product Management:
- Marty Cagan: Problem-first PRDs, separating problem space from solution space
- Teresa Torres: Outcome-focused requirements
Business Writing:
- Barbara Minto: Pyramid Principle - lead with conclusion, MECE structure
- Amazon: Working backwards, 6-pager narrative format
Golden Examples Found:
- Intercom's public PRD template
- Linear's product spec format
Common Mistakes:
- Jumping to solutions before defining the problem
- Writing for engineers instead of for alignment
- Missing success metrics
Which approaches resonate? Or should I search deeper into any of them?
You: "I like Amazon's approach combined with Cagan's problem-first thinking."
Skill-from-masters: [Fetches primary sources on Amazon's methodology, extracts principles, then generates skill via skill-creator]
Skills
This repository contains the following skills:
| Skill | Description | |-------|-------------| | skill-from-masters | Create new skills based on proven methodologies from domain experts. | | search-skill | Search for existing skills from trusted marketplaces. | | skill-from-github | Learn from high-quality GitHub projects and create skills based on that knowledge. |
skill-from-masters
When you want to create a new skill based on expert methodologies:
- 3-layer search: local database β web experts β primary sources
- Finds golden examples and anti-patterns
- Cross-validates across multiple experts
- Hands off to skill-creator for final generation
Example:
You: "Help me create a skill for user interviews"
β Finds: Rob Fitzpatrick (The Mom Test), Steve Portigal, Nielsen Norman Group
β You select which methodologies to incorporate
β Generates skill with those principles encoded
search-skill
When you want to find an existing skill instead of creating one:
- Searches only 5 trusted sources (no random internet results)
- Tier-based priority: official β curated β aggregators
- Filters out low-quality results (stars < 10, outdated, no SKILL.md)
- Security checks for suspicious code patterns
Example:
You: "I need a skill for frontend design, automated testing, and code review"
β Searches: anthropics/skills, ComposioHQ, travisvn, skills.sh, skillsmp.com
β Returns: frontend-design (official), webapp-testing (official), code-review-excellence (26k stars)
skill-from-github
When you want to learn from a GitHub project and turn that knowledge into a skill:
- Search GitHub for quality projects (stars > 100, actively maintained)
- Present options and wait for your confirmation
- Deep dive into selected project (README, source code, examples)
- Summarize what it learned, then create skill via skill-creator
Example:
You: "I want to convert images to ASCII art"
β Searches GitHub, finds: ascii-image-converter (3.1k stars), RASCII (224 stars)
β You select ascii-image-converter
β Learns: brightness-to-character mapping, aspect ratio handling, color techniques
β Creates skill encoding that knowledge (not just wrapping the tool)
Key difference: This skill encodes the knowledge from projects, so the skill works even without the original tool installed.
File Structure
skill-from-masters/
βββ skill-from-masters/
β βββ SKILL.md # Core skill: create from expert methodologies
β βββ references/
β βββ methodology-database.md # Curated expert frameworks
β βββ skill-taxonomy.md # 11 skill type categories
βββ skills/
β βββ search-skill/
β β βββ SKILL.md # Search existing skills from trusted sources
β βββ skill-from-github/
β βββ SKILL.md # Learn from GitHub projects
βββ README.md
βββ LICENSE
βββ .gitignore
Quality Checklist
Before finalizing any skill, this skill verifies:
- [ ] Searched beyond the local database
- [ ] Found primary sources, not just summaries
- [ ] Found golden examples of the output
- [ ] Identified common mistakes to avoid
- [ ] Cross-validated across multiple experts
- [ ] Encoded specific, actionable steps (not vague principles)
Contributing
Contributions welcome! Especially:
- Adding new domains and experts to the methodology database
- Improving framework descriptions with source links
- Sharing examples of skills created with this approach
Please:
- Fork the repository
- Create a feature branch
- Submit a pull request
License
MIT License β feel free to use, modify, and distribute.
Philosophy: Quality isn't written. It's selected.
Pros
- Utilizes expert methodologies for skill creation
- Cross-validates information for reliability
- Includes a comprehensive methodology database
Cons
- Dependent on the availability of skill-creator
- May require internet access for full functionality
- Learning curve for new users unfamiliar with methodologies
Related Skills
pytorch
SβIt's the Swiss Army knife of deep learning, but good luck figuring out which of the 47 installation methods is the one that won't break your system.β
agno
SβIt promises to be the Kubernetes for agents, but let's see if developers have the patience to learn yet another orchestration layer.β
nuxt-skills
SβIt's essentially a well-organized cheat sheet that turns your AI assistant into a Nuxt framework parrot.β
Disclaimer: This content is sourced from GitHub open source projects for display and rating purposes only.
Copyright belongs to the original author GBSOSS.
