gbsoss/skill-from-masters

Stand on the shoulders of giants — Create AI skills built on proven methodologies from domain experts.

726 stars81 forksUpdated Jan 24, 2026
npx skills add gbsoss/skill-from-masters

README

Skill From Masters

Stand on the shoulders of giants — 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.

License: MIT


Why This Skill?

The hard part of creating a skill isn't the format — 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:
   ├── Checks local methodology database
   ├── Searches web for additional experts
   ├── Finds golden examples of great outputs
   ├── Identifies common mistakes to avoid
   └── 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

FeatureDescription
3-Layer SearchLocal database → Web search for experts → Deep dive on primary sources
Golden ExamplesFinds exemplary outputs to define quality bar
Anti-PatternsSearches for common mistakes to encode "don't do this"
Cross-ValidationCompares multiple experts to find consensus and flag disagreements
Quality ChecklistVerifies completeness before generating

Methodology Database

The skill includes a curated database covering 15+ domains:

DomainExample Experts
WritingBarbara Minto, William Zinsser, Amazon 6-pager
ProductMarty Cagan, Teresa Torres, Gibson Biddle
SalesNeil Rackham (SPIN), Challenger Sale, MEDDIC
HiringLaszlo Bock, Geoff Smart, Lou Adler
User ResearchRob Fitzpatrick, Steve Portigal, JTBD
EngineeringMartin Fowler, Robert Martin, Kent Beck
LeadershipKim Scott, Ray Dalio, Andy Grove
NegotiationChris Voss, Fisher & Ury
StartupsEric Ries, Paul Graham, YC
Decision MakingJeff 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

  1. Download the skill-from-masters folder
  2. 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:

SkillDescription
skill-from-mastersCreate new skills based on proven methodologies from domain experts.
**[search-skill](skills/search-skill/SKILL

...

Read full README

Publisher

gbsossgbsoss

Statistics

Stars726
Forks81
Open Issues0
LicenseMIT License
CreatedJan 8, 2026