explaingit

swaylq/master-skill

15ShellAudience · developerComplexity · 2/5Setup · easy

TLDR

A shell-based skill for AI coding agents that automatically researches any industry and produces a reusable knowledge package capturing expert-level mental models, workflows, and terminology.

Mindmap

mindmap
  root((master-skill))
    What it does
      Industry research
      Knowledge packaging
      Source validation
    Outputs
      Skill file
      Bash scripts
      Sub-skills
    Use cases
      Domain expertise
      Agentic research
      Decision trees
    Audience
      AI agent users
      Developers
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Load the skill into an AI agent to give it senior-practitioner knowledge for a specific industry.

USE CASE 2

Generate bash scripts for running agentic research protocols on new questions in your field.

USE CASE 3

Distill knowledge from three prominent industry figures into separate sub-skills for persona-specific responses.

USE CASE 4

Use automated source quality checks to ensure research outputs cite primary, up-to-date references.

Tech stack

Shell

Getting it running

Difficulty · easy Time to first run · 30min

Requires Claude Code, Codex, or a compatible AI coding agent that supports skill loading, no external dependencies beyond bash.

In plain English

This repository is a skill for AI coding agents (Claude Code, Codex, and similar tools) that automatically researches an industry and produces a reusable knowledge package for that industry. You tell the agent which specific field you are in, and it spends 30 to 60 minutes running six parallel research tracks: finding the prominent figures in that field, mapping the tool landscape, documenting common workflows, identifying canonical reference materials, finding reliable information sources, and capturing the terminology and jargon specific to that industry. The output is a directory containing a skill file that, when loaded into any compatible AI agent, puts the agent into what the README describes as "the most senior person in this field" mode. The idea is that the agent does not just know facts about the industry but has internalized the mental models, decision rules, and working patterns that experienced practitioners actually use. The README gives examples showing the kind of responses this produces: instead of listing generic options, the agent identifies the real constraints and tradeoffs a practitioner would care about. Along with the main skill file, the process also generates a set of bash command-line scripts, one for running an agentic research protocol on a new question, others for specific decision trees and workflow walkthroughs. These scripts have no external dependencies and work on plain bash. The skill also optionally invokes a separate tool to distill three prominent individuals from the industry into their own sub-skills, so the agent can later respond from a specific person's perspective when asked. Source quality is checked with 16 automated rules. Primary sources (official documentation, the author's own writing, academic papers) are required. Content from certain aggregator sites is automatically rejected. Each source is dated, and sources older than 18 months are weighted less. The skill explicitly documents what it does not cover and which parts will go out of date fastest.

Copy-paste prompts

Prompt 1
Using the master-skill framework, research the [your industry] sector and produce a knowledge package covering key figures, tool landscape, common workflows, canonical references, and terminology.
Prompt 2
Load the generated skill file into Claude Code and ask: what would a senior [industry] practitioner prioritize when evaluating a new vendor offering [product]?
Prompt 3
Run the master-skill research protocol on [your question], then use the generated decision-tree bash script to walk through the analysis step by step.
Prompt 4
After generating a skill, invoke it from the perspective of [specific industry figure] and ask: how would this person approach [my specific problem]?
Open on GitHub → Explain another repo

← swaylq on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.