GitHub - wonsukchoi/domain-experts: all human experts into AI agents · GitHub
/" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
wonsukchoi
domain-experts
Public
Notifications<br>You must be signed in to change notification settings
Fork
Star
main
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>4 Commits<br>4 Commits
roles
roles
CONTRIBUTING.md
CONTRIBUTING.md
LICENSE
LICENSE
README.md
README.md
TEMPLATE.md
TEMPLATE.md
View all files
Repository files navigation
Domain Experts
All human experts into AI agents.
Open source, crowd-sourced library of job role definitions — written from first principles by (or with review from) real practitioners — structured so any AI agent can load one and act as that domain expert.
Why
LLM agents are generalists. Ask one to "think like a CFO" or "review this like a senior backend engineer" and you get a shallow imitation. This repo is an attempt to fix that by crowdsourcing the actual mental models, decision frameworks, heuristics, and blind spots that real practitioners in a role use — not job-description fluff.
Each role is written as a self-contained skill file (SKILL.md) that an AI agent (Claude Code, or any agent framework that supports skill/tool-style context injection) can load to adopt that role's reasoning process.
How it works
Every role lives in roles//SKILL.md.
Roles follow the schema in TEMPLATE.md: identity, first-principles core, mental models, decision frameworks, tools/methods, communication style, common failure modes, and sources.
Anyone can open a PR to add a new role, or improve an existing one. Practitioners with real experience in the role are especially welcome — call this out in your PR.
Quality bar: prefer how an expert actually thinks and decides over generic responsibility lists you could get from a job posting.
Current roles
Role<br>Path
Software Engineer (Backend)<br>roles/software-engineer/SKILL.md
Product Manager<br>roles/product-manager/SKILL.md
Financial Analyst<br>roles/financial-analyst/SKILL.md
UX Designer<br>roles/ux-designer/SKILL.md
Lawyer (Contracts / Commercial)<br>roles/lawyer-contracts/SKILL.md
Marketing Strategist<br>roles/marketing-strategist/SKILL.md
Sales Account Executive (B2B)<br>roles/sales-account-executive/SKILL.md
Data Scientist<br>roles/data-scientist/SKILL.md
HR / People Manager<br>roles/hr-people-manager/SKILL.md
Using a role with an agent
Point your agent (e.g. Claude Code's Skill tool, or any system prompt injection) at the relevant SKILL.md. The frontmatter (name, description) is written so agent harnesses can auto-match a role to a task; the body is the actual expert reasoning context.
Contributing
See CONTRIBUTING.md. Short version: pick a role (new or existing), fill in TEMPLATE.md's sections with real first-principles substance, open a PR.
License
MIT — see LICENSE.
About
all human experts into AI agents
Resources
Readme
License
MIT license
Contributing
Contributing
Uh oh!
There was an error while loading. Please reload this page.
Activity
Stars
stars
Watchers
watching
Forks
forks
Report repository
Releases
No releases published
Packages
Uh oh!
There was an error while loading. Please reload this page.
Contributors
Uh oh!
There was an error while loading. Please reload this page.
You can’t perform that action at this time.