Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/ai-employee-onboarding-wizard
Stand up a production-ready AI employee operating system in one guided session. Outputs 7 ready-to-use files: IDENTITY.md, SOUL.md, AGENTS.md, USER.md, MEMORY.md, HEARTBEAT.md, TOOLS.md.
Passed 19 of 22 test cases with the skill, and 7 of 22 without it.
and 18 more in the full report
13 fixed6 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to start the AI onboarding wizard. What is the very first batch of questions you must ask me before proceeding to agent identity or tools?
| Checked | Without skill | With skill |
|---|---|---|
| asks for the human user's day-to-day role | Missed | Passed |
| asks for the human user's timezone | Missed | Passed |
The instructions your model reads when the skill loads.
Optimized for Claude Code, Cursor, GitHub Copilot, and any AI that accepts markdown instructions. Paste this SKILL.md into your AI's context or project instructions and run it immediately.
Most people set up AI agents with a vague system prompt and wonder why it acts generic. The difference between an AI that feels like a real team member and one that feels like a chatbot is the operating system underneath it.
This skill builds that operating system for you in one guided session. Seven production-ready files. No placeholders. No "fill this in later." Deployable immediately.
Detect from context or ask: "Quick setup, full OS build, or full build with team customization?"
| Mode | What you get | Best for |
|---|---|---|
quick | 3 core files: IDENTITY.md, AGENTS.md, USER.md | Fast standalone agent setup |
standard | All 7 files: full production-ready AI employee OS | New agent deploy, solo operator |
deep | All 7 files + role-specific variations + team deployment guide | Multi-agent setup, onboarding a team |
Default: standard — use quick for a fast single-agent setup. Use deep if deploying across a team or building a multi-agent system.
The AI must confirm all gates before generating any files.
GATE CHECK — Required Before Starting
======================================
[ ] Human's role/job confirmed (what they actually do day-to-day)
[ ] Agent's primary function defined (what is this AI employee's job?)
[ ] Timezone confirmed
[ ] Top 3-5 recurring tasks identified
[ ] Tools/integrations stack noted (even rough — Gmail, Notion, Slack, etc.)
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.