Onboard an AI agent Skill (SKILL.md)
- Setting up a new agent
- Handing over a recurring task
- Sharpening weak results
- What does this skill do?
- Builds an onboarding brief for an AI agent: measurable goal, context and rules, examples of good work and a feedback loop.
- What do you put in?
- Topic, goal and a few bullet points.
- What do you get?
- Onboarding brief with role and purpose
- SMART goal with a done criterion
- Context and rules
- Examples of good work
- Checklist for the feedback round
- Works in
- Claude, ChatGPT, Gemini, Microsoft 365 Copilot, Cursor and other assistants
Skill instructions
This is how the AI works with this skill. Copy it or add it to your assistant as a file.
- Ask about the task, who the result is for and how often it comes up.
- Write a SMART goal: specific, measurable, achievable, relevant and with a deadline or rhythm. Add how the agent can tell that it is finished.
- Collect the context: purpose, audience, tone, allowed sources and terms the agent must know.
- Record rules and limits: what the agent never does, when it asks back and which steps a person approves.
- Ask for one or two real examples of good work and describe what makes them good. If examples are missing, mark the spot with [add example].
- Plan the feedback loop: check first results against the goal, note deviations and adjust the instructions.
View full text
--- name: agent-onboarding description: "Creates an onboarding brief for an AI agent or assistant. Use before handing a recurring task to an agent." license: "Free to use, including at work; do not republish as your own collection. AI Compare Ninja terms of use." --- # Onboard an AI agent You help onboard an AI agent like a new colleague: with a goal that can be checked, the background it needs and examples of good work. ## Steps 1. Ask about the task, who the result is for and how often it comes up. 2. Write a SMART goal: specific, measurable, achievable, relevant and with a deadline or rhythm. Add how the agent can tell that it is finished. 3. Collect the context: purpose, audience, tone, allowed sources and terms the agent must know. 4. Record rules and limits: what the agent never does, when it asks back and which steps a person approves. 5. Ask for one or two real examples of good work and describe what makes them good. If examples are missing, mark the spot with [add example]. 6. Plan the feedback loop: check first results against the goal, note deviations and adjust the instructions. ## Output - Onboarding brief with role and purpose - SMART goal with a done criterion - Context and rules - Examples of good work - Checklist for the feedback round ## Rules - Invent no numbers, facts or examples; mark open points as [clarify]. - No credentials or passwords in the brief. - Sending, deleting and paying only with human approval. - Do not invent facts, figures, names, dates or commitments. If something is missing, write [missing: …] or ask. - Reply in the user's language unless asked otherwise. - Repeat only as much personal data as the task requires. - You deliver a draft. The decision and any sending stay with the human. Use: free, including at work · do not republish as your own collection · Source: AI Compare Ninja
As a file: Download (ZIP)
Install in Claude
- In Claude, open Settings and turn on “Code execution and file creation” under “Capabilities”.
- Go to “Customize” › “Skills”.
- Click “+”, then “Create skill” and “Upload a skill”.
- Choose the downloaded ZIP file. The skill appears in your list, where you can switch it on and off.
The ZIP file contains the folder “agent-onboarding” with the file SKILL.md, exactly as Claude expects it. Do not unzip it; upload it as is.
Claude Code: unzip the file into ~/.claude/skills/ (for you) or .claude/skills/ in your project.
Steps per Anthropic's help pages, as of October 2026. Menu names are from the English interface and may differ in other languages or after updates. On Team and Enterprise accounts an admin must allow skills. Sources: https://support.claude.com/en/articles/12512180-use-skills-in-claude · https://claude.com/docs/skills/how-to
Use it in ChatGPT, Gemini and Copilot
ChatGPT: in Business, Enterprise and Edu workspaces you upload the file as a skill if your admin allows it. Gemini app: skills can be uploaded as SKILL.md or ZIP. Microsoft 365 Copilot: upload it as your own skill in Cowork. Codex, GitHub Copilot and Cursor read skills from the project folder .agents/skills/. Anywhere else, paste the text as instructions into a ChatGPT or Claude project or at the start of a chat.
According to the vendors' help pages, October 2026. Availability depends on plan, admin settings, age and region. Sources: https://help.openai.com/en/articles/20001066-skills-in-chatgpt · https://support.google.com/gemini/answer/17094296 · https://learn.microsoft.com/en-us/microsoft-365/copilot/cowork/cowork-customize · https://developers.openai.com/codex/skills · https://code.visualstudio.com/docs/copilot/customization/agent-skills · https://cursor.com/docs/context/skills
Use, safety and notes
Text only, reviewed by us. This skill contains no scripts, no links and no calls to other services. It tells the AI not to invent anything and to leave the final decision to you.
AI results can be wrong or incomplete. Check them before you use or send them. Not legal, tax, financial or medical advice. No warranty.
Do not enter passwords, health, bank or ID data, or other people's personal data into AI tools. Whatever you enter is processed by the provider under its own terms.
You may use and adapt our skills freely, including at work. Please do not republish them as your own collection. We give no warranty for AI results; check them yourself. Terms of use