Write a skill.
Stop explaining the same task to AI from scratch. Turn the way you want it done into a reusable skill, then try it on real work and improve it.
Try it now
Copy the prompt into your AI tool of choice, then answer its questions as they come.
Paste it into any AI chat to start. For most people, this is all you need.
Everything on this page in one paste: the prompt plus the full plan, every step and what to check. Use it for longer moves, to plan ahead, to share with a colleague, or if your AI can't open links.
How it goes
What the AI will do
- Guide you through creating a reusable skill for work you repeat: choose a useful task, write the skill for your AI environment, and try it on an example.
What to have ready
- A description of work you repeat or often explain to AI; the AI will help you find a useful starting point.
- An example task to try.
Where you come in
- Agree on the task before the AI writes the skill.
- Try invoking it yourself when possible, share what happened, and help refine it.
What you'll get
A skill for a recurring task, instructions for using it again, and an account of what was tested or which installation or invocation step remains.
You're done when
You have a skill for a task you actually do, know how to use it again, and have seen it tried on an example—or know exactly what installation step remains.
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result. ### Start with the activity and the user's context Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear. Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them. ### Check the capabilities needed for this work Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit. When useful access is missing: - Explain what you cannot reach and how that material would help. - Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot. - If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response. - Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available. ### Ask focused questions and respect the answers Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful. Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements. ### Keep evidence and independent contributions distinct Distinguish evidence, inference, and missing information. Check your work against the source material. Use independent agents when your system actually supports delegation and independent investigation or review would improve the work: - Give each agent a bounded brief and the context appropriate to its role. - Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations. - Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately. ### Produce, check, and revise the result Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them. Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result. Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized. Help me create a skill for a recurring task. Guide me through the process using the capabilities and documented skill format of this environment. ### 1. Find out how skills work here. - Inspect this AI environment and its available capabilities. - Identify whether it supports reusable skills, how they are created, and where they are saved. - Check relevant current documentation when local information is insufficient. - Explain a skill in plain language as reusable instructions and, where supported, supporting resources that help the AI perform a task consistently. - Explain how it would be invoked here. - If native skills are unsupported, identify a feasible environment for the skill and explain the difference between an installable skill and reusable prompt text. ### 2. Find a useful task with me. Interview me about work I repeat or repeatedly explain to AI. Ask one focused question at a time. Look for a task where recurring instructions, examples, or a known output would help. Propose a suitable candidate from my answers and clarify what starts it, what inputs it needs, what it should do, and what a good result looks like. Offer to write the skill and wait for my agreement. ### 3. Write and try the skill. - After I agree, use the actual skill format supported by the chosen environment. - Write the instructions and any needed supporting files. - Make the trigger, inputs, method, handling of missing information, and intended output clear enough for an AI without this conversation. - Save the skill in the appropriate supported location if permitted; otherwise provide the files and precise installation steps. Try the skill on a representative example using available capabilities. Compare the result with the outcome we agreed on and correct problems. Then show me how to invoke it and invite me to try it myself on a task I would actually use it for. If installation or invocation requires an action from me, guide me through that action and verify afterward where possible. Ask me to share the result or describe what happened and what needs improving; wait for my response before evaluating my trial. Inspect the actual output or behavior where accessible, resolve observed problems, and repeat the relevant check or ask me to retry when only I can perform it. If I cannot try it yet, provide the files and exact remaining installation or invocation step. Finish with instructions for using it again, distinguishing the AI’s trial, my reported experience, checks you could directly verify, and anything still untested. Do not describe the skill as installed or successfully invoked unless that actually happened. These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
View full AI instructions
Write a skill.
What the AI will do
- Guide you through creating a reusable skill for work you repeat: choose a useful task, write the skill for your AI environment, and try it on an example.
What you can provide
- A description of work you repeat or often explain to AI; the AI will help you find a useful starting point.
- An example task to try.
Where you'll take part
- Agree on the task before the AI writes the skill.
- Try invoking it yourself when possible, share what happened, and help refine it.
What you'll get
A skill for a recurring task, instructions for using it again, and an account of what was tested or which installation or invocation step remains.
Activity context
Stop explaining the same task from scratch. Work with your AI to turn something you do regularly into a reusable skill, then try it on a real example and refine it together.
For the user
Copy the instructions into your AI chat, or give it this page’s URL. If the AI cannot open the page, paste the full instructions instead.
The AI will ask about work you repeat and help you choose a useful task. Once you agree, it will write the skill and try it on an example. You’ll try using it yourself, tell the AI what needs improving, and learn how to use it again.
Guidance for the AI
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.
Start with the activity and the user's context
Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.
Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.
Check the capabilities needed for this work
Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.
When useful access is missing:
- Explain what you cannot reach and how that material would help.
- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.
Ask focused questions and respect the answers
Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.
Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.
Keep evidence and independent contributions distinct
Distinguish evidence, inference, and missing information. Check your work against the source material.
Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:
- Give each agent a bounded brief and the context appropriate to its role.
- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.
Produce, check, and revise the result
Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.
Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.
Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.
Your AI prompt
Help me create a skill for a recurring task. Guide me through the process using the capabilities and documented skill format of this environment.
1. Find out how skills work here.
- Inspect this AI environment and its available capabilities.
- Identify whether it supports reusable skills, how they are created, and where they are saved.
- Check relevant current documentation when local information is insufficient.
- Explain a skill in plain language as reusable instructions and, where supported, supporting resources that help the AI perform a task consistently.
- Explain how it would be invoked here.
- If native skills are unsupported, identify a feasible environment for the skill and explain the difference between an installable skill and reusable prompt text.
2. Find a useful task with me.
Interview me about work I repeat or repeatedly explain to AI. Ask one focused question at a time. Look for a task where recurring instructions, examples, or a known output would help. Propose a suitable candidate from my answers and clarify what starts it, what inputs it needs, what it should do, and what a good result looks like. Offer to write the skill and wait for my agreement.
3. Write and try the skill.
- After I agree, use the actual skill format supported by the chosen environment.
- Write the instructions and any needed supporting files.
- Make the trigger, inputs, method, handling of missing information, and intended output clear enough for an AI without this conversation.
- Save the skill in the appropriate supported location if permitted; otherwise provide the files and precise installation steps.
Try the skill on a representative example using available capabilities. Compare the result with the outcome we agreed on and correct problems. Then show me how to invoke it and invite me to try it myself on a task I would actually use it for. If installation or invocation requires an action from me, guide me through that action and verify afterward where possible.
Ask me to share the result or describe what happened and what needs improving; wait for my response before evaluating my trial. Inspect the actual output or behavior where accessible, resolve observed problems, and repeat the relevant check or ask me to retry when only I can perform it. If I cannot try it yet, provide the files and exact remaining installation or invocation step.
Finish with instructions for using it again, distinguishing the AI’s trial, my reported experience, checks you could directly verify, and anything still untested. Do not describe the skill as installed or successfully invoked unless that actually happened.
Done when
You have a skill for a task you actually do, know how to use it again, and have seen it tried on an example—or know exactly what installation step remains.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.