Documentation
Technical Documentation People Can Follow
Turn a feature or process into docs with a goal, prerequisites, numbered steps and failure notes.
The Prompt
technical-documentation-people-can-follow.md
You are a technical writer. Document so a new teammate can succeed without Slack. What to document: {{thing}} Audience: {{audience}} How it currently works: {{notes}} Stack / tools: {{stack}} Write: 1. Title and one-sentence purpose 2. Who this is for / not for 3. Prerequisites 4. Numbered steps (imperative voice, one action each) 5. Expected result after the last step 6. Troubleshooting: 3 likely failures and the fix 7. Open questions from my notes that a reviewer must confirm Do not invent UI labels. If a click path is unclear, mark it as [confirm in product].
Negative prompt
Included when you copy the prompt
Do not invent UI labels or click paths - mark unclear steps [confirm in product]. Do not skip prerequisites, expected results, or troubleshooting. Do not write marketing fluff. Do not assume Slack tribal knowledge.
Fill in your details below - this prompt updates as you type, then copy it.
Fill in your details
0 of 4 filled. Preview updates as you type - then copy the finished prompt (negative prompt included when present).
technical-documentation-people-can-follow.md
Prompt preview
You are a technical writer. Document so a new teammate can succeed without Slack. What to document: {{thing}} Audience: {{audience}} How it currently works: {{notes}} Stack / tools: {{stack}} Write: 1. Title and one-sentence purpose 2. Who this is for / not for 3. Prerequisites 4. Numbered steps (imperative voice, one action each) 5. Expected result after the last step 6. Troubleshooting: 3 likely failures and the fix 7. Open questions from my notes that a reviewer must confirm Do not invent UI labels. If a click path is unclear, mark it as [confirm in product].
Examples
Example input
thing: Rotate the staging Stripe webhook signing secret audience: Backend engineers new to the payments repo notes: Secret lives in 1Password "Payments Staging"; update STRIPE_WEBHOOK_SECRET in Render staging env; redeploy payments-api; send a test event from Stripe CLI; verify 200 in Render logs. Unclear: exact Render service name in the UI. stack: Stripe, Render, 1Password, payments-api (Node)
What you should get
Purpose + audience, prerequisites (1Password access, Stripe CLI), numbered imperative steps with [confirm in product] on the Render service name, expected 200 in logs, three troubleshooting fixes, and open questions for a reviewer - no invented UI labels.
When to use this prompt
Use it when
- You need help with engineers.
- You need help with pms.
- You need help with support teams.
Skip it when
- You only need a one-line ask with no constraints, format, or context.
- You cannot supply the fill-in details the template asks for.
- A different category or tool-specific workflow fits the job better.
How to get a good result
Done when
Purpose + audience, prerequisites (1Password access, Stripe CLI), numbered imperative steps with [confirm in product] on the Render service name, expected 200 in logs, three troubleshooting fixes, and open questions for a reviewer - no invented UI labels.
Common mistakes
- Leaving thing, audience, notes vague - the model then invents placeholders.
- Asking ChatGPT, Claude, or Cursor for a shorter answer after a long structured prompt - that throws away the format rules.
- Stopping when the first draft appears instead of checking it against the success criteria below.
FAQ
- What do I fill in before I copy this prompt?
- Replace these placeholders with your details: thing, audience, notes, stack. Required fields are marked on the page. The prompt text updates as you type.
- Which AI tools is this prompt written for?
- It works best with ChatGPT, Claude, Cursor. Copy the filled prompt and paste it into the tool you already use.
- What should a good result look like?
- Purpose + audience, prerequisites (1Password access, Stripe CLI), numbered imperative steps with [confirm in product] on the Render service name, expected 200 in logs, three troubleshooting fixes, and open questions for a reviewer - no invented UI labels.
- What are common mistakes with this prompt?
- Leaving thing, audience, notes vague - the model then invents placeholders. Asking ChatGPT, Claude, or Cursor for a shorter answer after a long structured prompt - that throws away the format rules. Stopping when the first draft appears instead of checking it against the success criteria below.
Best for
- Engineers
- PMs
- Support teams
Related Prompts
More prompts like this — same topic and style.