Task-Based Tutorial Writer

Writes a how-to tutorial around one testable end state: numbered steps with expected output after each, prerequisite checks, and a troubleshooting table.

Fill in the blanks

Prompt variables

4 variables detected — fill them and Copy inserts your values (0/4 filled).

Write a step-by-step tutorial that takes a reader from zero to one specific, verifiable end state. Not a concept explainer — a recipe that works. **End state the reader achieves:** {{end_state}} **Reader's starting point and skill level:** {{audience}} **Tools/stack involved:** {{stack}} **My working notes (commands, gotchas, real error messages I hit):** {{notes}} Structure: 1. **"What you'll have at the end"** — 2 sentences plus the single command/action that proves it worked and its expected output. 2. **Prerequisites** — as CHECKS, not claims: for each one, the command to verify it and the output that means "you're good" (e.g. `node -v` → "v20 or higher"). Exact versions where they matter. 3. **Steps** — numbered, each with: - One action (if a step contains "and", split it) - The exact command or code, copy-paste ready — no placeholder mush like `<your-thing-here>` without a concrete example value beside it - **What you should see** after the step, verbatim where possible. This is mandatory: readers use it to know they're still on the path. 4. **Checkpoint** every 3-5 steps — a way to verify cumulative progress, so a reader who went wrong knows within minutes, not at the end. 5. **Troubleshooting table** — the likely failures (use my notes' real errors first): symptom | cause | fix. No "make sure everything is configured correctly" non-fixes. 6. **Where to go next** — 2-3 concrete follow-ups, one sentence each. Voice: second person, imperative, zero fluff between steps. If my notes are missing something a step needs, write [GAP: what you need from me] rather than guessing.
Field notes

Comments (0)

LLM Atlas

A free map of prompts that actually work — tested on real models, starred by real people.

© 2026 LLM AtlasPrompts default to CC0 unless stated.