0
Generate a meta-prompt that produces well-structured prompts for a category of task
⁂auto-checked, 4 days oldAauraNovice
The prompt
Write a meta-prompt: a prompt whose job is to generate other prompts for the task category task_category. This isn't a single-use prompt, it's a generator, so it needs to ask the right clarifying questions and produce a properly structured output prompt every time. Requirements:
1. The meta-prompt must first gather the information it needs to write a good prompt for this category (what specifically varies task to task within this category, e.g. for 'code review prompts', that's language, focus area, severity scheme) by asking targeted questions, not by guessing defaults silently.
2. It must encode the structural best practices for prompts in this category (e.g. for eval-writing prompts: always require pass/fail criteria over vague quality scores) as a template the generator follows, not leave structure to chance each time.
3. It must include a self-check step: after drafting the prompt, review it against a short checklist (does it have clear success criteria, does it use variable placeholders correctly, is it free of ambiguous instructions) before presenting the final version.
4. Give me the actual meta-prompt text, then demonstrate it once by generating an example prompt for a specific instance of task_category.
Task category: task_category
What tends to vary across instances of this category: variation_factors
Where it has been run
| Model | Version | People | Broke | Auto | Last |
|---|---|---|---|---|---|
| Claude | Haiku 4.5 | 0 | 0 | 1/1 | 4 days ago |
Example output
Meta-prompt (for generating SQL-query-review prompts): 'Before writing the review prompt, ask: (1) which SQL dialect, (2) is performance or correctness the primary review focus, (3) should the output be a rewritten query or just findings. Then draft a prompt that: requires the reviewer to quote the specific line of SQL for each finding, requires severity classification, and requires an explanation of the execution-plan reasoning if performance is the focus. Self-check before presenting: does the drafted prompt have a way to distinguish severity levels, does it specify output format, does every {{variable}} have a one-line description.'
Demonstration for 'PostgreSQL, correctness-focused, findings only': generated prompt requires: dialect-specific syntax awareness (Postgres-specific functions), a findings table with columns Line/Issue/Why-it's-wrong/Fix, and an explicit instruction not to suggest performance optimizations since correctness was specified as the sole focus, keeping scope tight rather than defaulting to a generic 'review this SQL' prompt that would drift into performance commentary unasked.
0 comments
Sign in to comment or report what this prompt did for you.
Sign inNo comments yet. Run the prompt and report what you got.