0
Extract a reusable template from a one-off prompt that worked well
⁂auto-checked, 4 days oldAauraNovice
The prompt
I wrote a prompt for a specific task and it worked really well. Help me generalize it into a reusable template with variable placeholders, without over-abstracting it into something so generic it loses what made it work. Given the original prompt and the specific task it solved:
1. Identify which parts are genuinely task-specific (should become variables) versus which parts are structural (the reasoning steps, the output format requirements, the constraints) and should stay fixed since they're what made this prompt effective, not incidental wording.
2. For each variable you introduce, write a one-line description of what should go there and one example value, so future users of the template aren't guessing.
3. Explicitly call out any part of the original prompt that's doing real work but is easy to accidentally strip out during templating (a specific constraint, an example, an edge-case handling instruction) - these are the parts generic templates usually lose.
4. Test the template mentally against one different-but-similar task to see if it still holds up, and note if any part needs adjustment for that case, rather than assuming genericization is complete on the first pass.
Original working prompt: original_prompt
What task it solved: task_it_solved
Where it has been run
| Model | Version | People | Broke | Auto | Last |
|---|---|---|---|---|---|
| Claude | Haiku 4.5 | 0 | 0 | 1/1 | 4 days ago |
Example output
Structural parts to keep fixed: the requirement to state assumptions explicitly before answering, the 3-tier severity classification, and the rule against inventing information not present in the source, these are the mechanisms that made the original prompt reliable, not just its topic.
Variables introduced: `{{domain}}` (e.g. 'contract clauses'), `{{source_document}}` (the text to analyze), `{{severity_labels}}` (e.g. 'critical/moderate/minor', defaults to what the original used if not specified).
Easy-to-lose part: the original prompt has a specific line, 'if a clause is ambiguous rather than clearly problematic, say so instead of forcing it into a severity tier', this is doing real work preventing false-positive flagging, and it's the kind of nuance that gets cut when someone templates a prompt down to 'analyze X and flag issues.' Kept it verbatim, just swapped 'clause' for a `{{unit_of_analysis}}` variable.
Tested against a different task (reviewing marketing claims for substantiation instead of contract clauses): template holds, only needed to adjust the severity labels since 'critical/moderate/minor' maps less naturally to unsubstantiated-claims review than to 'unsupported/overstated/fine', worth exposing that as a variable with a task-appropriate default rather than a fixed value.
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.