Build A Prompt Library
Turn useful back-and-forth conversations into reusable one-shot prompts.
Why Save Prompts
The first useful answer often takes a few turns. You clarify the date range, ask for SKU instead of only ASIN, change the sort order, and ask the model to include source caveats. Once that workflow works, turn it into a reusable prompt instead of rediscovering it next week.
Save prompts in Claude Projects, Notion, Google Docs, internal SOPs, shared runbooks, or support playbooks. The storage system matters less than making the workflow reusable by changing dates, ASINs, SKUs, campaigns, keywords, or marketplaces.
Reverse Prompt
Paste this after a successful conversation to compress the workflow into a one-shot prompt.
We got to the answer I wanted after several back-and-forth steps with Agent Central. Turn this into a reusable one-shot prompt I can save in my prompt library. The prompt should: - Ask for the same final result directly - Include the right date range behavior - Specify the output format - Ask for SKU/product name instead of only ASIN when relevant - State which data source or caveats should be included - Be reusable by changing dates, ASINs, SKUs, campaigns, or marketplaces
Prompt Library Template
Use Agent Central to [job to be done]. Date range: - [yesterday / last 7 completed days / exact dates] Scope: - Marketplace: - ASINs, SKUs, campaigns, keywords, or account total: Return format: - [table / bullets / executive summary / CSV-style rows] - Include: - Sort by: Required context: - Data source: - Freshness or caveats: - Exact records to inspect next:
What To Capture
- The business question the prompt answers.
- The date range behavior: exact dates, yesterday, or completed periods.
- The identifiers the workflow needs: SKU, product title, ASIN, campaign, keyword, or marketplace.
- The output format: table, summary, action list, or meeting-ready takeaways.
- The required source, freshness caveat, or reporting limitation.
Continue Reading
Next: Ask For The Shape Of The AnswerTell the agent the exact table, sorting, caveats, and takeaways you need.
Related Best Practices
Give each agent or job the smallest useful Agent Central tool surface.
Share scoped keysCreate separate keys for teammates, contractors, and write-enabled workflows.
Ask for answer formatTell the agent the exact table, sorting, caveats, and takeaways you need.
Dates, metrics, sourcesAvoid ambiguous Amazon sales numbers by specifying dates, metrics, grouping, and freshness.