Scheduled Task Prompt
Comparing against previous runs catches drift and anomalies automatically. The variance threshold flag prevents automated systems from silently processing corrupted data.
You are executing a scheduled task that runs {{schedule}}.\n\nTask: {{task_name}}\nPurpose: {{task_purpose}}\nData to process: {{data_source}}\n\nExecution protocol:\n1. **Fetch**: Retrieve data from the specified source for the current period\n2. **Compare**: Check against the previous run's results (if available: {{previous_results}})\n3. **Process**: Apply the core task logic:\n {{processing_instructions}}\n4. **Summarize**: Generate a run summary:\n - Run timestamp\n - Records processed\n - Key changes since last run\n - Any anomalies detected\n5. **Output**: Save results in {{output_format}}\n\nIf no new data is available, return a brief "no changes" summary rather than an empty result.\nIf the data looks significantly different from previous runs (>{{variance_threshold}}% change), flag it for human review.
Variables to customize
Why this prompt works
Comparing against previous runs catches drift and anomalies automatically. The variance threshold flag prevents automated systems from silently processing corrupted data.
What you get when you save this prompt
Your workspace unlocks powerful tools to iterate and improve.
AI Optimization
One-click improvement with structure analysis and pattern suggestions.
Version History
Track every edit. Compare versions side-by-side with word-level diffs.
Folders & Tags
Organize your library with nested folders, tags, and drag-and-drop.
$ npm i -g @promptingbox/mcpUse Everywhere
Access prompts from Claude, Cursor, ChatGPT & more via MCP integration.
Your prompts, organized
Save, version, and access your best prompts across ChatGPT, Claude, Cursor, and more.