Data Transformation Prompt
The transformation log creates an audit trail for every change. Flagging assumptions prevents silent data corruption when the rules do not cover every case.
Transform the following data from {{source_format}} to {{target_format}}.\n\nInput data:\n{{input_data}}\n\nTransformation rules:\n{{transformation_rules}}\n\nProcess:\n1. Parse the input data and identify all fields\n2. Apply each transformation rule in order\n3. Validate the output matches the target format\n4. Report any data that could not be transformed (with reasons)\n\nOutput requirements:\n- Return the transformed data in the target format\n- Include a transformation log: [field] [original] [transformed] [rule applied]\n- Flag any values that required assumptions or best-guess interpretation\n- Count: total records, successfully transformed, failed, skipped\n\nIf any transformation rule is ambiguous, state your interpretation before applying it.
Variables to customize
Why this prompt works
The transformation log creates an audit trail for every change. Flagging assumptions prevents silent data corruption when the rules do not cover every case.
Save this prompt to your library
Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.
Related prompts
Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.
Tool Selection AgentThe ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.
Prompt CompressorExplicitly requiring all functional requirements to be preserved prevents the model from over-compressing and losing critical instructions.
Memory Management AgentExplicit memory read/write instructions create agents that improve over time. Categorization keeps memories organized, and the deduplication rule prevents context bloat.