id = "data-pipeline"
name = "Data Pipeline"
description = "ETL pipeline that extracts data from a source, transforms it into a target format, and validates the output for completeness and correctness."
category = "data"
tags = ["etl", "data", "pipeline", "transform"]

[i18n.zh]
name = "数据流水线"
description = "ETL 流水线，从数据源提取数据，转换为目标格式，并验证输出的完整性和正确性。"

[[parameters]]
name = "data_source"
description = "URL or file path to the data source"
param_type = "string"
required = true

[[parameters]]
name = "output_format"
description = "Desired output format (json, csv, markdown)"
param_type = "string"
required = false
default = "json"

[[steps]]
name = "extract"
prompt_template = "Extract raw data from the following source: {{data_source}}. Return the complete dataset without any transformation, preserving the original structure."

[[steps]]
name = "transform"
prompt_template = "Transform the following raw data into well-structured {{output_format}} format. Apply standard cleaning: trim whitespace, normalise dates to ISO-8601, remove duplicate rows, and convert empty strings to null.\n\nRaw data:\n{{extract}}"
depends_on = ["extract"]

[[steps]]
name = "validate"
prompt_template = "Validate the transformed data below for completeness and correctness. Check for: missing required fields, type mismatches, invalid date formats, out-of-range values, and referential integrity. Return a validation report with pass/fail status and any issues found.\n\nTransformed data:\n{{transform}}"
depends_on = ["transform"]