transform

Transform data across JSON, YAML, and CSV with explicit field mappings and provenance tracking.

4|1|Updated Jan 24, 2026

Search Tags:#validation #schema #data #provenance #conversion #mapping #transform

Ready to run

npx skills add https://github.com/synaptiai/agent-capability-standard --skill transform

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: transform
Source: https://github.com/synaptiai/agent-capability-standard/tree/main/skills/transform
Command: npx skills add https://github.com/synaptiai/agent-capability-standard --skill transform

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transform data between formats and schemas while preserving a trace of what is kept, changed, or dropped, enabling auditable data workflows.

Core Features & Use Cases

Deterministic transformations with explicit provenance
Schema conformance validation and loss tracking
Field mapping and nested structure handling for JSON, YAML, CSV

Quick Start

Provide a source payload, a target schema, and optional mappings to produce a proven, schema-compliant transformed output.

Frequently Asked Questions about transform

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert JSON to CSV while tracking lost data?▼

To convert JSON to CSV while tracking lost data, provide a source payload, target schema, and optional mappings to generate deterministic output that documents any information lost during the transformation.

What is data provenance in schema conversion?▼

Data provenance in schema conversion is the explicit trace of what information is preserved, modified, or dropped when transforming structured data between formats like JSON and YAML, enabling auditable workflows.

How do I map nested JSON fields to a flat schema?▼

You map nested JSON fields to a flat schema by providing explicit field mappings alongside the target schema, ensuring the transformation returns deterministic output with validation results and evidence anchors.

Does schema validation work with YAML and CSV conversions?▼

Schema validation works with YAML and CSV conversions by applying schema conformance checks and loss tracking across structured data, returning deterministic output that conforms to the target schema.

What happens to dropped fields during a data format conversion?▼

Dropped fields during a data format conversion are explicitly documented in the provenance trace, allowing you to audit what information was modified or lost when applying explicit field mappings to the target schema.

Can I transform nested objects between YAML and JSON deterministically?▼

You can transform nested objects between YAML and JSON deterministically by applying explicit field mappings to produce schema-compliant output with attached validation results and full provenance tracking.