Provenance Report Skill for ChatGPT: Measure Artifact Coverage and Broken Links
Reconcile supplied artifacts with provenance records. Report coverage by entity type or contributor and identify unresolved relationships or missing back-references.
中文Install in ChatGPT
Requires a ChatGPT workspace where you can create skills. This is a text adaptation of the pinned GitHub source.
- Review the inputs and outputs in the pinned agentic/code/frameworks/sdlc-complete/skills/provenance-report/SKILL.md.
- In ChatGPT, open Plugins, Skills, Create, and Create with editor.
- Write the skill rules using the workflow described here. Provide artifact IDs, types, provenance relationships, and the reporting window.
- Save the skill and check the fictional example in a new chat.
Example task
A fictional inventory contains requirement D1, test T1, and release note R1. D1 and T1 have records, and T1 points to archived spec D0, which was not supplied. Draft a coverage table.What to check
Show two of three tracked and list R1 as untracked. Separately flag the unresolved T1-to-D0 reference and record the artifact types and scope.
Original SKILL.md on GitHub · Updated
Frequently asked question
Does a provenance record guarantee a complete chain?
Coverage measures whether a record exists. Chain health also depends on references resolving and required reverse relationships being present. Report both.