Prompts

Type / followed by the prompt name in Copilot Chat to run one. Inputs in the table are asked for when you run the prompt, or you can pass them inline, for example /answer-business-questions label=local-baseline.

Prompt	Runs with agent	Inputs	What it does
/add-core-measures	model-improver	none	Add the 12 core measures, with these exact names, definitions, format strings, and display folders, to the Prescription Fill table, plus the Fill Type column.
/answer-business-questions	question-tester	`label`	Answer the five business questions against the current model, save the run file with the given label, and grade it.
/assess-model	model-assessor	`focus`	Assess the semantic model against the team conventions and AI-readiness checklist and write out/assessment.md.
/compare-question-runs	question-tester	`before`, `after`	Compare two graded question runs, write out/question-comparison.md, and explain which model changes caused each difference.
/create-cloud-agent-issue	Agent (built in)	`change`	Draft a model-change issue that Copilot cloud agent can pick up and finish without further questions.
/fix-relationships-and-date-table	model-improver	none	Fix the model’s relationships and Date table so time intelligence works, including single-direction many-to-one joins, a marked date table, sort-by columns, and auto date/time turned off.
/improve-names-and-descriptions	model-improver	none	Rename tables and columns to business names, add descriptions, hide keys, set summarization and display folders, then rebind the report.
/new-lab-page	lab-author	`lab`	Draft a new lab page for the lab site from the lab template and the checks in lab/checks.yaml (maintainers).
/review-model-pr	model-reviewer	`base`	Review semantic model and report changes on this branch before opening a pull request.
/write-ai-prep-drafts	model-improver	none	Draft Prep data for AI artifacts (AI instructions, AI data schema, synonyms, verified answers) in fabric/ai-prep/ and set the model flags that go with them.