vellum-migration-checklist
The vellum-migration-checklist skill provides structured guidance for validating database migrations, workspace migrations, and release-note migrations in the Vellum Assistant codebase. Use this skill when creating, editing, reviewing, or testing any migration that modifies persisted data, database schemas, workspace file formats, or release documentation to ensure idempotency, proper registration, and comprehensive test coverage.
git clone --depth 1 https://github.com/vellum-ai/vellum-assistant /tmp/vellum-migration-checklist && cp -r /tmp/vellum-migration-checklist/.cursor/skills/vellum-migration-checklist ~/.claude/skills/vellum-migration-checklistSKILL.md
# Vellum Migration Checklist ## When A Migration Is Required Use a migration for shipped interfaces and persisted data: - DB schema changes, indexes, backfills, or persisted row shape changes. - Workspace file renames, moves, format changes, or namespace changes. - Stored config or data that existing installs must keep reading. Do not delete migration files. Migrations are append-only, even when their logic becomes obsolete. ## DB Migrations For DB migrations: 1. Add a new file under `assistant/src/persistence/migrations/`. 2. Make it idempotent and safe to retry after interruption. 3. Register it in the `migrationSteps` array in `assistant/src/persistence/steps.ts`. 4. Update schema modules if the runtime schema changed. 5. Add or update a focused `db-*migration*.test.ts` test. Check for ordering drift and never reorder existing migrations. ## Workspace Migrations For workspace migrations: 1. Add a new numbered file under `assistant/src/workspace/migrations/`. 2. Append it to `WORKSPACE_MIGRATIONS` in `assistant/src/workspace/migrations/registry.ts`. 3. Make the migration idempotent. 4. Add or update a focused `workspace-migration-*.test.ts` test. Never reuse or reorder existing migration IDs. ## Release Notes Migrations There is currently no release-note surfacing mechanism. The update-bulletin feature (workspace migrations appending to a workspace bulletin file, processed by a background conversation at daemon startup) was removed. Do not add new `0XX-release-notes-*` workspace migrations — the historical set is frozen by `workspace-release-notes-feature-flag-guard.test.ts`. If a release needs user-facing notes, design an explicit on-demand surfacing mechanism first. ## Verification Run the focused migration test first. Add package typecheck when migration exports, schema types, or registry wiring changed: ```bash cd assistant && bun test src/__tests__/workspace-migration-example.test.ts cd assistant && bun test src/__tests__/db-example-migrations.test.ts cd assistant && bunx tsc --noEmit ``` Replace example paths with the actual test files related to the change.
Set up, authenticate, and run external coding agents (Claude Code, Codex) via the Agent Client Protocol
Shop on Amazon and Amazon Fresh through your browser
Record and analyze API surfaces of web services
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use, or to edit an app they already built here. Do NOT reach for a ui_show dynamic_page to fake an artifact — build a real persistent app here. A one-off diagram, chart, or explainer that just accompanies an answer belongs to the visualize skill (ui_show visual), not an app. NOT for complex, multi-user, or shippable products — those go to a real project folder with a coding agent (see Scope below).
Drive a specific named macOS app via raw input bypassing the Accessibility tree
Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum primitives. Handles single-source and multi-source migrations with a unified, deduplicated inventory.
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready text for search, Q&A, and summarization without building a custom parsing pipeline.
Import conversation history from ChatGPT into Vellum