vellum-user-facing-copy
This skill reviews user-facing text across Vellum Assistant projects, including documentation, CLI output, UI strings, and release notes. Use it when editing any content that end users or maintainers may read, ensuring consistent terminology (favoring "assistant" over internal terms like "daemon"), removing personal data from examples, keeping error messages clear and actionable, and verifying that documented features are generally available rather than feature-flagged or in rollout phases.
git clone --depth 1 https://github.com/vellum-ai/vellum-assistant /tmp/vellum-user-facing-copy && cp -r /tmp/vellum-user-facing-copy/.cursor/skills/vellum-user-facing-copy ~/.claude/skills/vellum-user-facing-copySKILL.md
# Vellum User-Facing Copy ## Terminology Use "assistant" in user-facing text. "Daemon" is an internal implementation detail and should only appear in internal code, internal comments, file paths, or architecture explanations intended for maintainers. When unsure, ask: would a user ever read this? If yes, say "assistant". ## Generic Examples Never include real personal data in examples, fixtures, tests, docs, or commit messages. Use: - Names: `Alice`, `Bob`, `Example User` - Emails: `user@example.com`, `alice@example.org` - Phone numbers: `555-0100` through `555-0199` - IDs: `user-123`, `org-abc`, `conv-xyz` Avoid real names, personal emails, real phone numbers, account IDs, tokens, or private workspace paths. ## Release Notes There is currently no release-note surfacing mechanism — the workspace-bulletin feature was removed. Do not add new release-note workspace migrations; the historical set is frozen. ## Error Messages Good user-facing errors: - explain what failed - avoid exposing internals or secrets - say what the user can do next when there is a clear action - use consistent product terminology Avoid stack traces, implementation-only vocabulary, and ambiguous "something went wrong" messages when a concrete cause is available. ## Review Workflow 1. Identify text users may read. 2. Check terminology, privacy, and clarity. 3. Check whether the copy implies unavailable or flagged behavior. 4. Preserve technical precision while removing internal jargon. 5. Recommend tests or snapshots when copy is part of a stable interface.
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