vellum-skill-authoring
This Claude Code skill guides the authoring and review of first-party Vellum skills within the vellum-assistant repository. Use it when creating or modifying skill files in the skills/ directory, writing SKILL.md documentation, defining tool contracts, or ensuring skills maintain proper isolation from the assistant codebase and follow Vellum's portability standards.
git clone --depth 1 https://github.com/vellum-ai/vellum-assistant /tmp/vellum-skill-authoring && cp -r /tmp/vellum-skill-authoring/.cursor/skills/vellum-skill-authoring ~/.claude/skills/vellum-skill-authoringSKILL.md
# Vellum Skill Authoring ## Scope Use this for Vellum runtime skills in `skills/` and bundled assistant skills, not for Cursor Agent Skills under `.cursor/skills/`. ## Core Constraints - First-party skills must be portable and isolated. - `skills/` must not import from `assistant/`. - `assistant/` must not import from `skills/`. - Prefer skill processes and supported contracts over new daemon tool registrations. - Avoid secrets, real personal data, and machine-specific paths in skill docs, tests, and fixtures. ## SKILL.md Quality Bar Skill instructions should be concise and operational: - State what the skill does and when to use it. - Prefer concrete steps over broad advice. - Keep user-facing terminology consistent. - Use generic examples only. - Avoid requiring hidden local state unless setup instructions create it. ## Tool And Script Review When a skill adds scripts or tools: 1. Verify tool input/output contracts are explicit. 2. Check error handling and user-facing messages. 3. Confirm scripts can run in the skill process environment. 4. Avoid direct imports across isolation boundaries. 5. Add focused tests for parsing, contract handling, and failure cases. ## Catalog And Packaging When adding or renaming skills, check the relevant catalog, manifest, bundled registry, or packaging path used by the runtime. Do not assume a `SKILL.md` file alone makes the skill available to users. ## Verification Use focused tests around the changed skill, catalog entry, proxy bridge, or bundled registry. Add typecheck when contracts or generated manifests changed.
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