vellum-feature-flag-rollout
This skill guides code review and implementation of feature flags for the Vellum Assistant. Use it when adding, editing, or reviewing assistant feature flags, rollout-gated behavior, release-note handling, permission controls, or related platform infrastructure changes. The skill ensures proper registry declaration, safe defaults, test coverage, and hygiene of user-facing communications to prevent accidentally shipping incomplete features to end users.
git clone --depth 1 https://github.com/vellum-ai/vellum-assistant /tmp/vellum-feature-flag-rollout && cp -r /tmp/vellum-feature-flag-rollout/.cursor/skills/vellum-feature-flag-rollout ~/.claude/skills/vellum-feature-flag-rolloutSKILL.md
# Vellum Feature Flag Rollout ## Flag Rules Assistant feature flags use simple kebab-case keys and must be declared in: ```text meta/feature-flags/feature-flag-registry.json ``` New flags require: - `scope: "assistant"` - a canonical kebab-case key - a safe default - tests or guard coverage when resolver behavior changes - a companion `vellum-assistant-platform` PR to provision the flag in Terraform ## Rollout Hygiene There is no release-note surfacing mechanism — the workspace-bulletin feature was removed and the historical release-note migrations are frozen. Do not add new release-note migrations for any feature (flagged or GA). If a release needs user-facing notes, design an explicit on-demand surfacing mechanism first. ## Permission Controls V2 Under `permission-controls-v2`, do not add new deterministic approval modes for assistant-owned actions beyond the conversation-scoped host computer access gate. Avoid global toggles, persistent trust-rule UI, wildcard scopes, and time-window approvals. ## Review Workflow 1. Confirm whether the change adds, renames, removes, or consumes a flag. 2. Check registry declaration and key format. 3. Check default behavior and rollout safety. 4. Check docs, release notes, and user-facing copy for flag leaks. 5. Check whether the platform repo needs a Terraform update. 6. Recommend focused tests for resolver, route, UI, or behavior changes. ## PR Notes Call out: - flag key - default state - rollout plan - companion platform PR status - whether release notes are intentionally omitted
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