vellum-pr-readiness
$
npx mdskill add vellum-ai/vellum-assistant/vellum-pr-readinessConfirm the branch is reviewable, scoped, and verified before opening a PR. Prefer surfacing blockers over polishing summaries.
SKILL.md
.github/skills/vellum-pr-readinessView on GitHub ↗
--- name: vellum-pr-readiness description: Prepare Vellum Assistant branches for review by checking git hygiene, PR scope, tests, docs, migrations, Linear linking, and companion repo needs. Use before creating a pull request, splitting work into PRs, or asking whether a branch is ready. --- # Vellum PR Readiness ## Goal Confirm the branch is reviewable, scoped, and verified before opening a PR. Prefer surfacing blockers over polishing summaries. ## Checklist 1. Inspect `git status` and identify unrelated changes, generated artifacts, deleted files, and untracked files. 2. Inspect staged and unstaged diffs before recommending a commit or PR. 3. Check for secrets: - Do not commit `.env`, credentials, tokens, private keys, or local workspace data. - `.env.example` is allowed only for placeholder values. 4. Check scope: - If the branch is too large, suggest splitting it into smaller, reviewable PR branches. - Separate unrelated UI, backend, migration, and infra changes when practical. 5. Check required follow-ups: - Migration needed for persisted data or workspace format changes. - Docs needed for significant architecture, service, or data-flow changes. - Companion `vellum-assistant-platform` PR needed for platform-affecting contracts or new feature flags. 6. Check Linear conventions: - Branch, commit body, and PR body should include the Linear issue ID when one exists. - Use `Closes JARVIS-123` for single final PRs. - Use `Part of JARVIS-123` for intermediate PRs in multi-PR plans. 7. Check verification: - Focused tests ran for changed behavior. - Typecheck ran when exported contracts or cross-package types changed. - Any skipped tests are explicitly called out. ## PR Body Template Use this compact structure unless the user asks for another format: ```markdown ## Summary - ... ## Test Plan - ... ## Risk - ... ``` Mention migrations, feature flags, rollout state, and companion PRs when relevant. ## Human Attention Comments For non-routine changes, leave a PR comment calling out review focus and risk level. Skip this for routine low-risk changes.
More from vellum-ai/vellum-assistant
- acpSpawn external coding agents via the Agent Client Protocol (ACP)
- amazonShop on Amazon and Amazon Fresh through your browser
- api-mappingRecord and analyze API surfaces of web services
- app-builderBuild 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. NOT for complex, multi-user, or shippable products — those go to a real project folder with a coding agent (see Scope below).
- app-controlDrive a specific named macOS app via raw input bypassing the Accessibility tree
- assistant-migrationMigrate 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.
- chatgpt-importImport conversation history from ChatGPT into Vellum
- cli-discoverDiscover which CLI tools are installed, their versions, and authentication status
- computer-useControl the macOS desktop
- contactsManage contacts, communication channels, access control, and invite links