vellum-ai

62 mods across 1 repository, 1.2k stars between them.

UserPromptSubmit

01

vellum-ai/vellum-assistant

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing linear-ticket-reminder.sh. From vellum-ai/vellum-assistant.

1.2k 2d ago A tokens not measured original MIT

SessionStart

02

vellum-ai/vellum-assistant

Hook Claude Code

Runs when a session starts, executing session-docs-primer.sh. From vellum-ai/vellum-assistant.

1.2k 2d ago A tokens not measured copy · 53% MIT

vellum-assistant

03

vellum-ai/vellum-assistant

Settings file Claude Code

Agent settings declaring 2 hook events (UserPromptSubmit, SessionStart) and 17 allowed tools.

1.2k 2d ago A tokens not measured original MIT

cli-testing

04

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Manually test a running Vellum assistant end-to-end purely from the CLI — no desktop app or web UI. Hatch an instance, send messages, watch the reply, and tear it down. Use when verifying assistant behavior, reproducing a bug, or smoke-testing a change without the macOS/web clients.

1.2k 2d ago A 66 tokens original MIT

release

05

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Cut a new release: create the release branch (staging bake), then dispatch the production Release run on that branch.

1.2k 2d ago A 26 tokens original MIT

update

06

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Restart the Vellum assistant and gateway services. Smart branch handling: pulls from main by default, restarts in-place on feature branches, or switches to a specified branch. Pass --pull to force-pull on the current branch.

1.2k 2d ago A 49 tokens original MIT

e2e

07

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Run end-to-end tests via the CI workflow.

1.2k 2d ago A 14 tokens original MIT

vellum-ai/vellum-assistant

Skill Claude CodeCodexCursor

Check Vellum Assistant architecture and package boundaries. Use when editing imports, moving code, adding endpoints, touching assistant/gateway/client/skill boundaries, or reviewing architecture-sensitive changes.

1.2k 2d ago A 43 tokens original MIT

vellum-ai/vellum-assistant

Skill Claude CodeCodexCursor

Review Vellum Assistant code changes for correctness, repo-specific quality rules, security risks, and missing validation. Use when reviewing diffs, preparing a PR, finishing implementation work, or when the user asks for a code review, quality pass, or pre-merge check in this repository.

1.2k 2d ago A 63 tokens original MIT

vellum-ai/vellum-assistant

Skill Claude CodeCodexCursor

Guide Vellum Assistant feature flag changes and rollout hygiene. Use when adding, editing, reviewing, or documenting assistant feature flags, rollout-gated behavior, or platform flag follow-up work.

1.2k 2d ago A 46 tokens original MIT

vellum-ai/vellum-assistant

Skill Claude CodeCodexCursor

Validate Vellum Assistant database and workspace migrations. Use when adding, editing, reviewing, or testing migrations, release-note migrations, persisted schemas, workspace file formats, or data backfills.

1.2k 2d ago A 45 tokens original MIT

vellum-pr-readiness

12

vellum-ai/vellum-assistant

Skill Claude CodeCodexCursor

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.

1.2k 2d ago A 57 tokens original MIT

vellum-ai/vellum-assistant

Skill Claude CodeCodexCursor

Author and review first-party Vellum skills in the repository. Use when editing files under skills/, assistant bundled skills, skill manifests, tool definitions, SKILL.md files, or first-party skill portability and isolation behavior.

1.2k 2d ago A 51 tokens original MIT

vellum-ai/vellum-assistant

Skill Claude CodeCodexCursor

Select focused verification commands for Vellum Assistant changes. Use when deciding what tests, typechecks, lints, or smoke checks to run after editing this repository, especially before commits and pull requests.

1.2k 2d ago A 45 tokens original MIT

vellum-ai/vellum-assistant

Skill Claude CodeCodexCursor

Review Vellum Assistant user-facing copy, examples, docs, CLI output, UI strings, and assistant-facing release notes. Use when editing text users may read, including README files, SKILL.md files, CLI messages, route errors, update bulletins, and client UI labels.

1.2k 2d ago A 63 tokens original MIT

vellum-ai/vellum-assistant

Instructions file CodexOpenCode

Instructions for vellum-ai/vellum-assistant, covering vellum assistant — agent instructions, project structure, intellectual honesty, development and dependencies.

1.2k 2d ago A 9,515 tokens original MIT

acp

17

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Set up, authenticate, and run external coding agents (Claude Code, Codex) via the Agent Client Protocol.

1.2k 2d ago A 25 tokens original MIT

app-builder

18

vellum-ai/vellum-assistant

Skill Claude CodeCodex

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…

1.2k 2d ago A 162 tokens original MIT

app-control

19

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Drive a specific named macOS app via raw input bypassing the Accessibility tree.

1.2k 2d ago A 18 tokens original MIT

contacts

21

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Manage contacts, communication channels, access control, and invite links.

1.2k 2d ago A 14 tokens original MIT

conversation-groups

22

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Organize conversations into custom sidebar groups — list groups, create new ones, and file conversations into them.

1.2k 2d ago A 24 tokens original MIT

document-editor

23

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Use whenever the user wants to write or draft an article, blog post, essay, report, or any long-form content. Creates the content in a rich text editor instead of dumping it in chat, so it can be streamed, reviewed, edited, and exported.

1.2k 2d ago A 56 tokens original MIT

followups

24

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Track sent messages awaiting responses across communication channels.

1.2k 2d ago A 11 tokens original MIT