novuhq/novu

The open-source communication infrastructure for agents and products

40kStars on the repository
55Mods indexed here, across every type
todayLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

novuhq/novu

Skill Claude CodeCodex

Use when building email features, emails going to spam, high bounce rates, setting up SPF/DKIM/DMARC authentication, implementing email capture, ensuring compliance (CAN-SPAM, GDPR, CASL), handling webhooks, retry logic, or deciding transactional vs marketing.

40k +9 today A 61 tokens

figma-use

02

novuhq/novu

Skill Claude CodeCodex

MANDATORY prerequisite — you MUST invoke this skill BEFORE every usefigma tool call. NEVER call usefigma directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in…

40k +9 today A 114 tokens

frontend-design

03

novuhq/novu

Skill Claude CodeCodex

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…

40k +9 today A 77 tokens

novuhq/novu

Skill Claude CodeCodex

Generate CI/CD configuration for Linear Release. Use when setting up release tracking, configuring CI pipelines for Linear, or integrating deployments with Linear releases. Supports GitHub Actions, GitLab CI, CircleCI, and other platforms.

40k +9 today A 49 tokens

react-email

05

novuhq/novu

Skill Claude CodeCodex

Use when creating HTML email templates with React components - welcome emails, password resets, notifications, order confirmations, newsletters, or transactional emails.

40k +9 today A 30 tokens

testerarmy-cli

06

novuhq/novu

Skill Claude CodeCodex

Use TesterArmy CLI to create, organize, and run dashboard-managed QA tests. Prefer saved tests, groups, project context, credentials, and remote runs over one-off local prompts. Trigger when defining regression coverage, adding QA flows, or wiring CI checks.

40k +9 today A 55 tokens

novuhq/novu

Skill Claude CodeCodex

Skill for integrating Better Auth - the comprehensive TypeScript authentication framework.

40k +9 today A 20 tokens

novuhq/novu

Skill Claude CodeCodexCursor

Build a new channel Connect button (e.g. WhatsApp, Discord, LINE) in @novu/js and @novu/react following the existing SlackConnectButton, MsTeamsConnectButton, and TelegramConnectButton pattern. Use when adding connect/disconnect UI for a new chat channel/provider to the SDK — covering the SolidJS core component, the…

40k +9 today A 102 tokens

novuhq/novu

Skill Claude CodeCodexCursor

Add a new chat channel's layer-1 setup guide — the in-dashboard SetupGuide that walks a developer through connecting the channel itself (create app/bot → save credentials → install/verify → send first message) with live connection detection — in apps/dashboard, following the existing Slack, MS Teams, and Telegram…

40k +9 today A 99 tokens

novuhq/novu

Skill Claude CodeCodexCursor

Add a new chat channel's layer-2 dashboard onboarding — the connected-state "What's next" / "FOR YOUR USERS" developer-rollout guide plus its connected details page — in apps/dashboard, following the existing Slack, MS Teams, and Telegram pattern. Use when a connected agent integration needs a per-provider "what's…

40k +9 today A 116 tokens

address-pr-review

11

novuhq/novu

Skill Claude CodeCodexCursor

Critically triage pull request review comments against PR requirements and codebase reality, implement only valid fixes, and reply only when declining a suggestion. Use when the user asks to address PR comments, review feedback, CodeRabbit/Bugbot threads, or /address-pr-review.

40k +9 today A 59 tokens

novuhq/novu

Skill Claude CodeCodexCursor

Use this skill when making changes to the enterprise submodule (.source/) or enterprise packages (enterprise/packages/), or when the enterprise submodule needs to be initialized/updated.

40k +9 today C 0 tokens

ink-tui-wizard

13

novuhq/novu

Skill Claude CodeCodexCursor

Build terminal user interfaces (TUIs) using Ink (React for CLIs) and @inkjs/ui with a reactive, session-driven wizard pattern. Use when creating interactive CLI installation wizards, setup flows, or multi-step terminal applications in Node.js/TypeScript. Covers reactive screen resolution, declarative flow pipelines…

40k +9 today A 92 tokens

novu-prepare-pr

14

novuhq/novu

Skill Claude CodeCodexCursor

Post-implementation PR prep for Novu feature branches — quality passes, commit/PR hygiene, CI triage, and review feedback. Use after feature work is done, when the user asks to prepare a PR, ship a branch, fix CI, address review comments, or babysit a pull request before merge.

40k +9 today A 69 tokens

novuhq/novu

Skill Claude CodeCodexCursor

Build or refactor a Tool-channel provider (PagerDuty, Opsgenie, future incident/alerting tools) to be endpoint-routed: per-subscriber secrets encrypted on the channel endpoint resource, a stateless provider that resolves routing from channelData at send time, SKIPPED steps when no endpoint exists, and the full…

40k +9 today A 121 tokens

nv-implement

16

novuhq/novu

Skill Claude CodeCodexCursor

Implement planned work by fanning out parallel subagents on isolated worktrees — TDD at pre-agreed seams, per-slice nv-park-and-review, merge back, full suite once at the end.

40k +9 today A 46 tokens

nv-onboard-dcr-mcp

17

novuhq/novu

Skill Claude CodeCodexCursor

Onboard a new DCR OAuth MCP catalog entry with provider-doc vetting and curl probes. Use when adding or changing mode: dcr entries in MCPSERVERS. Abort if the provider requires whitelist or manual approval.

40k +9 today A 0 tokens

nv-park-and-review

18

novuhq/novu

Skill Claude CodeCodexCursor

Commit local changes as a baseline, hop into a lightweight review worktree, run a thermo-nuclear code quality review scoped to ONLY that commit, commit the resulting refactor as a separate follow-up commit, then land it back and tear the worktree down. Use when the user asks to review their local/uncommitted changes…

40k +9 today A 87 tokens

nv-worktree-cleanup

19

novuhq/novu

Skill Claude CodeCodexCursor

Audits git worktrees and removes the ones that are safe to delete — merged into the base branch (including squash-merges via gh), missing on disk, or explicitly confirmed by the user — then deletes the associated local branches and runs git worktree prune. Use when the user asks to clean up worktrees, prune worktrees…

40k +9 today A 97 tokens

novuhq/novu

Skill Claude CodeCodexCursor

Git worktree command reference: path naming, create/remove/prune, .env copy, package-manager install, and cleanup. Use when implementing or debugging worktree setup — not as the primary user-facing workflow (see nv-worktree-create).

40k +9 today A 56 tokens

nv-worktree-create

21

novuhq/novu

Skill Claude CodeCodexCursor

Create a sibling git worktree and a new branch with the same name, copy local .env files, initialize the enterprise submodule, wire enterprise symlinks, and move the agent into the worktree. Use when the user asks for a worktree, parallel branch checkout, or /worktree with a branch name.

40k +9 today A 73 tokens

run-api-e2e-tests

22

novuhq/novu

Skill Claude CodeCodexCursor

Run e2e tests for the API service. Use when the user wants to run API E2E tests.

40k +9 today A 30 tokens

sanity-changelog

23

novuhq/novu

Skill Claude CodeCodexCursor

Create and publish Novu changelog entries in Sanity (changelogPost documents), including feature posts, "improvements & fixes" roundups built from Linear releases, and the Changes (changeBlock) component. Use when asked to write a changelog entry, announce a shipped feature on the changelog, roll up improvements/bug…

40k +9 today A 92 tokens

novuhq/novu

Skill Claude CodeCodexCursor

Triage failing @novu/agent-evals scenarios to decide whether a failure is real or flaky, and whether to fix the playbook/prompt or the test (grader, tape, scenario, or judge). Use when an agent-evals scenario fails, when the user asks why an eval is red, or when deciding whether to fix the test or the prompt.

40k +9 today A 83 tokens