| Skill | Added | Review |
|---|---|---|
novu-prepare-pr .cursor/skills/novu-prepare-pr/SKILL.md 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. | 73 73 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce | |
novu-trigger-notification docs/.mintlify/skills/trigger-notification/SKILL.md Trigger Novu notification workflows to send messages across email, SMS, push, chat, and in-app channels. Supports single triggers, bulk triggers, broadcast to all subscribers, topic-based targeting, and cancellation. Use when sending transactional notifications, alerts, or any event-driven messages. | 68 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce | |
nv-endpoint-routed-tool-provider .cursor/skills/nv-endpoint-routed-tool-provider/SKILL.md 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 API/worker/dashboard/docs/playground surface. Starts with a mandatory provider-docs discovery gate. Use when refactoring Opsgenie to the PagerDuty model, adding a new tool provider, or touching pagerduty_service channel endpoints. | 70 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce | |
nv-implement .cursor/skills/nv-implement/SKILL.md 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. | 64 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce | |
nv-park-and-review .cursor/skills/nv-park-and-review/SKILL.md 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 for AI slop and redundant code, or invokes nv-park-and-review. | 72 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce | |
nv-worktree-cleanup .cursor/skills/nv-worktree-cleanup/SKILL.md 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, list stale worktrees, remove merged worktrees or branches, or reclaim disk space from old checkouts. | 76 76 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce | |
nv-worktree-commands .cursor/skills/nv-worktree-commands/SKILL.md 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). | 71 71 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce | |
nv-worktree-create .cursor/skills/nv-worktree-create/SKILL.md 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. | 73 73 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce | |
react-email .agents/skills/react-email/SKILL.md Use when creating HTML email templates with React components - welcome emails, password resets, notifications, order confirmations, newsletters, or transactional emails. | 61 61 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce | |
run-api-e2e-tests .cursor/skills/run-api-e2e-tests/SKILL.md Run e2e tests for the API service. Use when the user wants to run API E2E tests. | 62 62 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce | |
sanity-changelog .cursor/skills/sanity-changelog/SKILL.md 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 fixes since the last release, or work with Sanity changelog content for the Novu website. | 68 68 Impact — No eval scenarios have been run Securityby High Do not use without reviewing Version: 320a0ce | |
testerarmy-cli .agents/skills/testerarmy-cli/SKILL.md 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. | 69 69 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce | |
triage-agent-eval-failures .cursor/skills/triage-agent-eval-failures/SKILL.md 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. | 72 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 320a0ce |