new
Add one capability to an existing Trigger.dev project (a task, a schedule, a progress UI, an approval step, a webhook handler) and prove it runs.
- License 许可
- MIT
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- new
- description
- Add one capability to an existing Trigger.dev project (a task, a schedule, a progress UI, an approval step, a webhook handler) and prove it runs.
- allowed-tools
- Bash(npx tsc --noEmit*) Bash(pnpm exec tsc --noEmit*) Bash(yarn tsc --noEmit*) Bash(bunx tsc --noEmit*) Bash(trigger-ctx *) Bash(node *trigger-ctx.mjs *) Bash(node *trigger-ctx.mjs" *)
- argument-hint
- <capability, e.g. progress bar for the import task>
- disable-model-invocation
- true
02 资源文件 1
- 参考文档agents/openai.yaml43 B
03 SKILL.md 正文
Add a capability
Capability requested: $ARGUMENTS
Project facts
!node "${CLAUDE_PLUGIN_ROOT}/scripts/trigger-ctx.mjs" detect --brief
(If the block is empty, run node "${CLAUDE_PLUGIN_ROOT}/scripts/trigger-ctx.mjs" detect --brief yourself.)
Procedure
This is init without the setup: the project already has Trigger.dev. If it does not (no root, SDK not installed), stop and suggest /trigger-dev:init. If the SDK is 3.x, read ${CLAUDE_PLUGIN_ROOT}/skills/build/scenarios/migrate-v2-v3.md first.
- Classify the request into one card from the table in
${CLAUDE_PLUGIN_ROOT}/skills/build/SKILL.md(a chat or AI-assistant request goes to thechat-agentskill). Read only that card. - Discover with
${CLAUDE_PLUGIN_ROOT}/skills/build/discovery.md: ask only what the facts and the request leave open, at most two questions, and state every assumption. - Decide in at most 15 lines: primitives, one line of why each, a doc link per primitive, the files you will touch. The user confirms before you write.
- Build. Verify every API name with
trigger-ctx docs <topic>before writing it. Follow the build invariants. Reuse the existing task layout (dirs), naming and package manager. A new call site is a type-onlytasks.trigger, or a REST call in the host language. - Prove it. Follow
${CLAUDE_PLUGIN_ROOT}/skills/build/verify.md; a failure goes toget_run_detailsand thediagnoseskill, not to blind retries. - Hand off. Say what changed. Mention
/trigger-dev:shipif it should go live. Done means a run reached COMPLETED; if you could not run it, say UNVERIFIED and why.
04 同仓库更多 Skills
ship
Deploy Trigger.dev tasks (trigger deploy) to staging, prod or a preview branch with a preflight, the right CI or integration pipeline, an explicit --env, and a verification step. Use when asked to deploy, ship or release the Trigger.dev tasks or jobs. Not for deploying the app itself to Vercel, Fly or another host.
init
Set up Trigger.dev in this repository with a short discovery, an explicit architecture decision, and a first task proven to run.
doctor
Check the Trigger.dev toolchain around this project (Node, CLI login and profile, MCP server, versions, duplicate official skills, self-host target, plugin install scope) and report what to fix.
diagnose
Find out why Trigger.dev runs or deploys misbehave (stuck QUEUED or PENDING_VERSION, failed, timed out, crashed or OOM, schedules not firing, 429s, CI deploy failures, chat history lost). Use when a Trigger.dev project shows an error, a run id such as run_abc123, or the user says a task did not run.
chat-agent
Build, migrate or debug AI chat agents on Trigger.dev (chat.agent, the chat transport, sessions, transcript storage, tool approvals, server, Slack and Linear callers). Use when a Trigger.dev project needs a chat assistant or agent, or code imports @trigger.dev/sdk/ai or @trigger.dev/sdk/chat.
audit
Review a Trigger.dev codebase against the plugin's rule catalog (stale APIs, silent-failure patterns, config, deploy, cost) and write a findings report; optionally apply safe fixes.