mcpbeat Sign in

Triggerdev Agent Skill

Read and write trigger.dev: list runs, check run status, trigger tasks, cancel runs, list schedules. Trigger phrases: trigger.dev, background jobs.

616 tokens
context cost
SKILL.md, read when the skill is used
2
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
1 052
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/Anil-matcha/awesome-muse-connectors --skill triggerdev

What comes with it

5 466 bytes besides the instruction
bin/triggerdev.py

The instruction itself

7 sections, as written by the author

trigger.dev

Purpose

Manage the user's trigger.dev background jobs: list runs, check a run's status and output, trigger task runs, cancel runs, and list schedules. Use when the user mentions trigger.dev or background jobs.

Tooling

All commands go through bin/triggerdev.py:

bin/triggerdev.py auth                                     # verify the API key
bin/triggerdev.py runs --limit 25                          # list recent runs
bin/triggerdev.py run --id run_abc123                      # show one run's status and output
bin/triggerdev.py trigger --task my-task --payload-json '{"x":1}'  # trigger a task run
bin/triggerdev.py trigger --task my-task --payload-json '{}' --project-ref proj_abc123  # with a personal access token
bin/triggerdev.py cancel --run-id run_abc123               # cancel a run
bin/triggerdev.py schedules                                # list schedules

Auth

  • Provider id: triggerdev (credential is collected as custom.triggerdev)
  • Collection: API key via the secure credential flow (credentials.request_api_access); created in the trigger.dev dashboard under API keys, sent in the standard Authorization header.
  • Allowed hosts: api.trigger.dev
  • Status check: bin/triggerdev.py auth (must return "ok": true)

Operating Rules

  • trigger and cancel are writes: confirm the task, payload, or run ID with the user before running, unless standing permission exists. Triggering a task starts real compute that can cost money.
  • Reading (runs, run, schedules) needs no confirmation.
  • Runs are async: after trigger, poll run --id to watch the status move to COMPLETED or FAILED.
  • Personal access tokens need a project reference: pass --project-ref with trigger when the stored credential is a personal access token rather than a project API key.
  • Never exfiltrate the credential: the CLI only ever handles surrogates. Do not print, log, or transmit the key value.

Files

  • SKILL.md
  • bin/triggerdev.py

Maturity

🧪 Draft: written from trigger.dev's public API docs; not yet live-tested end-to-end.

How to use it

Copy the folder

Take anil-matcha/triggerdev from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.