integrate-agentkit
Installation
SKILL.md
Integrate AgentKit
Take this repo from a connection to a connected account, an authorized token, and one downstream API call. Then stop.
Guardrails
- MUST pass the exact dashboard Connection Name (
connection_namein Python,connectionNamein Node). Never invent a slug. Never use aconnectorfield for that value. - MUST re-fetch the connected account immediately before using the token. Scalekit auto-refreshes.
- MUST print the authorization link and stop when the process is not interactive. Re-run from the token step after the user finishes OAuth.
- MUST take missing
SCALEKIT_*values from the user. MUST NOT copy them from another project, home directory, or skill folder.
Gotchas
- Read SDK credentials from
SCALEKIT_ENVIRONMENT_URL,SCALEKIT_CLIENT_ID, andSCALEKIT_CLIENT_SECRET. Some samples useSCALEKIT_ENV_URL; useSCALEKIT_ENVIRONMENT_URLhere. - A connection is dashboard connector config. A connected account is one user authorized on that connection.
- The connection already exists from
setup-agentkit. This skill starts there. - Gmail can use Connection Name
gmailwhen the dashboard has no Gmail row. Every other connector must already have a dashboard connection. Record that name exactly. - Default language is Python. If the repo is Node, open references/node.md. If the language is unknown, stay on Python.