Terminal
Terminal/Skill
Writes and fixes Kestra flow YAML against the live flow schema, so the output uses only valid task types and properties.
By Kestra
Works with
npx skills add kestra-io/agent-skills --skill kestra-flowUse this skill to generate production-ready Kestra Flow YAML grounded in the live schema.
Use this skill when the request includes:
Fetch the full schema with curl and read it directly — do not pipe it through any interpreter:
curl -s https://api.kestra.io/v1/plugins/schemas/flow
Read the raw JSON output to validate every type, property name, and structure used in the output. Do not generate anything before the schema is available.
Identify from the user message or conversation:
id — flow identifier (preserve if provided)namespace — target namespace (preserve if provided)Apply all generation rules below, then output raw YAML only.
Schema compliance
Structural preservation
id and namespace if provided.Triggers
Schedule trigger unless a regular occurrence is explicitly requested.{{ trigger.outputName }}; only use variables defined in the trigger's declared outputs.Looping
ForEach for repeated actions over a collection.LoopUntil for condition-based looping.Flow outputs
outputs if the user explicitly requests returning a value from the execution.State tracking between executions
io.kestra.plugin.core.kv.Set / io.kestra.plugin.core.kv.Get) to store and compare state across executions.JDBC plugin
fetchType: STORE when using JDBC tasks.Date manipulation in Pebble
dateAdd and date filters for date arithmetic.| number before numeric comparisons.Credentials and secrets
inputs of type SECRET or Pebble expressions (e.g., {{ secret('MY_SECRET') }}).APIs and connectivity
Quoting
Error handling
I cannot generate a valid Kestra Flow YAML for this request based on the available schema.
# comments at the top of the output for any caveats, assumptions, or warnings.kestractl.prod.data that reads from a Postgres table and writes the result to S3."