Schedule a Workflow
Build a CF Workflow — multi-day durable orchestration with sleeps + retries that survive redeploys.
Overview
Implements workflows/SKILL.md. Scaffolds a Cloudflare Workflow that runs on a schedule, sleeps arbitrary durations between steps (hours, days, weeks), retries failed steps with backoff, and resumes after Worker redeploys. Each step must be idempotent (re-running it produces the same result). Best for slow pipelines, daily digests, multi-day onboarding sequences, retry-tomorrow-on-failure jobs.
When to use this
- user wants something to run daily / weekly / on a cadence
- user says 'run this every morning' / 'schedule this workflow' / 'do X then sleep a day then Y'
- pipeline needs to retry on failure with backoff
When NOT to use this
- user wants a one-shot task → just run it
- the schedule is intra-second / sub-minute → use a Durable Object alarm or queue instead
- user wants an autonomous agent on the agent-runtime → use build-agent
Example prompts
Inputs and output
Inputs
| Field | Description |
|---|---|
purpose | what the workflow does in one sentence |
cadence | how often it runs (e.g. '@daily 9am UTC') |
Output
Workflow file path in /work + deploy instructions + the cron trigger config.
Runtime profile
What the engine commits when this skill runs.
| Property | Value | Meaning |
|---|---|---|
| Model tier | sonnet | The balanced default model class. Trades quality against cost for the vast majority of skill runs. |
| Cost class | standard | The balanced default model. Right for most skills. |
| Turn budget | 10 | Hard cap on tool-calling iterations before the engine forces a final answer. |
| Execution | synchronous | Runs inside the live turn; result lands in the same response. |
Under the hood
Tools the engine exposes to this skill and integrations it needs.
| Resource | Kind |
|---|---|
shell_exec | tool |
shell_write | tool |
Tags: engineering, workflow, schedule
Execution template
Shell tools dispatch via a command template. The model substitutes user inputs into the placeholders before firing the underlying tool.
Invoking this from an agent
Three paths reach this skill. From the chat UI, a user can type the persona slash command followed by a natural request and the discovery step resolves to this skill automatically. From the MCP server, fetch the skill detail with get_skill({id: "schedule-workflow"}) and then invoke it through the agent runtime once the authenticated tier ships. From your own code, hit /docs/skills/schedule-workflow/llm.txt for the token-efficient markdown body and feed it to your model directly.
Accept: text/markdown. The full machine-readable catalog lives at /.well-known/agent-skills/index.json.