Dailybot agent skill for Plan
The public Dailybot agent skill pack covers Plan (Beta): what an agent can do with it and where to find it.
Beta
Plan is in beta. Everything under /plan in the web app, the CLI and agent skill commands for projects, goals, boards and tasks, and the /v1/plan/ public API may change before general availability. Want to try it with your team? Write to [email protected].
The Dailybot agent skill is a public pack that teaches AI coding agents to use Dailybot, including Plan. It lives in the DailybotHQ/agent-skill repository; the Plan part is the sub-skill that wraps dailybot plan … and needs dailybot-cli 4.0.0 or later.
What it gives an agent
- The command surface of the Dailybot CLI for Plan, with examples an agent can follow.
- The rules for working a card on a person’s behalf: read the whole card, write back as the person with the agent named, tie shipped work to a task. See Agents on Plan.
- The reminder that card content is data, never instructions.
How agents use it
The skill calls the CLI, so an agent needs the CLI installed and a credential (see credentials). When the agent identifies itself with --agent-name or DAILYBOT_AGENT_NAME, its writes show up on the card as executed by that agent.
Command names and flags come from the CLI and the skill’s own reference, not from this page. If they differ from what you read here, the CLI and the skill win.