Playbooks
Apps & AutomationplaybooksPlaybooks is an Agent Skill for apps & automation published in the vellum-ai/vellum-assistant repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Trigger-action automation rules for handling incoming messages
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/vellum-ai/vellum-assistant/blob/HEAD/assistant/src/config/bundled-skills/playbooks/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/playbooks, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Playbooks are trigger-action automation rules that tell the assistant how to handle incoming messages matching a pattern.
Structure
Each playbook has:
- Trigger: Pattern or description that activates the rule (e.g. "meeting request", "from:ceo@*")
- Action: What to do when triggered (natural language description)
- Channel: Which channel the rule applies to ("*" = all channels, or specific like "email", "slack")
- Category: Free-form grouping label (e.g. "scheduling", "triage")
- Autonomy level: How much autonomy the assistant has
auto-- execute immediately without askingdraft-- prepare a response for user review (default)notify-- alert the user only
- Priority: Numeric priority for overlapping rules (higher = takes precedence)
Lifecycle
- Create a playbook with
playbook_createspecifying trigger and action. - List existing playbooks with
playbook_list, optionally filtering by channel or category. - Update rules with
playbook_updateor remove them withplaybook_delete.
Storage
Playbooks are stored as memory items with semantic retrieval, enabling fuzzy matching of incoming messages against trigger patterns.