Description
Superpowers and Playbooks make reusable agent instructions and curated operating collections directly usable in command-line workflows. dots playbooks import ingests a directory representation, while dots superpowers lists, opens, invokes, and creates typed Superpower records. Invocation resolves the durable asset and returns its usable fragment through the standard output boundary.
The workflow is designed for operators and coding agents. It uses the same authenticated, company-scoped service contracts as the rest of Dots, so terminal or protocol convenience never creates a second source of truth. Inputs are validated before or at the route boundary, and outputs preserve identifiers and structured details needed for a reliable next step.
Selling Points
- Turns reusable expertise into named assets instead of repeatedly pasted prompts.
- Lets teams import curated playbook collections from maintained files.
- Supports discovery and inspection before invocation, preserving operator control.
- Makes creation and use available to both humans and agents in headless sessions.
- Provides stable identifiers that other search and MCP workflows can reference.
User Story
A team imports a reviewed playbook directory, an agent lists available Superpowers, inspects the relevant one, and invokes it for the current task. The agent works from a durable, versionable operating asset rather than an ad hoc instruction. The result is a concrete, inspectable outcome that another person or automation can continue from without reconstructing hidden state.
Extension Surface
The CLI surface is automatable: packages/cli/src/commands/playbooks.ts and packages/cli/src/commands/superpowers.ts bind fixed operations. Superpower types may be extended through the SDK, but CLI verbs remain core-owned. The rating reflects the most-open supported seam that is true for this capability, not a transitive implementation detail. The cited path is the operational proof: consumers can use the documented seam, while unsupported changes still require a core release.
Capabilities & Limits
- Capability: Directory-based Playbook import.
- Capability: Superpower list, detail, invocation, and creation.
- Capability: Formatted fragments and stable asset identifiers for downstream agents.
- Limit: Invocation does not make an unreviewed asset trustworthy; permissions and the Superpower's own type contract still govern use.
The limit is intentional product truth rather than missing documentation. Calls also remain subject to authentication, tenant selection, schema validation, and the permissions enforced by the authoritative service.
Implementation Map
packages/cli/src/commands/playbooks.tspackages/cli/src/commands/superpowers.tsdocs/cli/playbooks-and-superpowers-commands.md