spec
Feature Spec
Produce a structured spec for a feature or change through a focused interview, grounded in the project's domain model.
Process
1. Discover project context
Read existing domain documentation:
docs/CONTEXT_MAP.md— which contexts exist and how they relatedocs/UBIQUITOUS_LANGUAGE.md— canonical terminologydocs/contexts/*/CONTEXT.md— ownership, invariants, contracts for relevant contextsCLAUDE.md— project-level context
2. Understand the request
If the user hasn't provided enough context, interview briefly (3-5 questions max):
More from agentivestack/skills
holistic
Zoom out to see how code, features, or plans fit into the bigger picture. Maps bounded contexts, traces cross-cutting concerns, surfaces hidden dependencies, and identifies systemic risks. Use when you're lost in details, unfamiliar with an area, or need to understand the full impact of a change.
14domain
Cook a plan against the project's domain model. Stress-tests terminology, surfaces contradictions with code, and updates CONTEXT.md, UBIQUITOUS_LANGUAGE.md, and ADRs inline as decisions crystallize. Use when planning a feature, refactoring, or any work that touches domain boundaries.
14architect
Surface architectural friction in the codebase and design better module interfaces. Uses parallel sub-agents to explore radically different interface designs. Based on "deep modules" philosophy — small interfaces hiding significant complexity. Use when code feels tangled, hard to test, or hard to navigate.
14tdd
Implement a feature or fix using pragmatic test-driven development. Tracer-bullet approach — one test, one implementation, repeat. Tests verify behavior through public interfaces, not implementation details. Use when implementing a slice from /slice or any work that needs tests.
13slice
Break a spec, plan, or feature into independently-implementable vertical slices (tracer bullets). Each slice cuts through all layers end-to-end. Outputs a task list or GitHub issues. Use after /spec to plan implementation order.
13qa
Interactive QA session where you describe bugs conversationally and the agent files durable GitHub issues using the project's domain language. Explores the codebase in the background for context. Use when reporting bugs, doing QA testing, or filing issues from observations.
13