Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Implements the Shape Up product development methodology for collaborative feature scoping with an LLM. Covers two phases: shaping (iterating on problem requirements and solution options with fit checks) and breadboarding (mapping systems into UI and code affordances with wiring). Produces decision matrices, affordance tables, and vertical implementation slices.
Unlike ad-hoc planning or user stories, it enforces a fit check across all requirements before committing to a shape, catching mismatches before any implementation begins.
When to use it
- Defining requirements for a new feature before writing any code
- Comparing solution approaches side by side with a structured fit check
- Mapping an existing system to find where a proposed change lands
- Breaking a scoped feature into demo-able vertical implementation slices
- Running a 'should we build X or Y?' discussion with structured outputs
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: 'Shape a new in-app notifications feature for our SaaS product'
- 1Gathers pain points and constraints to populate the requirements set (R0, R1, R2...)
- 2Sketches multiple high-level solution shapes (A, B, C) broken into components
- 3Builds a fit check matrix mapping each requirement against each shape with binary pass/fail
- 4Breadboards the selected shape into UI and code affordances with wiring diagrams
- 5Slices the breadboarded shape into vertical increments, each ending in demo-able UI
A structured shape document with a requirements list, selected shape, affordance tables, and labeled implementation slices ready for development