stevesolun/ctx / .agents/skills/prototype
prototype
VerifiedBuild a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
| File | Kind | Size |
|---|---|---|
| LOGIC.md | markdown | 1.7 KB |
| SKILL.md | skill md | 1.5 KB |
| UI.md | markdown | 2.0 KB |
| agents/openai.yaml | config | 100 B |
LOGIC.md
View on GitHub# Logic Prototype
A logic prototype makes business rules, state transitions, or data-shape
trade-offs concrete enough to exercise.
## Workflow
1. Write down the question and what evidence would answer it.
2. Choose the cheapest useful interaction:
- a small terminal UI for exploratory state transitions;
- a script or table of cases for deterministic rules;
- a focused test harness for invariants or regression behavior;
- a notebook or REPL when rapid data-shape exploration matters.
3. Use the project's existing runtime and tooling where practical.
4. Keep the logic separate from the harness when that separation helps compare
designs or reuse the result. Do not turn a disposable experiment into a
premature production abstraction.
5. Exercise representative normal, edge, and invalid cases. Surface the state,
transition, output, or error that answers the question.
6. Give the user the run command and summarize what the prototype demonstrated.
## Interactive terminal shape
When manual state exploration is the useful feedback loop, build a lightweight
terminal interface:
- Show the current relevant state and available actions.
- Accept one action at a time and render the resulting state.
- Keep the frame compact and make invalid transitions visible.
- Use native terminal capabilities or dependencies already present in the
project before adding a UI library.
## Guardrails
- Avoid real production mutations unless they are essential to the question and
safely isolated.
- Avoid speculative generalization.
- Keep harness concerns from obscuring the logic under evaluation.
- Treat prototype code as evidence, not production-ready implementation.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |