api-shape-explorer — Claude Code skill: parallel API design options
Runs several sub-agents at once so you get radically different interface designs for a module and can compare them before writing code.
npx skills add zebbern/claude-code-guide --skill api-shape-explorer -a claude-codeWhat api-shape-explorer does
The skill follows the "Design It Twice" idea from "A Philosophy of Software Design": your first interface shape is rarely the best one. It starts by gathering requirements — what the module solves, who calls it, which operations matter, what stays hidden and what gets exposed.
Then it spawns 3+ sub-agents at the same time through the Task tool. Each one gets a different constraint: keep it to 1–3 methods, support as many use cases as possible, optimise for the most common case, or borrow from a specific library. Every agent returns a signature, a usage example, the complexity it hides, and its trade-offs.
Designs are presented one after another, then compared on interface simplicity, module depth (a small interface over real complexity versus the opposite), and how easy it is to use correctly or misuse. The comparison is written in prose, not tables. No implementation comes out of this — the skill is about interface shape only, so don't expect working code. Give the sub-agents the same constraint and you'll get near-identical designs, which defeats the point.
What it helps with
- settle on a module interface before any code exists
- compare several API approaches instead of stopping at the first
- turn vague module requirements into a concrete checklist
- decide what stays internal and what callers see
- check whether an interface shape allows an efficient implementation
Example prompts for the agent
- Design the interface for a caching module with api-shape-explorer
- Run design it twice on the payment client API
- Compare different interface shapes for the file handling module
How to install api-shape-explorer
1Skills CLI (Vercel)
npx skills add zebbern/claude-code-guide --skill api-shape-explorer -a claude-code2Manually: put the files in place
~/.claude/skills/api-shape-explorer/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/api-shape-explorer/
1Skills CLI (Vercel)
npx skills add zebbern/claude-code-guide --skill api-shape-explorer -a codex2Manually: put the files in place
.agents/skills/api-shape-explorer/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add zebbern/claude-code-guide --skill api-shape-explorer -a cursor2Manually: put the files in place
.cursor/skills/api-shape-explorer/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install zebbern/claude-code-guide api-shape-explorer2Manually: put the files in place
.github/skills/api-shape-explorer/SKILL.md1Skills CLI (Vercel)
npx skills add zebbern/claude-code-guide --skill api-shape-explorer -a gemini-cli2Platform CLI
gemini skills install https://github.com/zebbern/claude-code-guide --path skills/api-shape-explorerManually: put the files in place
.devin/skills/api-shape-explorer/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add zebbern/claude-code-guide --skill api-shape-explorer -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about api-shape-explorer
How do I install api-shape-explorer in Claude?
Run npx skills add zebbern/claude-code-guide --skill api-shape-explorer -a claude-code. The skill then lives at ~/.claude/skills/api-shape-explorer/SKILL.md.
What does api-shape-explorer do?
It generates several radically different interface designs for a module using parallel sub-agents, presents each one, and compares them on simplicity, depth and ease of use.
Does it write the module code?
No. It works on interface shape only: signatures, usage examples, hidden complexity and trade-offs. You write the implementation.
Source text
SKILL.md · MIT
--- name: api-shape-explorer description: Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice". --- # Design an Interface Based on "Design It Twice" from "A Philosophy of Software Design": your first idea is unlikely to be the best. Generate multiple radically different designs, then compare. ## Workflow ### 1. Gather Requirements Before designing, understand: - [ ] What problem does this module solve? - [ ] Who are the callers? (other modules, external users, tests) - [ ] What are the key operations? - [ ] Any constraints? (performance, compatibility, existing patterns) - [ ] What should be hidden inside vs exposed? Ask: "What does this module need to do? Who will use it?" ### 2. Generate Designs (Parallel Sub-Agents) Spawn 3+ sub-agents simultaneously using Task tool. Each must produce a **radically different** approach. ``` Prompt template for each sub-agent: Design an interface for: [module description] Requirements: [gathered requirements] Constraints for this design: [assign a different constraint to each agent] - Agent 1: "Minimize method count - aim for 1-3 methods max" - Agent 2: "Maximize flexibility - support many use cases" - Agent 3: "Optimize for the most common case" - Agent 4: "Take inspiration from [specific paradigm/library]" Output format: 1. Interface signature (types/methods) 2. Usage example (how caller uses it) 3. What this design hides internally 4. Trade-offs of this approach ``` ### 3. Present Designs Show each design with: 1. **Interface signature** - types, methods, params 2. **Usage examples** - how callers actually use it in practice 3. **What it hides** - complexity kept internal Present designs sequentially so user can absorb each approach before comparison. ### 4. Compare Designs After showing all designs, compare them on: - **Interface simplicity**: fewer methods, simpler params - **General-purpose vs specialized**: flexibility vs focus - **Implementation efficiency**: does shape allow efficient internals? - **Depth**: small interface hiding significant complexity (good) vs large interface with thin implementation (bad) - **Ease of correct use** vs **ease of misuse** Discuss trade-offs in prose, not tables. Highlight where designs diverge most. ### 5. Synthesize Often the best design combines insights from multiple options. Ask: - "Which design best fits your primary use case?" - "Any elements from other designs worth incorporating?" ## Evaluation Criteria From "A Philosophy of Software Design": **Interface simplicity**: Fewer methods, simpler params = easier to learn and use correctly. **General-purpose**: Can handle future use cases without changes. But beware over-generalization. **Implementation efficiency**: Does interface shape allow efficient implementation? Or force awkward internals? **Depth**: Small interface hiding significant complexity = deep module (good). Large interface with thin implementation = shallow module (avoid). ## Anti-Patterns - Don't let sub-agents produce similar designs - enforce radical difference - Don't skip comparison - the value is in contrast - Don't implement - this is purely about interface shape - Don't evaluate based on implementation effort
© zebbern · MIT · zebbern/claude-code-guide