Use when defining or reviewing tool interfaces, skill payloads, executor-facing contracts, and structured request-response shapes in PonyBunny.
Scanned 9/11/2026
Install to Claude Code
npx -y skills add ponybunny-ai/ponybunny --skill tool-contract-design --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Tool Contract Design?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ponybunny-ai-tool-contract-design)More formats (shields.io, HTML) on the badges page.
---
name: tool-contract-design
description: Use when defining or reviewing tool interfaces, skill payloads, executor-facing contracts, and structured request-response shapes in PonyBunny.
---
# Tool Contract Design
## Use this skill when
- adding a tool
- changing a payload schema
- reviewing request/response design
- diagnosing tool mismatch bugs
## Goals
- make tool usage explicit
- reduce ambiguity
- improve validation
- support safe execution and auditability
## Process
1. Define the tool purpose.
2. Define caller expectations.
3. Define input schema.
4. Define output schema.
5. Define error schema.
6. Define side effects.
7. Define audit fields.
8. Define compatibility concerns.
## Output contract
Return:
- purpose
- request schema
- response schema
- error schema
- side-effect notes
- validation rules
- compatibility notes
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.