skill-builderlisted

## What This Skill Does Guides the creation and optimization of Claude Code skills using official best practices from the Claude Code documentation. Use this whenever: - Building a new skill from scratch - Deciding on advanced features (subagent execution, hooks, dynamic context, etc.) - Troubleshooting a skill that isn't working correctly To **audit or optimise an existing skill**, use the `library-audit` skill instead — it owns the per-skill hygiene lenses (visibility / determinism / composability) and the library-wide review. For frontmatter fields and advanced patterns, follow the official Claude Code skills documentation (the `claude-code-guide` agent can answer specifics). ## Mode 1: Build a New Skill When building a new skill, run the **Discovery Interview** first. Do NOT start writing files until discovery is complete. ### Discovery Interview Ask questions using AskUserQuestion, one round at a time. Each round covers one topic. Move to the next round only after the user answers. Keep going until you're 95% confident you understand the skill well enough to build it without further clarification. **Round 1: Goal & Name** - What does this skill do? What problem does it solve or what workflow does it automate? - What should we call it? (Suggest a name based on their answer -- lowercase, hyphens, max 64 chars) **Round 2: Trigger** - What would someone say to trigger this? (Get 2-3 natural language phrases) - Should it be user-only (`/slash-command`), Claude-auto-