From supertools
Use BEFORE any creative or implementation work — features, components, refactors, new functionality. Turns ideas into approved specs through one-question-at-a-time dialogue. Hard-gates implementation until a design is approved.
How this skill is triggered — by the user, by Claude, or both
Slash command
/supertools:brainstormingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turn an idea into an approved spec before any code is written.
Turn an idea into an approved spec before any code is written.
Do NOT write code, scaffold files, or invoke any implementation skill until you have presented a design AND the user has explicitly approved it. This applies even to "simple" projects. A todo list, a one-line script, a config tweak — all of them. The design can be short, but it must exist and be approved.
docs/supertools/specs/YYYY-MM-DD-<topic>.md after the user approves.writing-plans to produce the implementation plan.Before refining details, check scope. If the request describes multiple independent subsystems ("build a platform with chat, billing, and analytics"), say so immediately and propose splitting into separate specs — one per subsystem. Each spec should produce something working on its own.
Follow existing patterns. Where existing code has problems that affect the work (a file too big, tangled responsibilities), include targeted fixes — but stay focused on the goal. No unrelated refactoring.
After the user approves the written spec, the ONLY skill you invoke
next is writing-plans. Do not jump to implementation skills directly.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub yoshana/supertools --plugin supertools