Product Design — Action Scope, Undo and Recovery

When to use it

Supply a product flow, brief or disputed interaction decision. Produces rule-linked decisions, action scope/consequence definitions, state coverage and unresolved product questions. Useful for bulk deletion, undo, interrupted tasks and choosing controls before implementation. This decision layer is distinct from the existing agent-trust audit and rendered browser checks. Does not assess investment priority, style or build UI, certify accessibility or supply final copy; sibling skills handle those tasks. Keep references/rules.md and all mode references. Source documentation reviewed; not installed or runtime-tested. GitHub stars are repository-wide, not skill-specific.

Compatible agents

CodexClaude Code

Installation

With Node.js available, run `npx skills add mblode/agent-skills --skill product-design --agent codex claude-code`. Choose scope and intended host, retain the complete product-design folder including references/, and start a fresh session. The upstream README also documents collection-wide installation.

Review the source and instructions before installing in your agent.

License

MIT

Last checked Nov 4, 2026.

Pair this skill with a visual reference

A skill guides how your agent works; a design reference shows the direction you want. Choose an example for a specific job, such as the headline hierarchy or form layout, and keep your project's existing design rules explicit.

Start with design references you can inspect, then use our guide to briefing an AI coding agent to turn observations into requirements. If you need implementation components, compare UI libraries for your stack.

These pages are public. Browsing a skill does not install it, and TastefulKit's design-reference MCP tools do not search the AI-skill directory.