principle-exhaust-the-design-space

An agent skill by cursor, from cursor/plugins. Tags: analysis, architecture, design, prototyping, ui-ux.

What it does

Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add cursor/plugins --skill principle-exhaust-the-design-space

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/pstack/skills/principle-exhaust-the-design-space ~/.claude/skills/principle-exhaust-the-design-space

Safety box score

Grade A, minimal risk: 7 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a short design-work prompt: it tells the agent to explore 2–3 prototype variants for novel UI or architecture decisions before choosing one. It does not contain commands, network access, secret handling, or privileged/system changes; the main effect is extra local iteration and file churn inside the project.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, scripts, or code execution are present in `SKILL.md`.
Network access	0 (none)	The file contains no download, upload, API call, or remote-host instructions.
Filesystem reach	1 (low)	It asks the agent to "Build 2-3 competing prototypes and compare side by side before committing," which implies editing files in the workspace, but not outside it.
Secrets & credentials	0 (none)	There is no request to access tokens, passwords, key files, or other credentials.
Privilege & persistence	0 (none)	Nothing in the skill requires sudo, global installs, services, or OS/shell configuration changes.
Instruction hijack surface	0 (none)	There are no instructions to ignore safeguards, hide behavior, follow remote text, or otherwise override agent rules.
Irreversible actions	1 (low)	It directs the agent to independently generate and compare multiple prototypes for design decisions, but it does not authorize external actions like deploys, posts, or payments.
Transparency	0 (none)	The skill is a single readable markdown file; there are no binaries, minified assets, or decoded-at-runtime payloads.

Before installing

Read `SKILL.md` and confirm you want a prototype-heavy workflow for design choices.
Use it first on a scratch branch so the extra prototype variants stay isolated.
Check whether your repo has a convention for keeping discarded prototypes out of commits.

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository: cursor/plugins (all skills from this repository)
Path: pstack/skills/principle-exhaust-the-design-space/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

principle-foundational-thinking — Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share.
principle-redesign-from-first-principles — Apply when integrating a new requirement into an existing design.
app-platform-designer — Transform natural language application descriptions into production-ready DigitalOcean App Platform specifications.
domain-modeling — Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
interaction-design-board — Generate several genuinely different, runnable HTML interaction prototypes for one product surface, combine them in an interactive Design Board.
prototype — Build multiple genuinely different versions of a UI piece you describe.