Skip to main content
skill CX Codex

principle-experience-first — Claude Code skill for UX-first product

A principle skill that shifts priority toward the user when product, UX, or feature-scope tradeoffs come up. Useful when deciding what to cut.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add backnotprop/pstack --skill principle-experience-first -a claude-code
Open on GitHub

What principle-experience-first does

The skill sets one rule: when implementation convenience conflicts with user delight, choose delight. Every feature, control, and option must be justified, and three polished features beat ten rough ones.

The user is not only the end user of a UI. For a library or internal API, it's the colleague who imports it. The engineer who maintains the code next is a user too. The skill requires weighing their experience the same way and explaining impact from their perspective.

Prototyping gets explicit attention: design decisions are cheaper in throwaway HTML than in production code. The core loop matters as well, since every feature should serve the central workflow or get out of the way.

disable-model-invocation: true in the frontmatter means the model will not trigger the skill by itself. You call it explicitly when a product or UX tradeoff appears.

What it helps with

  • decide what to sacrifice when cutting scope
  • stop implementation convenience from overriding user experience
  • account for the maintainer's perspective in design choices
  • validate a design hypothesis before production code

Example prompts for the agent

  • Apply principle-experience-first to choosing between two feature variants
  • Which features should I cut to make the core flow better?
  • Evaluate this decision from the perspective of the library user

How to install principle-experience-first

1Skills CLI (Vercel)

npx skills add backnotprop/pstack --skill principle-experience-first -a claude-code

2Manually: put the files in place

~/.claude/skills/principle-experience-first/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/principle-experience-first/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about principle-experience-first

How do I install principle-experience-first in Claude Code?

Run npx skills add backnotprop/pstack --skill principle-experience-first -a claude-code. The skill file lands at ~/.claude/skills/principle-experience-first/SKILL.md.

What does principle-experience-first do?

It shifts priority toward the user when product, UX, or scope decisions come up. Ship fewer polished features rather than more rough ones, and justify every feature and option.

Why does the skill not run automatically?

The description sets disable-model-invocation: true, so the model does not invoke it on its own. Ask for it explicitly when a relevant tradeoff shows up.

Source text

SKILL.md · MIT
---
name: principle-experience-first
description: "Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones."
disable-model-invocation: true
---

# Experience First

When implementation convenience conflicts with user delight, choose delight.

- Every feature, control, and option must be justified
- Ship less, ship better (polished experience with three features beats rough one with ten)
- Prototype before committing (design decisions are cheaper in throwaway HTML than production code)
- Get the details right (transitions, alignment, spacing, feedback, error states)
- Tighten the core loop (every feature should serve the central workflow or get out of the way)

The user is whoever consumes the work. For a UI that is the end user. For a library or an internal API it is the colleague who imports it. The engineer who maintains the code next is a user too. Weigh their experience the same way, and explain impact from their perspective.

Foundations should serve the experience. Foundational thinking governs the *sequence* of work. This principle governs the *target*.

© backnotprop · MIT · backnotprop/pstack

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set44

maintain-verification-skill Keep a project's verification guide and feature map aligned with its code. The skill checks each mapped feature against the live app and flags confirmed fixes. CX Codex +1 5,200installs no-comments The skill spawns a comment-sicko subagent, deletes comments that explain nothing, and asks you before encoding real constraints as checks. CX Codex +1 5,200installs teach The skill explains codebases and architecture plainly without walls of text. It runs the how and why skills to combine implementation mechanics with design rationale. CX Codex +1 5,100installs tdd This skill makes the agent write a failing regression test for a bug before touching production code. It only kicks in when a cheap test path exists. CX Codex +1 5,100installs principle-separate-before-serializing-shared-state Architectural guideline for concurrent actors: eliminate shared mutable state across files or keys first, resorting to locks only when a single writer is strictly required. CX Codex +1 5,100installs principle-attack-the-premise This skill tests the shared premise behind repeated failed fixes. Use it before writing another fix that hits the same gate. CX Codex +1 5,100installs principle-foundational-thinking A principle set for the stage before logic: pick core types and data structures, order the scaffold, check what concurrent actors share. CX Codex +1 5,100installs correct Finds repeated mistakes made by coding agents and makes them impossible through architecture, types, linters, or tests. Useful when agents keep making the same wrong edits. CX Codex +1 4,200installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor