Testing vs Design · both proven

receiving-code-review vs web-artifacts-builder

Both skills were run through Claude twice: once on a fixed brief without the skill, once with it. The briefs differ because each is written for the job the skill claims to do, so compare each skill against its own baseline, then decide which difference matters for your work. They are in different categories, so this is a choice of job, not a head-to-head on the same job.

receiving-code-review

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Category: Testing
Source: obra/superpowers
License: MIT
Proof model: claude-opus-5-5
Brief: “I received this code review on my pull request that adds caching to our product API. Decide what to do with each comment and present your responses and planned changes as a single HTML page. 1. "Cache TTL of 24h is too long, prices change during the day." 2. "Use Redis instead of the in-memory Map so all 4 instances share the cache." 3. "Rename getProd to getProduct." 4. "You should rewrite this whole module in TypeScript." 5. "The cache key ignores the currency query param, so EUR users can get USD prices." 6. "Add a test."”
Skill commit: 2ce8aa1

Without the skillWith receiving-code-review

⇆

Without, runWith receiving-code-review, run3 independent runs per side, none selected by hand.

Download the with-skill page

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Category: Design
Source: anthropics/skills
License: Not stated
Proof model: claude-opus-5-5
Brief: “Build a single-page trip planner for a four-day weekend in Lisbon as one self-contained HTML file: a day-by-day itinerary with editable stops, a running budget that totals by category, a packing checklist with progress, and a simple map panel drawn with inline SVG that highlights the selected day's stops. State should live in the page and update everywhere when anything changes.”
Skill commit: dbd4588

Without the skillWith web-artifacts-builder

⇆

Without, runWith web-artifacts-builder, run3 independent runs per side, none selected by hand.

Download the with-skill page

We don’t pick a winner for you: the pages are the evidence. Both proofs can be repeated with the brief, model and commit shown above. See alternatives to receiving-code-review or alternatives to web-artifacts-builder.