Proven skills / Compare

Design vs Testing · both proven

algorithmic-art vs test-driven-development

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.

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Category
Design
Source
anthropics/skills
License
Not stated
Proof model
claude-opus-5-5
Brief
“Make a generative art piece called Tidewater: a single HTML page with a full-window canvas that draws slow, layered flow-field lines in a deep sea palette, seeded so the same seed always gives the same picture. Include a small control panel to change the seed, the line density and the palette, and a button to save the current frame as a PNG. Use p5.js from a CDN.”
Skill commit
dbd4588
Without the skillWith algorithmic-art
⇆
Without, runWith algorithmic-art, run3 independent runs per side, none selected by hand.

Download the with-skill page

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

Category
Testing
Source
obra/superpowers
License
MIT
Proof model
claude-opus-5-5
Brief
“Implement a function that parses a cron expression (the standard five fields) and returns the next run time after a given date, in TypeScript. Present the work as a single HTML page with two columns: the test file on the left and the implementation on the right, each in a code block, with a short note at the top on the order you did things in and anything you decided not to support.”
Skill commit
bb92a77
Without the skillWith test-driven-development
⇆
Without, runWith test-driven-development, 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 algorithmic-art or alternatives to test-driven-development.