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.

1.80x

Quality

65%

Does it follow best practices?

Impact

54%

1.80x

Average score across 10 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/anthropic-algorithmic-art/SKILL.md

The canonical home for this skill is algorithmic-art in anthropics/skills

Quality

Content

42%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and contains genuine code and a clear creative workflow, but it is heavily padded with repetition and poetic prose, relies on placeholder code and template files that are missing from the bundle, and lacks any output-validation checkpoint.

Suggestions

Collapse the repeated 'expert craftsmanship' emphasis and the four restatements of 'read the template first' into a single statement each; remove poetic filler to cut the body substantially.

Provide the referenced templates/viewer.html and templates/generator_template.js as actual bundle files (or inline their essential structure) so STEP 0's 'Read templates/viewer.html using the Read tool' is not a broken reference.

Add an explicit validation step (e.g., open the generated HTML, confirm the canvas renders and seed/parameter controls respond) before declaring the artifact complete.

Dimension	Reasoning	Score
Conciseness	The ~400-line body is noticeably verbose: the 'expert craftsmanship / meticulously crafted' theme is repeated six-plus times, the 'read the template first' instruction is restated four times, and poetic filler ('Beauty lives in the process, not the final frame') pads sections without adding actionable guidance.	2 / 5
Actionability	Real code is given (randomSeed/noiseSeed, params object, setup/draw, HTML skeleton, sidebar control-group markup), but core sections are placeholder-laden ('// Your generative algorithm', '// ALL p5.js code inline here') and the skill leans on a template file that is absent from the bundle, leaving execution incomplete.	3 / 5
Workflow Clarity	A clear two-phase sequence exists (philosophy creation -> deduce conceptual seed -> read template -> implement -> interactive artifact -> variations) with a STEP 0 checkpoint, but there is no validation step confirming the produced HTML artifact actually runs or renders.	3 / 5
Progressive Disclosure	Section structure is reasonable and references are clearly signaled in a RESOURCES section, but the document is largely a monolithic inline wall of examples and skeletons, and the referenced supporting files (templates/viewer.html, templates/generator_template.js) do not exist in the bundle.	3 / 5
	Total	11 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-formed description that clearly states what the skill does and when to invoke it, with a tight niche and natural trigger terms. Minor specificity and synonym-coverage gaps keep it just short of perfect.

Dimension	Reasoning	Score
Specificity	Names the domain (algorithmic art, p5.js) and several concrete actions ('seeded randomness', 'interactive parameter exploration', 'create original algorithmic art'), but the exact deliverables (.md/.html/.js outputs) are absent, leaving minor gaps.	4 / 5
Completeness	It explicitly answers both what ('Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration') and when ('Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems') with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Use this when' clause surfaces natural terms users would say ('generative art', 'algorithmic art', 'flow fields', 'particle systems', 'creating art using code'); common synonyms like 'creative coding' and 'procedural art' are omitted, so it is not quite comprehensive.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (generative/algorithmic art via p5.js) with distinct triggers (flow fields, particle systems, generative art) that are unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: boisenoise/skills-collections
Path: skills/anthropic-algorithmic-art/SKILL.md
Commit: 19c310e

Reviewed: about 17 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.