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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

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

Quality

Content

30%

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

The skill has a clear high-level workflow and some executable p5.js snippets, but it is verbose (repeatedly hammering craftsmanship rhetoric) and critically references templates/viewer.html and generator_template.js as required starting points that do not exist in the bundle. Missing validation steps and the broken template references drag down actionability and progressive disclosure.

Suggestions

Add the missing templates/viewer.html and templates/generator_template.js to the bundle (or replace the 'REQUIRED STARTING POINT' instructions with a self-contained inline template), since the skill cannot function as written without them.

Cut the repeated craftsmanship/master-level rhetoric (it appears in CRITICAL GUIDELINES, ESSENTIAL PRINCIPLES, CRAFTSMANSHIP REQUIREMENTS, and RESOURCES) to one concise statement to respect the context-window budget.

Add explicit validation checkpoints to the workflow — e.g., after generating the artifact, verify it loads, that seed navigation works, and that the same seed reproduces identical output — rather than only listing these as requirements.

Dimension	Reasoning	Score
Conciseness	The ~400-line body is heavily padded — repeating 'craftsmanship/master-level/meticulously crafted' directives many times and restating the fixed-vs-variable and template instructions across STEP 0, INTERACTIVE ARTIFACT CREATION, and RESOURCES sections instead of assuming Claude's competence.	1 / 3
Actionability	Provides executable seed/param/setup snippets and a parameter shape, but the central 'start from templates/viewer.html' instruction is non-actionable because that file does not exist in the bundle, leaving the literal starting point missing.	2 / 3
Workflow Clarity	The philosophy→implementation sequence is clear and numbered, but there are no validation checkpoints (e.g., verify the artifact runs, verify seed reproducibility) despite the output being a generated artifact; checks are mentioned as goals ('Same seed ALWAYS produces identical output') but not as steps to verify.	2 / 3
Progressive Disclosure	The body repeatedly designates templates/viewer.html and templates/generator_template.js as a REQUIRED STARTING POINT, yet neither file is present in templates/ — a broken one-level reference with no valid bundle to defer to, the worst-case anchor.	1 / 3
	Total	6 / 12 Passed

Description

100%

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 description: specific, in third person, with a clear 'Use when...' clause and natural trigger terms covering the generative-art niche. The copyright-avoidance note is a useful distinguishing detail without becoming fluff.

Dimension	Reasoning	Score
Specificity	Names the medium (p5.js), the mechanism (seeded randomness, interactive parameter exploration), and concrete deliverables (.md, .html, .js files); matches the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' (creating algorithmic art with p5.js + seeded randomness + interactive parameters) and 'when' via the 'Use this when users request...' clause, satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Natural user phrasing is well covered — 'creating art using code, generative art, algorithmic art, flow fields, or particle systems' are terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The p5.js generative/algorithmic-art niche with specific triggers (flow fields, particle systems) is distinct and unlikely to collide with other skills.	3 / 3
	Total	12 / 12 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: ThinkInAIXYZ/deepchat
Path: resources/skills/algorithmic-art/SKILL.md
Commit: b8dbc89

Reviewed: about 7 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.