algorithmic-art

Algorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms).

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/algorithmic-art/SKILL.md

Quality

Content

48%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 skill lays out a clear, well-sequenced creative workflow with usable code scaffolding, but it is heavily padded with repetition and relies on template files that are not present in the bundle. Tightening the prose and supplying the missing templates would substantially improve it.

Suggestions

Include the referenced templates/viewer.html and templates/generator_template.js in the bundle, or remove the STEP 0 'read the template first' dependency and inline a complete minimal template.

Cut the repeated craftsmanship-emphasis directives and the multiple restatements of fixed-vs-variable; state each once.

Move the detailed artifact/HTML sidebar specification into a reference file and keep SKILL.md as an overview with one-level-deep pointers.

Dimension	Reasoning	Score
Conciseness	The ~410-line body is noticeably verbose: craftsmanship emphasis is explicitly repeated ('Emphasize craftsmanship REPEATEDLY ... repeat phrases like ...'), the fixed-vs-variable distinction is restated four or more times, and it explains p5.js basics Claude already knows (setup/draw, createCanvas, randomSeed/noiseSeed).	2 / 5
Actionability	Provides concrete scaffolding (seed setup, params object, canvas skeleton, HTML artifact shell, sidebar control-group HTML), but the declared 'LITERAL STARTING POINT' templates/viewer.html does not exist in the bundle and the core algorithm guidance is abstract, leaving key details missing.	3 / 5
Workflow Clarity	A clear sequenced workflow (Philosophy Creation -> Deducing Conceptual Seed -> p5.js Implementation -> Interactive Artifact Creation) with an upfront two-step summary; no validation checkpoints, but the task is non-destructive generative output so none are required.	4 / 5
Progressive Disclosure	Section structure and a signaled RESOURCES section exist, but the referenced bundle files (templates/viewer.html, templates/generator_template.js) are absent from the bundle, and large amounts of artifact/philosophy specification are inlined that would belong in separate reference files.	3 / 5
	Total	12 / 20 Passed

Description

53%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.

The description conveys a distinctive niche and concrete output file types, but it is written in jargon rather than natural user trigger phrases and omits any 'when to use' guidance. It is serviceable but not comprehensive.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks for generative art, p5.js sketches, creative coding, or algorithmic/interactive visuals.'

Replace jargon ('computational aesthetic movements') with terms users actually say ('generative art', 'p5.js', 'algorithmic art').

Lead with the concrete actions (create a philosophy, build a self-contained interactive p5.js viewer) before the abstract framing.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete output types ('Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms)') but the only action is 'Output ... files', which is minimal rather than comprehensive.	3 / 5
Completeness	Clearly states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes some relevant keywords ('generative algorithms', 'interactive viewer') but relies on jargon ('computational aesthetic movements', 'algorithmic philosophies') and misses the natural phrases users say such as 'generative art', 'p5.js', or 'creative coding'.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (seeded generative p5.js art with an interactive viewer) with minimal overlap risk against unrelated skills, though it could brush against other art/creative-coding skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/algorithmic-art/SKILL.md
Commit: 900c504

Reviewed: 1 hour 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.