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

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

38%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 lays out a clear creative workflow with usable code snippets, but it is padded with repeated craftsmanship rhetoric, lacks any validation checkpoints, and critically depends on template files that are not present in the bundle, breaking its foundational starting step.

Suggestions

Ship the referenced bundle files (templates/viewer.html, templates/generator_template.js) or, if absent, inline the minimal template skeleton directly so the "LITERAL STARTING POINT" step is actually executable.

Add explicit validation checkpoints to the workflow, e.g. "Open the HTML in a browser and confirm it renders", "Re-run with the same seed and confirm identical output", and "Verify every parameter has a working UI control".

Cut the repeated craftsmanship rhetoric (it appears in CRITICAL GUIDELINES, ESSENTIAL PRINCIPLES, and CRAFTSMANSHIP REQUIREMENTS) to a single concise statement to reduce token padding.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: craftsmanship rhetoric ("meticulously crafted", "master-level", "top of their field", "EXPERT CRAFTSMANSHIP") is restated across the guidelines, principles, and requirements sections, and ALL-CAPS directives repeat the same idea ("The algorithm flows from the philosophy, not from a menu of options") multiple times.	2 / 5
Actionability	Provides executable code snippets (seeded randomness, params object, setup/draw, HTML skeleton, control-group markup), but the foundational instruction "Read templates/viewer.html... Use that file as the LITERAL STARTING POINT" references a file absent from the bundle, and the core algorithm guidance is abstract ("consider using...") rather than concrete.	3 / 5
Workflow Clarity	A clear two-step sequence (Philosophy Creation → p5.js Implementation) with a numbered creative-process summary is present, but there are no validation checkpoints (no "verify the artifact opens", no "confirm the seed reproduces identically") despite reproducibility being a stated requirement.	3 / 5
Progressive Disclosure	References to templates/viewer.html and templates/generator_template.js are clearly signaled (STEP 0, RESOURCES) but those files do not exist in the bundle, and the ~400-line body inlines content (HTML skeleton, philosophy examples, parameter structure) that belongs in separate files.	2 / 5
	Total	10 / 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 distinct niche and lists concrete output artifacts, but it leans on abstract jargon ("computational aesthetic movements") over natural trigger terms and omits any "Use when..." guidance, capping completeness and trigger quality at the midpoint.

Suggestions

Add an explicit "Use when..." clause naming natural triggers, e.g. "Use when the user asks to create generative art, p5.js sketches, or interactive algorithmic visuals."

Replace abstract jargon ("Algorithmic philosophies are computational aesthetic movements") with concrete action verbs a user would recognize ("Create", "Generate", "Build"), and include synonyms like "generative art", "creative coding", and "p5.js".

Vary the action verbs beyond the repeated "Output" to better signal the range of capabilities (e.g., author a philosophy, build an interactive viewer, implement a generative algorithm).

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete output artifacts ("Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms)"), but all share the single verb "Output" and the opening sentence is abstract/definitional rather than action-varied.	3 / 5
Completeness	Provides a clear "what" (output philosophy/viewer/algorithm files) but no "Use when..." clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Contains some relevant keywords ("generative algorithms", "interactive viewer", file extensions) but misses the natural phrases users actually say ("generative art", "p5.js", "creative coding"), and the dominant language ("computational aesthetic movements") is abstract jargon rather than trigger terms.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (generative algorithmic art via p5.js artifacts) with low conflict risk, but the abstract trigger phrasing keeps it from the crisp, minimal-overlap level 5.	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: sickn33/antigravity-awesome-skills
Path: skills/algorithmic-art/SKILL.md
Commit: 1f67c44

Reviewed: about 15 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.