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.

Quality

70%

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 ./configs/microservice/bff-service/configs/agent-skills/claude-science/algorithmic-art/SKILL.md

Quality

Content

52%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-sequenced with concrete code examples, but it is heavily padded with repeated craftsmanship rhetoric and references template files that are absent from the bundle, breaking its core 'read the template first' instruction. Tightening the prose and actually shipping the referenced template files would materially raise quality.

Suggestions

Ship the referenced bundle files: create templates/viewer.html and templates/generator_template.js so the 'STEP 0: READ THE TEMPLATE FIRST' checkpoint resolves to real files, or remove the references and inline the template structure once.

Cut the repeated craftsmanship emphasis — the phrases 'meticulously crafted', 'master of computational aesthetics', and 'countless iterations' appear many times; state the quality bar once and move on.

Deduplicate the FIXED/VARIABLE and 'read the template' guidance, which is restated across STEP 0, INTERACTIVE ARTIFACT CREATION, and RESOURCES; consolidate into a single section to recover token budget.

Dimension	Reasoning	Score
Conciseness	The ~400-line body is noticeably verbose: craftsmanship framing is repeated many times ('meticulously crafted', 'master of computational aesthetics', 'painstaking optimization'), the STEP 0 'read the template' instruction and the FIXED/VARIABLE sidebar breakdown are each restated multiple times, and poetic philosophy prose pads sections without adding executable value.	2 / 5
Actionability	Provides mostly executable guidance — seeded-randomness snippet, params object, canvas setup, sidebar control-group HTML, and a full single-artifact HTML skeleton — with minor gaps where the core algorithm body is left as placeholders ('// Your generative algorithm').	4 / 5
Workflow Clarity	Clear multi-step sequence (philosophy → conceptual seed → p5.js implementation → interactive artifact) with explicit checkpoints like 'STEP 0: READ THE TEMPLATE FIRST' and 'Pause to gather thoughts'; the 100-variation batch is low-risk and non-destructive so the missing-validation cap does not apply, but no explicit verify step keeps it at 4 rather than 5.	4 / 5
Progressive Disclosure	References are clearly signaled in a RESOURCES section, but the referenced bundle files (templates/viewer.html and templates/generator_template.js) do not exist in the bundle — no templates/, references/, scripts/, or assets/ directories are present — so the skill's primary checkpoint ('Read templates/viewer.html using the Read tool') points at a missing file, and large inlined blocks (HTML skeleton, sidebar structure) belong in those template files.	2 / 5
	Total	12 / 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 description that clearly states what the skill does and when to invoke it, using natural trigger terms in third-person voice. Minor room to broaden synonym coverage, but it cleanly satisfies the what/when requirement.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete capabilities — 'Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration' — with only minor coverage gaps; not quite a comprehensive multi-action list so it stops short of 5.	4 / 5
Completeness	Explicitly answers both 'what' (creating algorithmic art with p5.js, seeded randomness, 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	Good natural-term coverage with 'creating art using code, generative art, algorithmic art, flow fields, or particle systems', but misses common synonyms (e.g. 'procedural art') and any file extensions, so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (generative/algorithmic art via p5.js) with distinct triggers like 'flow fields' and 'particle systems' that minimize overlap with other 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: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/claude-science/algorithmic-art/SKILL.md
Commit: 030c20b

Reviewed: 20 days 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.