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

75%

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

50%

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

The skill provides a clear creative workflow with useful code and UI scaffolding, but it is markedly verbose with repeated craftsmanship framing and depends on template files that are absent from the bundle. Tightening the prose and supplying the referenced templates would lift all four dimensions.

Suggestions

Remove the repeated craftsmanship framing ('meticulously crafted', 'master-level', 'deep expertise', repeated CRITICAL blocks) — state the quality bar once; this alone would tighten the body substantially.

Add the referenced templates/viewer.html and templates/generator_template.js to a bundle directory (or drop the references), so the 'STEP 0: READ THE TEMPLATE' and RESOURCES sections point to real files.

Add an explicit validation checkpoint (e.g., 'open the artifact and confirm seed controls + parameters respond before finalizing output') to close the workflow's verification gap.

Dimension	Reasoning	Score
Conciseness	Body is 404 lines and repeatedly restates the same craftsmanship framing ('meticulously crafted', 'master-level', 'deep expertise') and re-explains the 'read the template first' instruction multiple times; it could be tightened substantially without losing meaning, hence not score 3.	2 / 3
Actionability	Concrete code snippets exist (seeded randomness, params object, canvas setup, sidebar HTML scaffold), but the core algorithm is left abstract and the body repeatedly instructs use of templates/viewer.html and generator_template.js that are not present in the bundle, so guidance is not fully executable/copy-paste ready.	2 / 3
Workflow Clarity	The multi-step process (philosophy → conceptual seed → p5.js → artifact) is sequenced, but it depends on a referenced template file that does not exist and offers no validation/verification checkpoint before output, leaving the sequence present but with gaps.	2 / 3
Progressive Disclosure	Content is a single monolithic 404-line SKILL.md that should be split, and it references external template files (templates/viewer.html, generator_template.js) that are not present in references/scripts/assets, so navigation is signaled but the bundle structure does not support it.	2 / 3
	Total	8 / 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.

The description is specific, trigger-rich, complete, and distinctive — it cleanly states the capability and when to invoke it using natural terms a user would actually say. Third-person voice and the explicit 'Use this when' clause are both present. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration' and 'Create original algorithmic art rather than copying existing artists' work' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (creating p5.js algorithmic art with seeded randomness and parameter exploration) and when via the explicit 'Use this when users request...' clause.	3 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'creating art using code', 'generative art', 'algorithmic art', 'flow fields', 'particle systems'.	3 / 3
Distinctiveness Conflict Risk	Narrow niche (p5.js generative art) with distinct triggers and copyright guidance, making it unlikely to fire for unrelated 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: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/claude-science/algorithmic-art/SKILL.md
Commit: f618458

Reviewed: about 13 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.