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,...
Install with Tessl CLI
npx tessl i github:boisenoise/skills-collections --skill algorithmic-art69
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies its niche (p5.js generative art) and includes an explicit 'Use when' clause with natural trigger terms. The main weakness is that the capabilities section could be more specific about concrete actions beyond the general techniques mentioned.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (algorithmic art, p5.js) and mentions specific techniques (seeded randomness, interactive parameter exploration), but doesn't list multiple concrete actions like 'create flow fields, generate patterns, export images'. | 2 / 3 |
Completeness | Clearly answers both what (creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration) and when (explicit 'Use this when...' clause with specific trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes excellent natural keywords users would say: 'art using code', 'generative art', 'algorithmic art', 'flow fields'. The ellipsis suggests more terms follow, and these cover common variations users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche combining p5.js, generative/algorithmic art, and seeded randomness. Unlikely to conflict with general coding skills or other art tools due to specific technology and domain focus. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a creative framework for generative art but suffers from severe verbosity and redundancy. The same concepts (craftsmanship, algorithmic philosophy, template usage) are repeated multiple times throughout. While the workflow is identifiable, the content would benefit greatly from condensing the philosophy examples, removing redundant explanations, and providing more concrete, executable code rather than abstract guidance.
Suggestions
Reduce content by 60-70% by eliminating redundant mentions of 'craftsmanship', 'algorithmic philosophy', and template instructions - state each concept once clearly
Replace the abstract 'express the philosophy through code' guidance with 2-3 complete, executable algorithm examples that demonstrate different philosophy types
Move the 5 philosophy examples to a separate EXAMPLES.md file and reference it, keeping only 1-2 inline for quick reference
Add explicit validation checkpoints: 'Before proceeding to implementation, verify the philosophy includes: [checklist]' and 'Test the artifact by: [specific steps]'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines with significant redundancy. Concepts like 'craftsmanship' and 'algorithmic philosophy' are repeated excessively. Many sections explain things Claude already knows (what p5.js is, how to structure HTML, basic canvas setup). The philosophy examples alone take up substantial space that could be condensed. | 1 / 3 |
Actionability | Contains some executable code snippets (seeded randomness, canvas setup) but much is pseudocode or incomplete. The actual algorithm implementation is left vague ('express the philosophy through code') rather than providing concrete, copy-paste ready examples. References external template files that must be read separately. | 2 / 3 |
Workflow Clarity | The two-step process (philosophy creation → implementation) is clearly stated, and Step 0 emphasizes reading the template first. However, validation checkpoints are missing - there's no verification that the philosophy is complete before proceeding, no testing steps for the generated HTML, and no error recovery guidance for common issues. | 2 / 3 |
Progressive Disclosure | References external files appropriately (templates/viewer.html, templates/generator_template.js) with clear signaling. However, the main content is a monolithic wall of text with repetitive sections. The philosophy examples, implementation details, and UI requirements could be split into separate reference files rather than inline. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
Table of Contents
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.