CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/algorithmic-art/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

31%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 coherent two-phase creative workflow and includes a genuine verification section, but it is heavily padded with repeated boilerplate, and its single most important dependency — templates/viewer.html, described as the required starting point — is missing from the bundle entirely, leaving the implementation step unexecutable. The structure is monolithic where reference files should carry the detail.

Suggestions

Ship the actual templates/viewer.html and templates/generator_template.js files in the bundle (or inline the essential template skeleton in the body) — the entire implementation phase hinges on a file that does not exist.

De-duplicate the repeated "adapt to the user's brand; do not imply Anthropic affiliation" parenthetical and the restated read-the-template instructions into a single STEP 0 note, and trim the five example philosophies to one or two compact ones.

Move the UI/sidebar specification, artifact HTML scaffold, and example philosophies into a reference file (e.g., references/viewer-spec.md) so SKILL.md stays a lean overview, and integrate the verification checklist as explicit numbered checkpoints at the end of the implementation workflow.

DimensionReasoningScore

Conciseness

The body is noticeably verbose: the parenthetical "(adapt to the user's brand; do not imply Anthropic affiliation)" is repeated verbatim about eight times, the read-the-template instruction is restated across STEP 0, INTERACTIVE ARTIFACT CREATION, and RESOURCES, and the five philosophy examples carry purple prose ("painstaking frequency calibration where every ratio was carefully chosen"). This matches anchor 2 (several unnecessary explanations or padded sections); it is not 3 because the redundancy is pervasive rather than occasional.

2 / 5

Actionability

A few concrete snippets exist (randomSeed/noiseSeed setup, the control-group HTML markup, the single-file artifact skeleton), but the parameters and canvas snippets are comment skeletons, and the foundational instruction "Read templates/viewer.html using the Read tool" (SKILL.md:112) points to a file that does not exist in the bundle, making the required "LITERAL STARTING POINT" unexecutable. This matches anchor 2 (high-level hints but missing the specific steps to execute); it is not 3 because the workflow's central step cannot be performed and most code is placeholder.

2 / 5

Workflow Clarity

The two-phase sequence (algorithmic philosophy .md, then p5.js HTML artifact) is clearly laid out, with a five-step CREATIVE PROCESS recap, and a trailing "Template status and verification" section supplies a verification checklist ("Verify controls, seed replay at a fixed simulation step, mobile layout and exported PNG"). However, validation is a trailing note rather than an integrated checkpoint with feedback loops, and the missing template breaks the sequence's critical step. Matches anchor 3 (steps listed but validation gaps, checkpoints implicit); not 4 because of these gaps.

3 / 5

Progressive Disclosure

Scored against the actual bundle structure: no templates/, references/, scripts/, or assets/ directories exist, yet templates/viewer.html and templates/generator_template.js are repeatedly cited as REQUIRED reading — broken references to the skill's core dependency. Additionally, the ~420-line body inlines UI specifications, five example philosophies, and full artifact scaffolding that belong in separate reference files. Matches anchor 2; not 3 because the clearly-signaled references are nonexistent and the monolithic inline bulk should be split out.

2 / 5

Total

9

/

20

Passed

Description

42%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 states a partially concrete "what" (three output file types with purposes) wrapped in an abstract definitional first sentence, but provides no "when" guidance and omits the natural vocabulary of its own domain (generative art, p5.js, creative coding). It is moderately distinct as a niche yet weakly triggered. Adding an explicit trigger clause and the domain's natural terms would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for generative art, creative coding, algorithmic or p5.js artwork, or animated/seeded visual pieces."

Replace the definitional opening ("Algorithmic philosophies are computational aesthetic movements...") with action verbs describing what the skill does, e.g. "Creates generative art movements as written philosophies (.md) and implements them as interactive p5.js artworks (.html viewer + inline .js algorithm)."

Include the natural trigger terms of the domain — "generative art", "creative coding", "p5.js", "seeded randomness" — so users' phrasing actually matches the description.

DimensionReasoningScore

Specificity

"Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms)" lists three concrete output types, but the opening sentence "Algorithmic philosophies are computational aesthetic movements that are then expressed through code" is abstract definitional language with no creation verbs or named technology (e.g., p5.js, generative art). This matches anchor 3 (names domain and 1-2 concrete actions, not comprehensive); it is not 4 because the what is padded with definition rather than covering more concrete actions.

3 / 5

Completeness

A "what" is present (output .md philosophy, .html interactive viewer, and .js generative algorithm files), but there is no "Use when..." clause or any equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Matches anchor 3 (clear what, when missing); not 4 because "when" is not even weakly implied.

3 / 5

Trigger Term Quality

The only keywords present are "algorithmic", "philosophies", "code", and the file extensions .md/.html/.js; the natural phrases a user would say for this domain ("generative art", "creative coding", "p5.js", "make art with code") are entirely absent. This fits anchor 2 (missing the natural phrases users say); it is not 3 because, unlike "Works with PDF files", even the core user-facing domain term (art) never appears.

2 / 5

Distinctiveness Conflict Risk

"Algorithmic philosophies" is a distinctive niche, but ".html files (interactive viewer)" and generic "expressed through code" overlap with general web-development and creative-coding skills, and the absence of any trigger terms leaves the overlap unresolved. Matches anchor 3 (somewhat specific but could still overlap with similar skills); not 4 because without distinct triggers the conflict risk stays real.

3 / 5

Total

11

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

sickn33/agentic-awesome-skills

Path

skills/algorithmic-art/SKILL.md

Reviewed

Table of Contents

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.