CtrlK
BlogDocsLog inGet started
Tessl Logo

p5js

p5.js sketches: gen art, shaders, interactive, 3D.

59

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/creative/p5js/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A richly actionable, well-sequenced production pipeline for p5.js: full executable templates, exact export commands, and a validated 6-stage workflow with feedback loops. Its weaknesses are minor padding in the creative-philosophy sections and a single broken bundle reference to a missing templates/viewer.html.

Suggestions

Add the missing templates/viewer.html file (referenced in Workflow Step 2, Step 3, and the References table) or remove the references and inline a minimal viewer scaffold.

Trim the "Creative Standard" motivational prose ("The canvas is the medium; the algorithm is the brush") and the "Creative Divergence" SCAMPER/Distance-Association frameworks, or move them to a reference file, to reduce non-instructional token weight.

Collapse the duplicated pipeline presentation (the short CONCEPT→VERIFY block and the expanded Workflow Steps cover the same stages) into one canonical sequence.

DimensionReasoningScore

Conciseness

The body is dense with genuinely p5-specific, non-obvious guidance (FES overhead, pixelDensity, Math.* in hot loops, noLoop+_p5Ready headless capture, WebGL origin gotchas) and compact tables, but the "Creative Standard" motivational prose ("The canvas is the medium; the algorithm is the brush") and the elaborate "Creative Divergence" frameworks (SCAMPER, Distance Association) are padding Claude does not need — matching anchor 3 ("Mostly efficient but includes some unnecessary explanation or could be tightened").

3 / 5

Actionability

Provides a complete copy-paste HTML scaffold, executable snippets (fbm noise, createGraphics layers, fxhash platform integration, instance mode, key bindings, noLoop+_p5Ready), and exact export commands ("node scripts/export-frames.js sketch.html --frames 300", "bash scripts/render.sh sketch.html output.mp4 --duration 30") covering PNG/GIF/MP4/SVG — fully executable guidance covering the common cases per anchor 5.

5 / 5

Workflow Clarity

Sequences the explicit 6-stage pipeline (CONCEPT → DESIGN → CODE → PREVIEW → EXPORT → VERIFY), with a dedicated Step 6 Quality Verification checklist (resolution, performance, color, edge cases) and an explicit feedback loop ("If it looks generic, go back to Step 1"), matching anchor 5's clear sequence with validation steps and error-recovery feedback.

5 / 5

Progressive Disclosure

Structure is otherwise strong: a clear overview with a References table mapping all 10 reference files and 4 scripts (all real, one level deep, well-signaled) to their contents — but "templates/viewer.html" is referenced three times in the body (Workflow Step 2/3 and the References table) yet does not exist in the bundle, a broken reference that keeps it at anchor 4 ("Good structure... minor organization gaps") rather than 5.

4 / 5

Total

17

/

20

Passed

Description

61%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 is a terse, keyword-rich noun-phrase list that names a clear niche and several natural trigger terms, but it omits any "Use when..." trigger guidance and uses no verbs, leaving the "when" and the concrete actions implicit. It is distinctive and uses natural language, yet falls short on completeness and action specificity due to its brevity.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when the user asks for p5.js sketches, creative coding, generative art, interactive visualizations, or shader effects').

Lead with concrete verbs/actions (e.g., 'Creates and exports browser-based p5.js sketches — generative art, shaders, interactive, and 3D — as HTML, PNG, GIF, MP4, or SVG.') to convert the category list into stated capabilities.

Include common synonyms users say ('creative coding', 'generative art', 'data visualization', 'canvas animation') to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Quotes "p5.js sketches" plus four concrete sub-areas ("gen art, shaders, interactive, 3D"), naming the domain and several specific output categories, but lists no verbs/actions and is not comprehensive — matching anchor 3 ("Names domain and 1-2 concrete actions, but not comprehensive") rather than 4, since the items are categories rather than the concrete actions the higher anchors exemplify.

3 / 5

Completeness

The "what" is clear (p5.js sketches across four categories) but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric guideline caps completeness at 3; not 4 because the "when" is entirely missing rather than merely weak.

3 / 5

Trigger Term Quality

Includes natural user terms — "p5.js sketches", "gen art", "shaders", "interactive", "3D" — that a user would plausibly say, giving good keyword coverage; it falls short of anchor 5 because natural synonyms like "creative coding", "generative art", "data visualization", and "animation" are absent.

4 / 5

Distinctiveness Conflict Risk

"p5.js sketches" is a specific, unambiguous niche with distinct triggers, but the metadata lists related creative-coding skills (ascii-video, manim-video, excalidraw) creating minor overlap risk, so it is mostly distinct (anchor 4) rather than the minimal-conflict anchor 5.

4 / 5

Total

14

/

20

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (559 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

12

/

16

Passed

Repository
NousResearch/hermes-agent
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.