CtrlK
BlogDocsLog inGet started
Tessl Logo

p5js

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

56

Quality

67%

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

77%

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

The content is highly actionable with executable templates, concrete commands, and a well-sequenced pipeline backed by real reference files, but it carries some philosophical padding and includes a broken reference to a templates/viewer.html file that is absent from the bundle.

Suggestions

Resolve the missing templates/viewer.html reference: either add the template file to the bundle or remove/replace the references to it in the Modes, Workflow Step 2/3, and References table.

Trim the philosophical/creative-motivation prose (e.g. 'The canvas is the medium; the algorithm is the brush') to keep the body lean and token-efficient.

Consider moving the experimental 'Creative Divergence' (SCAMPER / Distance Association) section into a dedicated reference file to reduce inline bulk.

DimensionReasoningScore

Conciseness

The body is mostly efficient with lean, executable code blocks and tight tables, but it also carries philosophical prose ('The canvas is the medium; the algorithm is the brush') and extended creative-thinking sections (parameter philosophy, SCAMPER, Distance Association) that pad beyond what Claude needs to execute, matching the 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

It provides a copy-paste-complete HTML scaffold, concrete commands ('bash scripts/render.sh sketch.html output.mp4', 'node scripts/export-frames.js sketch.html --frames 300'), specific API calls with version pins, and key-binding conventions, matching the fully-executable anchor.

3 / 3

Workflow Clarity

A clear 6-stage pipeline (CONCEPT -> DESIGN -> CODE -> PREVIEW -> EXPORT -> VERIFY) plus an 8-step Agent Workflow and an explicit Step 6 verification checklist ('Does it match the vision?', resolution/performance/color checks) give a clear sequence with validation checkpoints, matching the level-3 anchor.

3 / 3

Progressive Disclosure

It has a well-organized overview with one-level-deep references to 10 real references/*.md files in a clearly signaled table, but templates/viewer.html is referenced in the Modes/Workflow/References sections and does not exist in the bundle, a broken navigation link that breaks the otherwise clean structure.

2 / 3

Total

10

/

12

Passed

Description

57%

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 concise and distinct, naming a clear p5.js creative-coding niche, but it relies on abbreviated noun fragments and omits an explicit 'Use when...' trigger clause, so it answers 'what' only weakly and leaves 'when' implied.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for p5.js sketches, generative art, interactive visuals, or canvas-based creative coding.'

Replace abbreviations with full natural terms users actually say ('gen art' -> 'generative art') and add 'creative coding', 'canvas animations', 'data viz'.

Lead with concrete verbs ('Create, animate, and export p5.js sketches...') to lift specificity from domain-naming to concrete actions.

DimensionReasoningScore

Specificity

Names the domain ('p5.js sketches') and several output families ('gen art, shaders, interactive, 3D'), but uses terse noun fragments rather than listing multiple concrete actions (e.g. create, animate, export), so it falls short of the level-3 anchor.

2 / 3

Completeness

It tersely states what the skill produces but has no explicit 'Use when...' trigger clause, so the 'when' is only implied; per the rubric guideline a missing trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

Includes relevant natural keywords ('p5.js sketches, gen art, shaders, interactive, 3D'), but abbreviates 'generative art' to 'gen art' and omits common variations users say like 'creative coding', 'canvas', 'data viz', leaving coverage incomplete.

2 / 3

Distinctiveness Conflict Risk

The 'p5.js sketches: gen art, shaders, interactive, 3D' niche is clearly scoped and unlikely to trigger for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

9

/

12

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 (557 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.