CtrlK
BlogDocsLog inGet started
Tessl Logo

falling-leaves

Build falling leaves that read as leaves, with each one tumbling on its own axis so it presents a face, thins to an edge, and opens out again, and with its sideways slip driven by that same tumble. Covers the 2-D canvas build and the instanced-3-D variant, where leaves are recycled from, density-versus-count maths, depth layering, colour under a tone-mapped composite, reduced motion, and visibility pausing. Use for autumn maple, sakura petals, blossom, ash, snowfall shapes, or any drifting foliage where a generic particle field reads as confetti.

80

Quality

100%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 high-quality, executable skill body: dense and assumption-respecting prose, concrete code for both the 2-D and 3-D variants, a clear build sequence, and a closing verification checklist. It is self-contained with no unnecessary external references.

DimensionReasoningScore

Conciseness

Lean and dense throughout: it never explains basic concepts (canvas, Matrix4, InstancedMesh, IntersectionObserver) and instead spends its tokens on earned domain insight ('That instant of near-disappearance is what the eye reads as leaf'; 'The eye finds the common rhythm in about two seconds'), assuming Claude's competence.

5 / 5

Actionability

Fully executable, copy-paste-ready code blocks cover the common cases — the 2-D tumble (`ctx.scale(Math.cos(l.spin), 1)`), the slip coupling (`l.x += Math.sin(l.spin) * l.slip * dt`), the 3-D ahead-of-camera recycle disc, and the viewport-area count scaling — with concrete parameter ranges in the layer table.

5 / 5

Workflow Clarity

A single-purpose build skill with a clear ordered build sequence (tumble first → couple slip → bake faces → vary params → recycle → density → layer → colour → budget → pause → reduced motion) closing in an explicit 'Verify' checklist of validation checkboxes, satisfying the simple-skill exception.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed: the body is a single self-contained file organised into well-signalled section headers, with nothing (no API reference or large lookup table) that clearly belongs in a separate one-level-deep reference.

5 / 5

Total

20

/

20

Passed

Description

100%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.

An excellent description: specific, trigger-rich, complete in both what and when, and clearly distinguished from sibling particle skills. Voice is imperative (matching the rubric's own good examples) with no first/second-person drift or vague fluff.

DimensionReasoningScore

Specificity

Names the domain and lists multiple concrete build aspects — '2-D canvas build and the instanced-3-D variant', 'leaves are recycled', 'density-versus-count maths', 'depth layering', 'colour under a tone-mapped composite', 'reduced motion, and visibility pausing' — giving comprehensive coverage rather than a single generic action.

5 / 5

Completeness

Explicitly answers both halves: the 'what' ('Build falling leaves that read as leaves, with each one tumbling on its own axis...') and the 'when' ('Use for autumn maple, sakura petals, blossom, ash, snowfall shapes, or any drifting foliage where a generic particle field reads as confetti').

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and concrete shapes a user would actually say: 'falling leaves', 'autumn maple', 'sakura petals', 'blossom', 'ash', 'snowfall shapes', 'drifting foliage', plus the contrast term 'confetti'.

5 / 5

Distinctiveness Conflict Risk

A clear niche (recognisable drifting foliage) with an explicit boundary against the generic-particle-field neighbour ('where a generic particle field reads as confetti'), so it is unlikely to trigger for the wrong skill.

5 / 5

Total

20

/

20

Passed

Validation

100%

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
MengTo/Skills
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.