CtrlK
BlogDocsLog inGet started
Tessl Logo

worker-visualizer

A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps. Produced as a single self-contained `index.html`. Use when the brief asks for a "web worker", "simulation", "particle system", "physics", "off-main-thread", "fractal", "real-time compute", or "audio/data visualizer". OpenDesign serves this in powered-preview mode so Workers and SharedArrayBuffer actually work.

67

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 tight, well-structured body with a clear workflow and a genuine validation checklist, giving concrete API guidance without padding. Its main defect is that it outsources all executable code to example.html, which is missing from the bundle — making Step 0 unactionable and leaving the skill without a working reference implementation.

Suggestions

Ship example.html (the 'working 12k-particle SharedArrayBuffer sim') with the bundle, or inline its essential worker-transport scaffold (Blob worker construction, the SAB guard, and the transferable fallback) so Step 0 and Step 2 are self-sufficient.

Add an explicit fix-and-retry loop after the Step 4 self-review checklist (e.g., 'if the worker throws SecurityError, switch to the transferable path and re-verify') to strengthen the feedback loop.

Trim the platform-history aside ('In the old opaque sandbox all three failed; here they just work') and compress the powered-preview explanation to the actionable facts.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence (no explanation of what Web Workers or SharedArrayBuffer are), but 'In the old opaque sandbox all three failed; here they just work' and parts of the 'Why this is a powered artifact' paragraph are trim candidates. Fits anchor 4 (efficient, minor over-explanation); not 5 because the platform-history aside doesn't fully earn its tokens.

4 / 5

Actionability

Concrete API-level guidance ('Build the worker from a Blob + URL.createObjectURL', 'Guard on typeof SharedArrayBuffer !== \'undefined\' && crossOriginIsolated', 'postMessage a transferable ArrayBuffer') with minor gaps. Not 5: there are no code blocks in the body — all executable code is deferred to example.html, and that file is absent from the bundle, so nothing here is copy-paste ready. Not 3: the guidance is specific and executable in direction, not pseudocode.

4 / 5

Workflow Clarity

Steps 0-4 are clearly sequenced and Step 4 is an explicit P0 self-review checklist ('verify BOTH branches degrade cleanly', 'Main-thread render holds ~60fps', 'No unbounded growth'). Not 5: Step 0 ('Read example.html') cannot be executed because example.html is not in the bundle, and there is no fix-and-retry loop after the checklist.

4 / 5

Progressive Disclosure

Sections are well organized with a clear resource map and a one-level-deep reference scheme, but the sole referenced file (example.html, flagged 'READ FIRST') does not exist in the bundle — the resource map and Step 0 point at a missing file, breaking navigation. Scored against the actual bundle structure, this fits anchor 3 (structure present but organization is broken); not 4 because a claimed-but-absent reference is worse than a minor organization gap.

3 / 5

Total

15

/

20

Passed

Description

91%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.

A strong description: third-person, concrete about the artifact's mechanism (Worker compute, SharedArrayBuffer, 60fps canvas, single index.html), with an explicit 'Use when...' clause and rich synonym trigger coverage. Weaknesses are minor — descriptive rather than action-verb phrasing, platform-specific meta, and a few overly broad single-word triggers.

DimensionReasoningScore

Specificity

Names several concrete capabilities ('heavy compute runs in a Web Worker (off the main thread)', 'sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps', 'Produced as a single self-contained index.html'), but phrasing is descriptive rather than action-oriented and includes platform meta ('OpenDesign serves this in powered-preview mode'). Not 5 because it describes the artifact rather than listing a comprehensive set of actions; not 3 because coverage goes well beyond 1-2 actions.

4 / 5

Completeness

Explicitly answers both: what ('A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker... renders to a canvas at 60fps') and when ('Use when the brief asks for a "web worker", "simulation", "particle system"...'). Matches anchor 5 exactly; anchor 4 would require a weaker or less concrete 'when' clause.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage with synonyms and variants: 'web worker'/'worker', 'particle system', 'physics sim', 'fractal', 'off main thread', 'sharedarraybuffer', 'real-time compute', 'audio/data visualizer', 'visualizer'. Fits anchor 5's synonym-completeness criterion; not 4 because no common variations are obviously missing.

5 / 5

Distinctiveness Conflict Risk

Distinct niche (worker-based real-time visualizers) with mostly non-conflicting triggers, but bare 'worker', 'simulation', and 'visualizer' could overlap with generic simulation or data-viz skills. Fits anchor 4 (mostly distinct, minor overlap risk); not 5 because several single-word triggers are broad.

4 / 5

Total

18

/

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
nexu-io/open-design
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.