CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

visual-explainer

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.

Quality

84%

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

77%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 is highly actionable with an excellent workflow and validation checklist, and the reference signaling is well organized by content type. Its two real weaknesses are duplication between the Style and Anti-Patterns sections (inflating token cost) and four referenced template files that do not exist in the bundle, which would cause an agent following the instructions to fail when trying to read them.

Suggestions

Add the missing ./templates/*.html files to the bundle (architecture.html, mermaid-flowchart.html, data-table.html, slide-deck.html) or remove those references and inline the essential patterns, since the body instructs the agent to read them in the Structure step and before generating slides.

Deduplicate the Anti-Patterns section against the Style section: forbidden fonts, forbidden accent colors, and forbidden animations are each stated twice; consolidate into one canonical list and cross-reference it.

Fix or remove the dangling reference to websocket-implementation-plan.html (line 36) — it has no path and does not exist in the bundle.

DimensionReasoningScore

Conciseness

The guidance is mostly non-obvious and earns its tokens, but there is real duplication: forbidden fonts, accent colors, and animations are stated in both the Style section and again in the Anti-Patterns section; Mermaid zoom controls appear twice (lines 83 and 337); and the rendering-approach table (lines 67-79) is restated across the Diagram Types sections. This matches the mostly-efficient-but-could-be-tightened anchor rather than the minor-trimming anchor at 4.

3 / 5

Actionability

Fully executable throughout: exact hex accent palettes, named font pairings, a complete HTML file skeleton, concrete Mermaid theming directives, and copy-paste bash for surf-cli including OS-specific base64 variants (base64 -i vs base64 -w 0).

5 / 5

Workflow Clarity

A clear four-step sequence (Think, Structure, Style, Deliver) with an explicit pre-delivery validation checklist (squint test, swap test, both themes, no overflow, clean file open) and a regeneration feedback loop in the Slop Test ("If two or more of these are present, the page is slop. Regenerate").

5 / 5

Progressive Disclosure

References are one level deep and well signaled per content type, and all four ./references/*.md files exist with their cited sections. However, the body directs the agent to read ./templates/architecture.html, ./templates/mermaid-flowchart.html, ./templates/data-table.html, and ./templates/slide-deck.html — none of which exist in the bundle — plus an unpathed websocket-implementation-plan.html at line 36. Broken navigation paths are more than the minor organization gaps of the 4 anchor, so this sits at 3.

3 / 5

Total

16

/

20

Passed

Description

83%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 that explicitly covers what the skill does and when to use it, with a well-chosen set of natural trigger terms and an unusually useful proactive trigger for ASCII tables. It is held back from the top by a single-verb action list and slight breadth in "any visual explanation of technical concepts" that could overlap with charting skills.

DimensionReasoningScore

Specificity

"Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data" names the domain and several concrete deliverable targets, matching the several-specific-actions anchor with minor gaps. It falls short of 5 because it is essentially one action (generate HTML pages) applied to content types rather than multiple distinct operations, and "beautiful" is mild fluff.

4 / 5

Completeness

Both what ("Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data") and when ("Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table...") are explicitly stated with concrete triggers, plus a proactive trigger for ASCII tables.

5 / 5

Trigger Term Quality

The trigger list "diagram, architecture overview, diff review, plan review, project recap, comparison table" plus the proactive ASCII-table clause contains natural phrases users would say. Not 5 because common variations such as flowchart, timeline, roadmap, chart, and visualization are missing.

4 / 5

Distinctiveness Conflict Risk

The niche of self-contained HTML visual explanations is distinct with specific triggers, but "any visual explanation of technical concepts" and "comparison table" are broad enough for minor overlap with charting/dataviz skills. It is clearly above the 3 anchor ("could still overlap with similar skills") because the HTML-page deliverable and review/recap triggers are distinctive.

4 / 5

Total

17

/

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

0xRabbidfly/Eric-Cartman

Path

.github/skills/visual-explainer/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.