CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-domain-svg-infographic

Author editable SVG technical infographics — architecture, flow, comparison, hierarchy — by computing the layout numerically before writing markup, then rendering a 2x PNG via headless Chromium. Carries a CJK-first font stack, a deterministic source lint, and mermaid-vs-SVG selection rules.

Quality

85%

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

92%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, highly actionable skill body: the numeric-layout method is stated as executable formulas, every workflow step carries an explicit validation checkpoint, and detailed material is properly offloaded to real, well-organized bundle files. The only weakness is mild verbosity from rhetorical emphasis and deliberate rule repetition across the rationalization, red-flag, and verification sections.

DimensionReasoningScore

Conciseness

Dense and information-rich with no explanations of concepts Claude already knows, but rhetorical flourishes ("an unlabelled diagram is not a degraded diagram, it is an absent one"), the one-home rule restated across Step 0, the rationalizations table, and the verification checklist, and the long run-on slop-symptom #12 sentence could each be trimmed. It is efficient with minor over-explanation rather than padded, so it fits the 4 anchor and not 3 or 5.

4 / 5

Actionability

Fully executable throughout: exact grid/containment/connector formulas, copy-paste lint and render commands with flags and exit-code semantics, a copyable CJK-first font stack, dial values with defaults, and a degradation matrix. All cited bundle paths (check-svg.mjs, render.mjs, references/authoring.md sections 2.5 and 8, the 42 fixtures) verify as real, matching the 5 anchor.

5 / 5

Workflow Clarity

Six steps in explicit order with a hard ordering constraint ("Steps 1 through 3 finish before a single SVG element is written"), validation checkpoints at every stage (containment "stop if any fails", "clear every error; triage every warning", PNG header dimensions where "a mismatch is a failure"), plus feedback loops and a final checklist. This matches the 5 anchor's validate-fix-retry pattern exactly.

5 / 5

Progressive Disclosure

The core method is inline while the full formula set, archetype skeletons, imports, and the sketch preset are split into well-signaled, one-level-deep references (verified: no .md-to-.md chains), each described in a bundled-references table with section-level pointers, and the scripts and 42-fixture lint suite are documented. Structure matches the 5 anchor.

5 / 5

Total

19

/

20

Passed

Description

75%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 specific, distinctive description that names concrete actions across the full pipeline in third person. Its one real gap is completeness: trigger guidance lives in the separate when_to_use frontmatter field rather than in the description itself, so the description field alone does not tell Claude when to reach for this skill.

Suggestions

Append an explicit trigger clause to the description field itself (e.g., "Use when the deliverable is a static diagram image for slides, email, social, or offline use, or when pixel-level control or precise CJK line wrapping is needed"), rather than relying on the separate when_to_use field, since the description alone is weakly implied at best.

Add the natural term "diagram" and the ".svg" extension to the description's trigger vocabulary — they are the phrasings users most likely say but currently appear only in when_to_use.

Consider briefly folding the when_to_use routing signals (static image vs. markdown-embedded, frequently-changing diagrams stay mermaid) into the description so skill discovery works even when only the description is surfaced.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions covering the whole pipeline: "Author editable SVG technical infographics", "computing the layout numerically before writing markup", "rendering a 2x PNG via headless Chromium", "deterministic source lint", and "CJK-first font stack". Matches the comprehensive 5 anchor rather than 4, since coverage spans authoring, layout, rendering, linting, and typography.

5 / 5

Completeness

The "what" is clear and concrete, but "when" is only weakly implied by "mermaid-vs-SVG selection rules", which names a feature rather than stating trigger guidance; there is no "Use when..." clause in the description itself. Per the guideline this caps completeness at 3, and it is not 4 because no explicit when-clause is present at all.

3 / 5

Trigger Term Quality

Good natural-term coverage ("SVG", "infographics", "architecture", "flow", "hierarchy", "PNG"), but the most natural user phrasing "diagram" and the ".svg" extension are absent from the description (they appear only in the separate when_to_use field). Fits the 4 anchor (a few natural terms missing), not the 5 anchor's synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

A clear niche (numeric-layout editable SVG infographics with headless-Chromium PNG rendering and a CJK-first font stack) that even names its nearest neighbor boundary ("mermaid-vs-SVG selection rules"), minimizing conflict risk. Matches the 5 anchor.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

modu-ai/moai-adk

Path

.claude/skills/moai-domain-svg-infographic/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.