CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

multica-icons

Use when a Multica web/desktop UI change needs an icon that `@multica/ui/icons` does not export yet, or when redrawing or reviewing a Multica glyph. Covers the grid, corner and stroke construction, the body/detail markers, and the generate-and-preview loop. Never reach for an icon library, inline SVG, or emoji instead.

Quality

89%

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

86%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, domain-dense skill that teaches a project's icon construction system almost entirely through concrete rules, numeric constraints, and runnable commands. The only notable improvements are a worked example of a `DRAWINGS` entry and an explicit retry step after a failed preview check.

Suggestions

Add one short worked example of a `DRAWINGS` entry (e.g. the `Webhook` glyph's inner SVG markup) so the expected shape of a drawing — helper calls, class="b"/class="k" markers — is unambiguous before the reader writes their own.

Close the Loop with an explicit feedback step, e.g. 'If any of the four checks fails, fix the drawing and re-run --preview before regenerating', making the validate-fix-retry cycle explicit rather than implied.

DimensionReasoningScore

Conciseness

Every sentence carries project-specific information — grid bounds, k-value ranges, helper signatures, exact pnpm commands — with one-clause rationales ('a gap survives at 14px', 'the round cap pokes out if it runs past') and zero padding or explanation of concepts Claude already knows.

5 / 5

Actionability

The loop gives copy-paste commands (`pnpm --filter @multica/ui icons --preview NewName Neighbour1 Neighbour2`, regenerate, test) and concrete helper signatures (`shape([[x, y, k], ...])`, `head(x, y, dir, depth, half)`, `tick(a, v, b)`, `dot(x, y, r)`), but no worked example of a `DRAWINGS` entry showing what a complete drawing's markup looks like. This is a minor gap, matching anchor 4 rather than 5.

4 / 5

Workflow Clarity

The Loop is a clear numbered sequence with an explicit 4-point visual validation checklist (48px grid fit, 14px legibility, tinted-tile fill, neighbour distinctness) plus a test/typecheck gate, and 'icons.test.ts fails when they drift' supplies a drift signal. It falls short of anchor 5 only because no explicit fix-and-retry feedback loop is stated after a failed check.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external reference files (none exist in the bundle), and its five `##` sections (Before drawing, Where things live, Construction, Body and details, Loop) are well-organized, which the simple-skill guideline scores as 5.

5 / 5

Total

18

/

20

Passed

Description

87%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 with an explicit, concrete trigger clause, a clear statement of coverage, and an explicit negative scope boundary that prevents mis-triggering. It is only marginally short of exemplary on specificity and trigger-term breadth (missing synonyms like 'symbol').

DimensionReasoningScore

Specificity

'Covers the grid, corner and stroke construction, the body/detail markers, and the generate-and-preview loop' plus 'Never reach for an icon library, inline SVG, or emoji instead' enumerates several concrete capability areas and prohibitions. It stops short of anchor 5 because it describes scope rather than comprehensively listing the skill's actions (drawing, aliasing existing glyphs, regenerating generated files, running tests).

4 / 5

Completeness

The 'when' is explicit and concrete — 'Use when a Multica web/desktop UI change needs an icon that `@multica/ui/icons` does not export yet, or when redrawing or reviewing a Multica glyph' — and the 'what' is explicitly stated via the coverage sentence and the library prohibition, matching anchor 5 rather than 4 where the trigger would be less specific.

5 / 5

Trigger Term Quality

Natural terms users would say are well covered — 'icon', 'glyph', 'inline SVG', 'emoji', 'icon library', 'redrawing' — including the icon/glyph synonym pair. A few natural variations ('symbol', 'pictogram', 'drawing') are missing, so it fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (Multica glyphs exported from `@multica/ui/icons`) and adds an explicit anti-trigger — 'Never reach for an icon library, inline SVG, or emoji instead' — making conflict with generic SVG or asset skills minimal, which matches anchor 5.

5 / 5

Total

18

/

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

multica-ai/multica

Path

.agents/skills/multica-icons/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.