emcn-design-review

Review UI code for alignment with the emcn design system — components, tokens, patterns, and conventions

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/emcn-design-review/SKILL.md

Quality

Content

83%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.

An exceptionally dense, actionable ruleset with excellent token efficiency — concrete paths, tokens, and patterns throughout with no filler. Its one real weakness is the workflow: applying batch fixes has no validation checkpoint, and the long token/badge catalogs are inlined rather than split into a reference file.

Suggestions

Add an explicit verification step after applying fixes when fix=true, e.g., "5. After applying fixes, run typecheck/lint (or the repo's check script) and fix any breakage introduced" — this both closes the feedback loop and lifts the destructive/batch cap on workflow clarity.

Move the full Design Tokens and Badges color catalogs into a references/tokens.md file and keep a short summary inline, with a clearly signaled one-level-deep pointer ("See [tokens.md](references/tokens.md) for the full list").

Clarify how scope arguments are resolved (e.g., what to do when $ARGUMENTS is empty or malformed) so step 3's "specified scope" is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is a lean rulebook: dense token lists, a variant mapping table, and anti-pattern bullets with zero conceptual explanation and no padding — every token earns its place and it fully assumes Claude's competence (e.g., it even tells Claude to read the actual buttonVariants rather than duplicating them).	5 / 5
Actionability	Guidance is fully concrete and executable for a review skill: exact barrel paths ("packages/emcn/src/index.ts"), exact token names ("text-[var(--text-primary)]"), an intent-to-variant table, specific class patterns to flag ("h-[Npx] w-[Npx]"), and pointers to authoritative source files for anything not enumerated.	5 / 5
Workflow Clarity	The four steps (read barrel, read tokens, analyze scope, apply or propose fixes) are clearly sequenced with argument defaults, but fix=true performs batch edits across the scope with no validation or verification step (e.g., typecheck, lint, or build check after applying fixes), which per the rubric caps workflow clarity at 3.	3 / 5
Progressive Disclosure	The bundle has no references/, scripts/, or assets/ — this is a single-file skill with well-organized, clearly headed sections, which is good structure. It falls short of a 5 because the ~80-line body inlines fairly large catalogs (the full token and badge color lists) that could live in a one-level-deep reference file, and it points to .claude/rules/emcn-components.md, a path outside the bundle.	4 / 5
	Total	17 / 20 Passed

Description

70%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 crisp, third-person description with a clear what and a distinct niche, but it omits any when-to-use trigger guidance, which caps its completeness. Adding a "Use when..." clause with natural trigger phrases would lift it to the top band.

Suggestions

Append a trigger clause such as "Use when reviewing or editing UI code, or when the user mentions the emcn design system, styling, tokens, or component conventions" to explicitly answer when the skill applies.

Include natural synonyms users would say (e.g., "styling", "Tailwind", "CSS", "design tokens") in the description to improve trigger term coverage.

Mention the flag-and-fix behavior (e.g., "flags violations and optionally applies fixes") to make the capability set more comprehensive.

Dimension	Reasoning	Score
Specificity	The description names its domain ("UI code", "the emcn design system") and enumerates concrete review targets ("components, tokens, patterns, and conventions"), which is more than the 1-2 actions of anchor 3 but rests on a single action verb ("Review"), leaving minor gaps versus the comprehensive coverage of anchor 5.	4 / 5
Completeness	The "what" is clearly stated ("Review UI code for alignment with the emcn design system") but there is no "Use when..." clause or any equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Natural phrases users would say are present ("UI code", "design system", "components", "tokens", "patterns"), giving good keyword coverage, but common synonyms a user might actually say such as "styling", "CSS", or "Tailwind" are missing, so it falls just short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	"emcn" is a named proprietary design system, giving the skill a clear niche with distinct triggers and minimal risk of firing for unrelated skills; generic terms like "UI code" are anchored by the emcn qualifier.	5 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: simstudioai/sim
Path: .agents/skills/emcn-design-review/SKILL.md
Commit: 8725250

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.