CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

frontend

Builds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain way.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Failed to scan

The risk profile of this skill

The canonical home for this skill is frontend in code-yeongyu/oh-my-openagent

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.

An unusually well-engineered router: the body carries only the always-needed rules and gates, routes everything else to a real, well-indexed reference library, and backs every phase with runnable lint/detect/audit commands and explicit verification checkpoints. Its single weakness is density — several bullets over-enumerate variants and restate standards that could be tightened without losing meaning.

DimensionReasoningScore

Conciseness

The body is dense rule-prose that teaches nothing Claude already knows, but a few passages over-enumerate: the ~200-word draft-guard bullet cataloguing every stripe variant ("border-left: 4px solid <accent> or border-l-4 border-indigo-500, a coloured ::before/::after bar inside it, an inset box-shadow stripe...") and restated WCAG ratios ("text 4.5:1 (large 3:1)") could be trimmed — anchor 4 ("efficient; minor instances of over-explanation that could be trimmed") rather than the every-token-earns-its-place bar of 5.

4 / 5

Actionability

Copy-paste-ready commands with real flags cover the operational cases ("bun $SKILL_DIR/scripts/perfection/check-draft-guard.ts <changed files or dirs>", "detectPage({ kind: \"url\", url }, { reflow: true })", "python3 -B $SKILL_DIR/references/ui-ux-db/scripts/search.py \"<query>\" --design-system -p \"Project\"") plus exact thresholds (44x44 pt, 24x24 px, 65-75 characters per line, 1.25x heading steps) and named probes (read each control's getBoundingClientRect() in every state) — fully executable, anchor 5.

5 / 5

Workflow Clarity

The flow "ground -> brief -> build -> subtract -> verify" is stated up front and sequenced as numbered sections 0-4 with explicit validation gates and error-recovery loops: "Exit 1 means a tell is in the draft: remove it, do not argue with the finding", "Fix every error and warning before /visual-qa", and a bounded /visual-qa review loop ("its Step 4 sets the budget") — matching anchor 5's checkpoints-and-feedback-loops pattern.

5 / 5

Progressive Disclosure

The file declares itself "a router over references/" and delivers: a request-keyed routing table with a named reason per reference, Layer A/Layer B tables, and _INDEX.md ("catalogs all 83") over a verified one-level-deep bundle — every named file checked exists and holds real content (stylegallery.md, craft-floor.md, detect.md, check-draft-guard.ts, search.py, and the 12 taste skills / 70 brand files match the stated counts) — matching anchor 5's clear-overview-with-well-signaled-one-level-deep-references pattern.

5 / 5

Total

19

/

20

Passed

Description

88%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 throughout (no voice penalty), concrete actions, broad artifact coverage, and an explicit 'Use for...' trigger clause. The only gaps are a few high-frequency trigger synonyms ('design', 'frontend', 'redesign') and minor overlap risk with dedicated slide/PDF/chart skills arising from the breadth of claimed artifacts.

DimensionReasoningScore

Specificity

Lists three concrete actions ("Builds, styles, and polishes") across eight named artifact types ("web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack"), matching the anchor-5 pattern of multiple specific actions with comprehensive coverage; nothing is generic filler, so it does not fall to 4.

5 / 5

Completeness

Both halves are explicit: a clear 'what' ("Builds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components...") and an explicit when-clause with concrete triggers ("Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain way"), matching the anchor-5 example structure; the when-guidance is explicit, so it does not fall to 4.

5 / 5

Trigger Term Quality

Natural phrases users say are present ("styling, layout, animation, or visual-quality task", "make something look or feel a certain way", "web UI", "Notion or Slack"), but common synonyms — "design", "frontend", "redesign", "website" — are missing, fitting anchor 4 ("good keyword coverage; a few natural terms missing") rather than the comprehensive synonym-and-extension coverage of 5.

4 / 5

Distinctiveness Conflict Risk

The HTML/CSS/SVG visual-quality niche is clear with distinct triggers, but claims over "slides", "HTML reports rendered to PDF or print", and "PNG/SVG diagrams" create minor overlap with dedicated presentation, PDF, and charting skills — anchor 4 ("mostly distinct; minor overlap risk with closely related skills"); the framing technology ("anything drawn with HTML, CSS, or SVG") keeps it above 3.

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

referenced_paths_exist

Referenced path issues: 19 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

code-yeongyu/lazycodex

Path

plugins/omo/skills/frontend/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.