CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

team-ui-polish

Unified team skill for UI polish. Auto-discover and fix UI design issues using Impeccable design standards. Anti-AI-slop detection, color/typography/spacing quality, motion, interaction states, visual hierarchy. Uses team-worker agent architecture. Triggers on "team ui polish", "ui polish", "design polish".

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/team-ui-polish/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 a well-organized, lean overview that sequences a multi-role pipeline with concrete scaffolding and an error-handling/escalation loop. Its main weakness is progressive disclosure: the SKILL.md references eleven role/spec files that are not present in the bundle, so the detailed instructions it routes to cannot be reached.

Suggestions

Ship the referenced bundle files (roles/<role>/role.md and specs/*.md) alongside SKILL.md so the one-level-deep navigation actually resolves.

Inline the most critical Phase 2-4 steps (or a minimal fallback) so the skill remains actionable when a role spec is missing.

Add an explicit validation checkpoint in the verify step inline (not only in the referenced verifier role) to lift workflow_clarity toward 5.

DimensionReasoningScore

Conciseness

The body is dense and efficient — ASCII architecture diagram, compact tables, and a reusable spawn template — and assumes Claude's intelligence without explaining UI/design concepts, matching the 4 anchor; a few sections (e.g., the session-directory tree) could be trimmed slightly, so it is not a lean 5.

4 / 5

Actionability

Provides concrete executable scaffolding — an Agent({...}) spawn template with real parameters, specific CLI invocations ('ccw cli --mode analysis'), concrete MCP calls, and a session-path layout — but the core Phase 2-4 domain instructions are delegated to role.md files, leaving minor gaps that fit the 4 anchor rather than fully copy-paste 5.

4 / 5

Workflow Clarity

The scan -> diagnose -> optimize -> verify pipeline is clearly sequenced with an architecture diagram, role prefixes, and an error-handling table that includes a verifier GC loop (max 2 rounds) with user escalation, giving most checkpoints; detailed validation lives in the verifier role spec, so it sits at 4 rather than the explicit-validation 5.

4 / 5

Progressive Disclosure

The structure is well-signaled and one-level-deep (role registry + specs reference tables with links), but none of the referenced files (roles/*.md, specs/*.md) exist in the bundle — no references/, scripts/, or assets/ directories are present — so the overview points to dangling paths, which undermines navigation and caps this at the 3 anchor.

3 / 5

Total

15

/

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.

The description is third-person, specific, and supplies explicit trigger phrases that satisfy both the 'what' and 'when' requirements. It is held at 4 across dimensions by somewhat narrow trigger coverage and a domain-list framing of capabilities rather than crisp distinct actions.

Suggestions

Broaden trigger terms with natural variants/synonyms (e.g., 'fix UI', 'improve design', 'clean up interface') to push trigger_term_quality and completeness toward 5.

Reframe the capability list as distinct concrete actions rather than domain areas to strengthen specificity.

Sharpen the distinctiveness of the trigger phrases so 'design polish' cannot collide with general styling skills.

DimensionReasoningScore

Specificity

Lists several concrete capability areas — 'Auto-discover and fix UI design issues', 'Anti-AI-slop detection', 'color/typography/spacing quality', 'motion, interaction states, visual hierarchy' — giving broad coverage, though several read as domains rather than distinct actions, so it stops just short of the comprehensive 5 anchor.

4 / 5

Completeness

It answers both 'what' (the capability list) and 'when' (an explicit 'Triggers on...' clause with concrete phrases), satisfying the 4 anchor; the 'what' is domain-list heavy rather than a crisp action list, keeping it below the 5 anchor.

4 / 5

Trigger Term Quality

Explicit 'Triggers on "team ui polish", "ui polish", "design polish"' provides natural user-facing phrases, but coverage is narrow (only three near-synonymous terms) and omits common variants like 'fix UI' or 'improve design', fitting the 4 anchor rather than 5.

4 / 5

Distinctiveness Conflict Risk

The 'team-ui-polish' framing and specific UI-design trigger phrases carve a mostly distinct niche with only minor overlap risk against general design/polish skills, matching the 4 anchor; not a 5 because 'design polish' could still collide with broad styling skills.

4 / 5

Total

16

/

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

relative_links

Relative link issues: 11 missing, 5 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

catlog22/Claude-Code-Workflow

Path

.claude/skills/team-ui-polish/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.