CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ux-ui

UX/UI Designer Nicolify. Toma 01-spec.md (ui-story o mixed) y produce 02-design-ui.md + mockups HTML. Iterative dialogue con Chris hasta aprobación. Si descubre edge cases nuevos → propone delta-spec.md, /po ratifica. Cargá skills sales-agent-expert, brand-expert, frontend-expert, tessl__shadcn-ui, tessl__tailwind. Activa cuando user dice: '/ux-ui', 'diseñemos la pantalla', 'mockup', 'wireframe', 'rediseña', 'la UI de X'.

70

Quality

88%

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

88%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 tight, highly operational workflow: concrete file paths, executable commands, templates for every output, and a six-step sequence with explicit escalation and validation checkpoints. Its weaknesses are minor — slight redundancy (skill list, server snippet) and an opportunity to move the long design-artifact checklists into reference files.

DimensionReasoningScore

Conciseness

The body is dense and operational — tables, numbered rules, and copy-paste templates with almost no explanation of concepts Claude already knows. Minor redundancy keeps it below 5: the skills-to-load list appears in both the frontmatter and the body ('Skills cargados (HARD GATE)'), and the 'Live verification' python http.server snippet repeats the one already shown in Step 2.

4 / 5

Actionability

Fully executable guidance throughout: exact input paths ('frontend/src/components/ui/'), a runnable preview command ('python3 -m http.server 8888'), a ready-to-send delta-spec.md template, per-iteration output message templates, and a feedback→action table mapping each Chris response to a concrete action. Covers the common cases copy-paste ready.

5 / 5

Workflow Clarity

Steps 1–6 are clearly sequenced with explicit validation checkpoints: Step 1 validates scope and escalates to /po if ambiguous, Step 3 defines a feedback loop ('NUNCA rebuilds from scratch', escalate on out-of-scope changes) that loops 'hasta Chris dice está bien', Step 5 routes edge cases to /po ratification, and 'Live verification' gates declaring done. This matches the anchor with explicit validation steps and error-recovery feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the ~165-line skill is organized into clear one-level sections with the single external pointer ('docs/specs/templates/02-design-ui-template.md') clearly signaled. At this length, some inline material (e.g., the full mockup rules or the 02-design-ui.md field checklist) could be split into reference files, placing it at 'good structure, minor organization gaps' rather than fully appropriate splitting.

4 / 5

Total

18

/

20

Passed

Description

83%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: it names concrete inputs, outputs, the escalation path, and explicit activation triggers in the user's natural phrasing. Its only flaws are a second-person imperative fragment ('Cargá skills ...') and a few missing trigger synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with named artifacts — 'Toma 01-spec.md ... y produce 02-design-ui.md + mockups HTML', 'propone delta-spec.md, /po ratifica' — giving comprehensive coverage of the workflow. However the guideline penalizes non-third-person voice by 1 point on this dimension: 'Cargá skills ...' is second-person imperative (voseo), pulling it down from a clear 5.

4 / 5

Completeness

Explicitly answers both: 'what' ('Toma 01-spec.md ... y produce 02-design-ui.md + mockups HTML', iterative dialogue until approval, delta-spec escalation) and 'when' ('Activa cuando user dice: ...' with concrete trigger phrases). This matches the 5 anchor — clear what AND when with concrete triggers; not 4 because the 'when' clause is fully explicit rather than merely present.

5 / 5

Trigger Term Quality

Includes natural trigger phrases users would say: '/ux-ui', 'diseñemos la pantalla', 'mockup', 'wireframe', 'rediseña', 'la UI de X' — good coverage. A few natural synonyms are missing (e.g., 'diseño', 'pantalla', 'interfaz', English 'UI design'), so it sits just below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The Nicolify-specific pipeline (01-spec.md → 02-design-ui.md, Chris iteration, /po ratification) carves a clear niche with minimal conflict risk. Generic design terms like 'mockup' and 'wireframe' could overlap with other design-related skills, keeping it at 'mostly distinct' rather than the 5 anchor.

4 / 5

Total

17

/

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

allowed_tools_field

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

Warning

Total

15

/

16

Passed

Repository

alpacapurpura/ap_sales_agent

Path

.claude/skills/ux-ui/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.