CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

po-ux

Product Owner + UX/UI Designer fusión v4 (post pm-redesign 2026-05 Punto 4). Toma 1 UI standard story (CRUD/list/detail/form/dashboard) state=refining → produce 01-spec.md UNIFICADO con Gherkin AI-resistant + wireframes inline (ASCII / HTML mockup / Figma link) + estados visuales + microcopy Spanish neutro + Playwright graders → transition state=refining→refined al ratificar. NO se usa para agentic-stories (use /ux-agentico) ni service-stories (use /po). Loop iterativo Chris hasta ratificación. Activa cuando user dice: '/po-ux', 'definamos esta historia UI', 'spec + diseño', 'pantalla CRUD', 'dashboard', 'form nuevo', 'list view', 'detail page', 'wireframe', 'mockup'.

71

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

77%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 highly actionable, well-sequenced workflow skill with strong validation gates and executable templates. Its weaknesses are redundancy — the v4.1 gate content appears three times and version-history dates litter the text — and a monolithic 415-line body that inlines spec-template material instead of splitting it into reference files.

Suggestions

Consolidate the v4.1 sub-category coverage rule into one canonical table (Step 3) and have the Step 5 checklist and Anti-patterns section reference it instead of restating it, cutting ~40 lines of duplication.

Move version-history markers ('v4.1 cement 2026-05-19', 'R26 2026-05-05', 'Wave 3 redesign', 'post reorg 2026-05-15') into a single 'Changelog / deprecated patterns' section or drop them, per the time-sensitive-information guideline.

Extract the spec-section templates (microcopy table, estados visuales, grader YAML shapes) into a references/spec-template.md and point to them from Step 3, so SKILL.md stays an operational overview; the Referencias section already shows this pattern works.

DimensionReasoningScore

Conciseness

The body is mostly efficient operational guidance, but the v4.1 sub-category table is repeated three times (Step 3 table, Step 5 checklist, Anti-patterns) and version-history markers like '★ v4.1 cement 2026-05-19', 'R26 2026-05-05', and 'post reorg 2026-05-15' are embedded in prose rather than a changelog/deprecated section, per the time-sensitive-information guideline. This fits 'mostly efficient but could be tightened' rather than the noticeably padded anchor 2, since almost all content is operational rather than explanations of known concepts.

3 / 5

Actionability

Guidance is copy-paste ready: executable bootstrap commands ('WS=$(git rev-parse --show-toplevel)', 'python3 -m http.server 8888'), concrete YAML templates for frontmatter/graders/telemetry/checkpoint, exact file paths, per-screen state tables, and literal output-format blocks including sample microcopy ('Aún no tienes ofertas'). Placeholders like {story-id} and {m} are appropriate template variables, not gaps.

5 / 5

Workflow Clarity

Steps 1–5 are clearly sequenced with an explicit validation checkpoint: a hard pre-handoff gate checklist ('Si gate FAIL → STOP, NO transition refining→refined'), an iterate-with-Chris feedback loop until 'ratified_by_chris: true', anti-pattern for giving up after one iteration, and graded escalation rules (pequeño/medio/grande). This matches the anchor-5 example of sequence plus explicit validation with error-recovery loops.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the 415-line body inlines material that belongs in reference files — full spec-section templates (microcopy table, estados visuales, grader YAML) that duplicate docs/specs/templates/01-spec-template.md. The trailing 'Referencias' list is clearly signaled and one level deep, but the body itself is a near-monolithic wall, fitting 'some structure but content that should be separate is inline' rather than the well-split anchor 4.

3 / 5

Total

16

/

20

Passed

Description

100%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 exemplary: it states what the skill produces (unified spec with Gherkin, wireframes, visual states, microcopy, and Playwright graders), when to activate it via ten natural trigger phrases, and where it does not apply relative to sibling skills. Version-history fragments ('fusión v4 (post pm-redesign 2026-05 Punto 4)') add minor noise but no ambiguity.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with comprehensive coverage: 'produce 01-spec.md UNIFICADO con Gherkin AI-resistant + wireframes inline (ASCII / HTML mockup / Figma link) + estados visuales + microcopy Spanish neutro + Playwright graders → transition state=refining→refined'. Every output artifact is named explicitly; no coverage gaps, matching the anchor-5 example rather than the minor-gaps anchor 4.

5 / 5

Completeness

It explicitly answers both 'what' (takes one UI standard story in state=refining and produces the unified spec with enumerated elements, then transitions state upon ratification) and 'when' (an explicit 'Activa cuando user dice: ...' clause with concrete trigger phrases).

5 / 5

Trigger Term Quality

'Activa cuando user dice: "/po-ux", "definamos esta historia UI", "spec + diseño", "pantalla CRUD", "dashboard", "form nuevo", "list view", "detail page", "wireframe", "mockup"' provides ten natural trigger phrases covering the slash command, task phrasings, and screen types a user would actually say.

5 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche and explicitly redirects adjacent cases: 'NO se usa para agentic-stories (use /ux-agentico) ni service-stories (use /po)'. Trigger terms are scoped to UI-spec work, so conflict risk with sibling skills is minimal.

5 / 5

Total

20

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

alpacapurpura/luana-method

Path

claude/skills/po-ux/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.