po

Product Owner Nicolify. Toma 1 user story (de /pm o Chris directo) y produce 01-spec.md + actualiza/crea product/stories/{module}/{id}.yaml. Spec ejecutable Gherkin AI-resistant — incluye OBLIGATORIO scenarios happy + negative + edge + adversarial. Loop iterativo con Chris hasta ratificación. Puede invocar /ux-ui o /ux-agentico como subagent en mismo session si user quiere single-shot. Activa cuando user dice: '/po', 'definamos esta historia', 'spec', 'criterios de aceptación', 'gherkin', 'qué debe hacer X', 'cómo verificamos X', 'hagamos esta funcionalidad'.

Quality

88%

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

Quality

Content

81%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 tightly written, highly actionable workflow with an explicit step sequence, hard validation gates, and feedback loops for ratification and design deltas. The main gaps are minor redundancy in the anti-patterns and reliance on external templates that are referenced but not included in any bundle.

Suggestions

De-duplicate the anti-patterns and the 'NO redactes spec sin story brief' warnings to tighten conciseness toward a fully lean body.

Bundle the referenced templates (01-spec-template.md, story-ui/agentic/service.yaml) under references/ and link to them so the grader examples and schemas live in one discoverable place.

Add a short 'verify before hand-off' checklist in Step 7 confirming scenario coverage + ratification state, making the validation gates uniform across the workflow.

Dimension	Reasoning	Score
Conciseness	Dense and command-style, assuming Claude knows Gherkin/specs without explaining them; every section earns its place, though the anti-patterns and a few repeated warnings (e.g. 'NO redactes spec sin story brief' restated) could be trimmed, so it sits above the midpoint but not fully lean.	4 / 5
Actionability	Provides concrete bash commands (cat/ls), copy-ready grader YAML blocks per story type, trial_policy, and exact output-format strings; the only gap is that the underlying templates (01-spec-template.md, story-*.yaml) are referenced rather than inlined, leaving minor detail to external files.	4 / 5
Workflow Clarity	An explicit 8-step sequence with hard validation gates ("Si 00-story.md no existe → escala /pm", "Si falta UNO → /po rechaza spec, no procede") and genuine feedback loops — the Chris ratification loop (Step 6) and the UX delta loop — covering error recovery and re-validation.	5 / 5
Progressive Disclosure	Well-organized into Inputs, Workflow, UX delta loop, Anti-patterns, and Output format with signaled external references (templates, personas, rubrics); no bundle files exist, and the inlined grader YAML examples are appropriately kept as illustrations rather than buried, but overall content density keeps it just short of a fully split, one-level-deep structure.	4 / 5
	Total	17 / 20 Passed

Description

96%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, third-person description that explicitly states capabilities and enumerates concrete user-spoken trigger phrases, answering both 'what' and 'when' clearly. Its only weakness is a few generic product phrases that could overlap with neighboring skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "produce 01-spec.md", "actualiza/crea product/stories/{module}/{id}.yaml", mandatory "scenarios happy + negative + edge + adversarial", "Loop iterativo con Chris hasta ratificación", and invoking /ux-ui or /ux-agentico as subagents — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Clearly answers both 'what' (produce executable spec + story YAML with mandatory scenario types and ratification) and 'when' via the explicit "Activa cuando user dice: ..." clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Explicit natural trigger phrases a user would actually say are enumerated verbatim: '/po', 'definamos esta historia', 'spec', 'criterios de aceptación', 'gherkin', 'qué debe hacer X', 'cómo verificamos X', 'hagamos esta funcionalidad'.	5 / 5
Distinctiveness Conflict Risk	The /po command and spec/gherkin triggers carve a clear niche distinct from /pm, /ux-* and /architect, but generic phrases like 'qué debe hacer X' and 'hagamos esta funcionalidad' carry minor overlap risk with adjacent product skills; not a level-5 'minimal conflict risk'.	4 / 5
	Total	19 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: alpacapurpura/ap_sales_agent
Path: .claude/skills/po/SKILL.md
Commit: d31f7bc

Reviewed: ~18 hours 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.