Skill do Product Owner para especificação de features. Use quando precisar definir requisitos de negócio, escrever user stories, critérios de aceitação, priorização de backlog, ou qualquer documento de especificação de produto. Trigger em: "nova feature", "especificação", "user story", "requisito", "backlog", "PO", "definir escopo", "critério de aceitação", "MVP", "roadmap".
59
67%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/01-po-feature-spec/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope as a Product Owner feature specification skill. It excels in all dimensions by listing concrete actions, providing extensive natural trigger terms, explicitly stating both what it does and when to use it, and occupying a distinct niche. The explicit 'Trigger em' list is a particularly effective addition for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: defining business requirements, writing user stories, acceptance criteria, backlog prioritization, and product specification documents. | 3 / 3 |
Completeness | Clearly answers both 'what' (Product Owner skill for feature specification, defining requirements, writing user stories, acceptance criteria, backlog prioritization) and 'when' (explicit 'Use quando' clause with specific trigger scenarios, plus an explicit 'Trigger em' list). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'nova feature', 'especificação', 'user story', 'requisito', 'backlog', 'PO', 'definir escopo', 'critério de aceitação', 'MVP', 'roadmap'. These are terms users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly carved out niche around Product Owner / product specification work with distinct triggers like 'PO', 'user story', 'critério de aceitação', 'MVP' that are unlikely to conflict with other skills such as general coding or documentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill covers the PO feature specification domain comprehensively but suffers from significant verbosity — it explains concepts Claude already understands (what acceptance criteria are, what a PO does) and includes inline content that should be in referenced files. The workflow is present but scattered rather than clearly sequenced, and while the ambiguity scoring mechanism is a strong actionable element, much of the remaining content is descriptive rather than directly executable.
Suggestions
Cut sections that explain concepts Claude already knows: 'Responsabilidades', 'Código Limpo', basic acceptance criteria definitions. Focus only on project-specific conventions and formats.
Consolidate the workflow into a single numbered sequence: 1) Calculate ambiguity score → 2) Choose path (direct/enrich/interview) → 3) Write spec using structure template → 4) Validate against checklist → 5) Handoff. Add explicit validation before handoff.
Move the prioritization matrix, vertical slice examples, and acceptance criteria examples into the referenced docs/skill-guides/po-feature-spec.md file, keeping only a one-line summary with link in the main skill.
Add a concrete, copy-paste-ready spec template (with placeholder fields) instead of just describing what a spec should contain.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is excessively verbose at ~180 lines, explaining many concepts Claude already knows (what a PO does, what acceptance criteria are, basic prioritization matrices). Sections like 'Responsabilidades', 'Código Limpo', and the detailed explanation of good vs bad acceptance criteria are unnecessary padding. The governance preamble and integration pipeline section add tokens without actionable value. | 1 / 3 |
Actionability | The skill provides some concrete guidance like the ambiguity scoring formula, prioritization matrix, and vertical slice examples. However, much of the content is descriptive rather than instructive — it tells Claude what good specs look like but doesn't provide a concrete, fill-in template or executable workflow. The Deep Interview protocol references a template file but doesn't give enough inline detail to act on. | 2 / 3 |
Workflow Clarity | There is an implicit workflow (calculate ambiguity → decide path → write spec → handoff), but it's scattered across sections rather than presented as a clear sequential process. The ambiguity scoring thresholds provide decision points, but there's no explicit validation step to verify the spec is complete before handoff. The 'Evidencia de Conclusao' section serves as a checklist but isn't integrated into a numbered workflow with feedback loops. | 2 / 3 |
Progressive Disclosure | The skill references several external files (docs/skill-guides/po-feature-spec.md, policies/vertical-slices.md, templates/deep-interview.md, docs/skill-guides/ideation-frameworks.md) which is good progressive disclosure structure. However, no bundle files are provided to verify these exist, and the main file itself contains too much inline content that could be offloaded (e.g., the full prioritization matrix, vertical slice examples, acceptance criteria best practices). | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
ec5fa71
Table of Contents
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.