product-requirements

Interactive Product Owner skill for requirements gathering, analysis, and PRD generation. Triggers when users request product requirements, feature specification, PRD creation, or need help understanding and documenting project requirements. Uses quality scoring and iterative dialogue to ensure comprehensive requirements before generating professional PRD documents.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, actionable requirements-gathering workflow with a clear feedback loop and concrete scoring system, but it is verbose and monolithic: generic tone coaching, redundant DO/DON'T lists, and a large inline template that should be split into a reference file.

Suggestions

Move the ~170-line PRD template into references/prd-template.md and link to it from the body, trimming SKILL.md to a concise overview that qualifies for a higher progressive_disclosure score.

Cut the 'Communication Guidelines/Tone' section and the 'Important Behaviors DO/DON'T' list — this coaching restates the process steps and tells Claude what it already knows about being professional.

Remove the inline bracket-explanations inside the PRD template (e.g., '[2-3 paragraphs covering: what problem this solves...]') to reduce token load without losing the structure.

Dimension	Reasoning	Score
Conciseness	The ~360-line body pads concepts Claude already knows — the 'Communication Guidelines/Tone' coaching ('Professional yet approachable', 'Be transparent'), redundant DO/DON'T lists that restate the process steps, and inline bracket-explanations inside the PRD template — though the core scoring rubric and question bank are efficient.	2 / 3
Actionability	Highly concrete for an instruction skill: exact 100-point scoring breakdown with per-dimension point allocations, a 90+ threshold, a dimension-specific question bank, named tool ('AskUserQuestion'), exact display format, output path 'docs/{feature-name}-prd.md', and a copy-paste PRD template.	3 / 3
Workflow Clarity	Five clearly sequenced steps with an explicit feedback loop (assess → if <90 clarify → refine → recalculate → repeat until ≥90), gated by the quality threshold; this conversational skill is not a destructive/batch operation, so no validation cap applies.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the ~170-line PRD template is inline content that could be a separate reference file, and there are no external references at all; at >50 lines the 'well-organized sections only' exception does not apply.	2 / 3
	Total	10 / 12 Passed

Description

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.

A well-constructed description that follows the good-example pattern: concrete actions, third-person voice, and an explicit 'Triggers when...' clause covering natural user terms. The final sentence on quality scoring adds mild verbosity but is not vague.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'requirements gathering, analysis, and PRD generation' plus 'quality scoring and iterative dialogue' — matching the score-3 anchor of multiple specific concrete actions; uses third person throughout with no vague fluff.	3 / 3
Completeness	Clearly answers both what ('requirements gathering, analysis, and PRD generation') and when ('Triggers when users request...') with an explicit trigger clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	Explicit 'Triggers when users request product requirements, feature specification, PRD creation...' gives good coverage of natural terms a user would say (PRD, feature specification, product requirements).	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Product Owner / PRD generation) with distinct triggers unlikely to conflict with other skills, matching the score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: stellarlinkco/myclaude
Path: skills/product-requirements/SKILL.md
Commit: f2e75c1

Reviewed: about 9 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.