prp-prd

Interactive PRD generator - problem-first, hypothesis-driven product spec. Use when the user wants to create a PRD, write a product or feature spec, scope a new product, or invokes $prp-prd.

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%Weight 40%Scale 1-3

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

A thorough, highly actionable PRD-generation skill with excellent workflow sequencing and validation gates, plus copy-paste templates and subagent prompts. Its main weaknesses are a monolithic single-file structure that inlines a large template, and minor redundancy between the process overview and the closing flow diagram.

Suggestions

Extract the large PRD markdown template (Phase 7) into a reference file (e.g. references/prd-template.md) and link to it, reducing SKILL.md to an overview and improving progressive disclosure.

Remove or merge the closing 'Question Flow Summary' ASCII diagram, since it duplicates the 'Process Overview' box near the top.

Trim the 'Your Role' persona bullets to only the directive guidance (e.g. the anti-pattern note) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural instruction, but the 'Your Role' persona bullets add flavor over guidance and the closing 'Question Flow Summary' ASCII diagram fully restates the 'Process Overview' box. It is not level 3 because not every token earns its place; it is above level 1 because it avoids explaining concepts Claude already knows and stays task-focused.	2 / 3
Actionability	It provides executable bash (the PRP store resolver), exact copy-paste subagent spawn prompts, a concrete output path, and a complete PRD markdown template - fully actionable and copy-paste ready.	3 / 3
Workflow Clarity	The 8 phases are clearly sequenced, each ending in an explicit 'GATE: Wait for user response' validation checkpoint, with feedback loops (restating understanding, confirming before proceeding). This matches the anchor for clear sequence with explicit validation steps and error-recovery loops.	3 / 3
Progressive Disclosure	This is a single ~470-line monolithic file with no bundle references; the large PRD template (~150 lines) is inline and could reasonably be split into a reference file. It is above level 1 because sections are well-organized, but not level 3 because the skill far exceeds the 'under 50 lines' simple-skill exception and inlines content that should be separated.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 concisely states the skill's purpose and gives explicit, natural-language triggers covering the main ways a user would request it. It answers both what the skill does and when to use it without fluff.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions - 'create a PRD, write a product or feature spec, scope a new product' - and characterizes the approach as 'problem-first, hypothesis-driven', matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	It answers both 'what' ('Interactive PRD generator - problem-first, hypothesis-driven product spec') and 'when' via an explicit 'Use when the user wants to create a PRD...' clause, satisfying the highest anchor.	3 / 3
Trigger Term Quality	It includes natural terms a user would say - 'PRD', 'product spec', 'feature spec', 'scope a new product' - plus the invocation token '$prp-prd', giving good coverage of phrasings users actually employ.	3 / 3
Distinctiveness Conflict Risk	The PRD/product-spec niche with its dedicated triggers is clearly distinguishable from other skills; 'scope a new product' has minor overlap with planning skills but the PRD framing keeps it distinct. It is above level 2 because the niche and triggers are specific rather than merely 'somewhat specific'.	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: Wirasm/prp
Path: .agents/skills/prp-prd/SKILL.md
Commit: 1142738

Reviewed: 11 days 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.