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

80%

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 1-5

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 process skill with verbatim prompts, explicit GATE checkpoints, and a complete template. Its main weaknesses are token redundancy (a duplicated flow diagram) and the absence of any progressive disclosure into reference files despite the large body.

Suggestions

Remove or merge the "Question Flow Summary" ASCII diagram, which duplicates the "Process Overview" and the per-phase section headers.

Extract the large PRD template block (lines ~240-394) into a references/ template file and link to it, reducing SKILL.md to an overview and improving progressive_disclosure.

Trim the role-prompting fluff in "Your Role" to the concrete anti-pattern rule that actually changes behavior.

Dimension	Reasoning	Score
Conciseness	The ~480-line body is mostly efficient but carries redundancy — the boxed "Question Flow Summary" diagram restates the earlier "Process Overview" and per-phase sections — plus light role-prompting fluff ("You are a sharp product manager who...").	3 / 5
Actionability	It provides verbatim question prompts, exact subagent spawn blocks, an executable bash store-resolver, and a complete copy-paste-ready PRD template plus output summary template, fully covering the common cases.	5 / 5
Workflow Clarity	Phases 1–8 are explicitly sequenced with a GATE checkpoint after each phase ("Wait for user response before proceeding") and a closing Success Criteria checklist, matching the anchor-5 example of clear sequencing with explicit checkpoints and a process checklist.	5 / 5
Progressive Disclosure	No bundle files exist and everything is inline in one ~480-line file; section headers give structure, but the large PRD template and redundant flow diagrams are content that could plausibly live in separate reference files, fitting the anchor-3 case of structure with inline content that should be split.	3 / 5
	Total	16 / 20 Passed

Description

83%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 clearly answers both what the skill does and when to invoke it, with concrete natural-language triggers. It is slightly held back by overlapping action verbs and a mildly broad "scope a new product" trigger.

Dimension	Reasoning	Score
Specificity	"create a PRD, write a product or feature spec, scope a new product" lists several specific actions, but they are overlapping variants of the same task rather than comprehensive distinct capabilities, fitting the anchor-4 example.	4 / 5
Completeness	It explicitly states what ("Interactive PRD generator - problem-first, hypothesis-driven product spec") and when ("Use when the user wants to create a PRD, write a product or feature spec, scope a new product, or invokes $prp-prd"), matching the anchor-5 example of both what and when with concrete triggers.	5 / 5
Trigger Term Quality	"PRD", "product or feature spec", and "scope a new product" are natural phrases users would say, giving good keyword coverage, though a few synonymous phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	The PRD-generator niche is mostly distinct with clear triggers, but the "scope a new product" phrasing is broad enough to create minor overlap risk with general planning skills.	4 / 5
	Total	17 / 20 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: 9724799

Reviewed: ~12 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.