write-prd

Produce a Product Requirements Document (PRD) for a product feature. Use when the user asks to write a PRD, or to formalize a feature's scope, goals, user value and success metrics. Not for internal technical or architecture change proposals.

Quality

80%

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

78%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.

The body is a well-structured, actionable PRD-writing methodology with concrete templates and examples and no padding of known concepts. Main improvements would be de-duplicating the persistence instruction and strengthening the review step into a real feedback loop.

Suggestions

De-duplicate the persist-to-disk instruction: keep it in the numbered Writing Strategy (step 5) and trim the opening CRITICAL block to a brief pointer to avoid redundancy.

Turn the soft 'Review' step into an explicit feedback loop: 'If the requirement matches a Bad example, rewrite it to match the Good example, then re-check before persisting.'

Fill out the thin one-line template sections (e.g. Dependencies & Risks, UX) with a concrete sub-bullet or example each so the template is copy-paste ready throughout.

Dimension	Reasoning	Score
Conciseness	Largely efficient with no explanation of concepts Claude already knows, but the persist-to-disk instruction is duplicated (the CRITICAL block and step 5) and the 'Prompt Engineering principles' line is mildly meta, so a couple of trims remain.	4 / 5
Actionability	Provides a concrete PRD template, specific bad/good requirement examples (e.g. 'under 200ms for 95% of requests at 100 QPS'), and a Mermaid sample, but some template sections remain one-line placeholders, leaving minor gaps.	4 / 5
Workflow Clarity	Section 2 gives a clear numbered sequence (Analyze -> Ask -> Draft -> Review -> Persist) with a review checkpoint, but the 'check against examples' validation is soft and there is no explicit error-recovery feedback loop, so it falls short of a 5.	4 / 5
Progressive Disclosure	A self-contained single-file skill with clean numbered sections (0-5) and no nested references; nothing clearly belongs in a separate file, so well-organized sections earn the top score.	5 / 5
	Total	17 / 20 Passed

Description

82%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.

The description is strong: it explicitly answers both what the skill does and when to use it, includes natural trigger terms and a helpful negative scope boundary. Its only weakness is that the listed actions are elaborations of one task rather than several distinct capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('Produce a Product Requirements Document (PRD)') and 1-2 concrete actions ('formalize a feature's scope, goals, user value and success metrics'), but these are sub-parts of one action rather than several distinct actions, so it is not comprehensive enough for a 4.	3 / 5
Completeness	Explicitly states both the 'what' ('Produce a Product Requirements Document (PRD) for a product feature') and the 'when' ('Use when the user asks to write a PRD, or to formalize...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Captures the natural term a user would say ('write a PRD', 'formalize a feature's scope, goals...') with good coverage, but misses common synonyms like 'product spec' or 'requirements doc', keeping it below a 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (PRD writing) with distinct triggers, plus an explicit negative boundary ('Not for internal technical or architecture change proposals') that actively minimizes conflict risk.	5 / 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: korchasa/flowai-plugins
Path: plugins/flowai-engineering/skills/write-prd/SKILL.md
Commit: ad81ae6

Reviewed: 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.