write-a-prd

Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.

Quality

85%

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

70%

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

The content is a well-sequenced, self-contained interview-to-PRD workflow with strong workflow clarity and organization. Its weaknesses are minor unnecessary explanation of a known concept and missing concrete mechanics for file creation and issue submission.

Suggestions

Remove or shorten the 'deep module' definition — Claude already knows the deep-vs-shallow module distinction, so a one-word cue suffices.

Add a concrete step for producing the artifact, e.g. write the PRD to `./ai-context/prds/<name>.md` and submit with `gh issue create --title ... --body-file ...`.

Make the completion gate before writing the PRD crisper than 'Once you have a complete understanding' — e.g. an explicit checklist the user must confirm.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, but the parenthetical 'A deep module (as opposed to a shallow module) is one which encapsulates a lot of functionality...' explains a software-design concept Claude already knows, so it could be tightened.	2 / 3
Actionability	The PRD template and step sequence are concrete, but the mechanics are incomplete — there is no command or method for creating the markdown file or submitting the GitHub issue (e.g., a `gh issue create` invocation).	2 / 3
Workflow Clarity	A clearly numbered 1–5 sequence with explicit user-confirmation gates ('Check with the user that these modules match their expectations' and 'Once you have a complete understanding...') serving as the feedback loops appropriate for an interview/planning skill.	3 / 3
Progressive Disclosure	No bundle files exist and none are needed; the skill is self-contained and organized into numbered steps plus a clearly delimited template block, which is appropriate for a reference-free skill.	3 / 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.

The description is strong across all dimensions: it specifies concrete actions, includes natural trigger terms, answers both what and when, and carves out a distinct niche. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'user interview, codebase exploration, and module design, then submit as a GitHub issue' — in third-person voice, matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (create a PRD through interview/exploration/design and submit it as a GitHub issue) and when via a present 'Use when...' clause.	3 / 3
Trigger Term Quality	Uses natural terms a user would say — 'write a PRD', 'create a product requirements document', 'plan a new feature' — giving good coverage rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear PRD-creation niche with distinct triggers; 'plan a new feature' has minor overlap but the PRD framing makes conflict unlikely.	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: webiny/webiny-js
Path: .claude/skills/write-a-prd/SKILL.md
Commit: 484553b

Reviewed: about 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.