prd-designer

Transforms loose ideas or refined concepts into structured PRDs that capture the what, who, and why — problem, target users, goals, non-goals, and testable acceptance criteria — while deliberately deferring the how (architecture, data models, APIs, delivery phasing) to the planning phase. Works through a progressive interview, light de-risking of risky assumptions, and optional codebase exploration. Use when asked to "write a PRD", "create a PRD", "design a feature", "flesh out this idea", "turn this into a spec", "product requirements", "spec this out", or /prd-designer. Outputs a markdown PRD at docs/prds/{name}.md. Optionally creates a GitHub issue via gh CLI. Dependencies: gh CLI (optional, for issue creation).

Quality

96%

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

92%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 content is a well-structured, actionable, and navigable 5-phase workflow with concrete commands, limits, validation checkpoints, and appropriately offloaded references. Its only weakness is mild redundancy in restating the 'defer the how' principle and a few preachy phrases that pad token use.

Suggestions

Consolidate the repeated 'do not write architecture/data models/APIs/how' guidance into the core principle section and reference it once from each phase instead of re-explaining it in Phases 2, 3, and 4.

Trim editorial phrasing like 'Enforce it relentlessly' and 'The PRD draws the perimeter of the solution space; planning and design fill it in' to directive statements that assume Claude's competence.

Consider moving the AC-ID traceability rationale paragraph into references/prd-template.md, keeping only the operative rule (stable AC-N IDs, never renumbered) in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete phases, rules, and limits, but restates the 'defer the how / don't write architecture' principle across multiple sections and includes light preaching ('Enforce it relentlessly') that could be trimmed, fitting the 4 anchor rather than the lean 5 anchor.	4 / 5
Actionability	Provides copy-paste-ready commands (gh auth status, gh issue create --title ... --body "$(cat ...)", /plan-with-docs docs/prds/{kebab-name}.md), exact output paths, and concrete numeric limits (3 questions per message, 3 assumptions max, 2 cycles), so the guidance is fully executable for an instruction-only skill.	5 / 5
Workflow Clarity	A clearly sequenced 5-phase pipeline with explicit validation checkpoints (confirm understanding, probing stop-conditions, user validation of findings, review rounds), error handling, and edge cases, matching the 5 anchor's feedback loops and checklists; the destructive/batch cap does not apply to PRD drafting.	5 / 5
Progressive Disclosure	The body is an overview of the pipeline that delegates detail to two clearly signaled, one-level-deep, real reference files (references/prd-template.md and references/probing-guide.md), matching the 5 anchor for well-signaled shallow references and easy navigation.	5 / 5
	Total	19 / 20 Passed

Description

100%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 concrete, comprehensive, and well-triggered, clearly stating both capability and use conditions in third person with no over-claims. It is among the strongest examples and needs no changes.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — capturing problem/users/goals/non-goals/acceptance criteria, running a progressive interview, de-risking assumptions, optional codebase exploration, writing a markdown PRD, and optionally creating a GitHub issue — giving comprehensive coverage, matching the 5 anchor rather than the 4 anchor's 'minor gaps'.	5 / 5
Completeness	Explicitly answers both what (transforms ideas into structured PRDs capturing what/who/why) and when (Use when asked to...) with concrete trigger phrases, satisfying the 5 anchor and avoiding the 'missing Use when' cap at 3.	5 / 5
Trigger Term Quality	Covers natural trigger phrases users would actually say — 'write a PRD', 'create a PRD', 'design a feature', 'flesh out this idea', 'turn this into a spec', 'product requirements', 'spec this out', and /prd-designer — with synonym coverage, matching the comprehensive 5 anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear PRD-design niche with distinct triggers and explicitly defers the 'how' to a separate /plan planning phase, so conflict risk with adjacent skills is minimal, matching the 5 anchor.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: MrToxy/claude-skills
Path: prd-designer/SKILL.md
Commit: 66c7102

Reviewed: 3 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.