create-prd
Generates a clear, actionable Product Requirements Document (PRD) in Markdown from a feature description. Use when a user asks to plan a feature, define requirements, or create a PRD. Covers goals, user stories, requirements, and non-goals for Rails-oriented workflows.
93
92%
Does it follow best practices?
Impact
91%
1.49xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly communicates what the skill does, when to use it, and what domain it targets. It includes specific deliverables (goals, user stories, requirements, non-goals), explicit trigger conditions, and a distinctive Rails-oriented scope. The description is concise, uses third-person voice, and covers natural trigger terms effectively.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and outputs: 'Generates a clear, actionable Product Requirements Document (PRD) in Markdown', and specifies it covers 'goals, user stories, requirements, and non-goals for Rails-oriented workflows'. | 3 / 3 |
Completeness | Clearly answers both what ('Generates a clear, actionable PRD in Markdown covering goals, user stories, requirements, and non-goals') and when ('Use when a user asks to plan a feature, define requirements, or create a PRD') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'plan a feature', 'define requirements', 'create a PRD', 'Product Requirements Document', 'PRD', 'feature description'. These cover common variations of how users would request this. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: PRD generation specifically for Rails-oriented workflows. The combination of PRD, Markdown output, and Rails context makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides clear, actionable guidance for generating PRDs. The workflow is well-sequenced with validation checkpoints and hard gates. The main weakness is moderate verbosity — the Common Mistakes and Red Flags sections overlap, and some guidance (like the clarifying question format example) explains things Claude can already do well.
Suggestions
Merge 'Common Mistakes' and 'Red Flags' into a single concise table to eliminate redundancy and save tokens.
Trim the clarifying questions format example — Claude already knows how to format multiple-choice questions; a single-line instruction would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and well-structured, but includes some content that could be tightened — the 'Common Mistakes' and 'Red Flags' sections overlap significantly, and the clarifying questions section is somewhat verbose given Claude already understands Socratic questioning. The question format example with A/B/C/D options adds bulk for something Claude can infer. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: a specific PRD structure with 10 numbered sections, exact filename conventions (prd-[feature-name].md), exact output location (/tasks/), a clear process with numbered steps, and a hard gate constraint. The question format example and table-based quick reference make execution unambiguous. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced in 7 numbered steps with explicit validation (step 6: re-read and verify), a hard gate preventing premature implementation, conditional branching (skip questions if prompt is detailed), and clear next-step chaining. The quick reference table provides an excellent at-a-glance summary of the entire workflow. | 3 / 3 |
Progressive Disclosure | The skill is well-organized with a quick reference table up front, clearly delineated sections, and an integration table at the bottom that signals related skills with one-level-deep references. Content is appropriately structured for a single SKILL.md file without needing external references, and navigation is easy via clear headers. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- igmarin/rails-agent-skills
- Commit
ae8ea63
- Reviewed
Table of Contents
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.