prd
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
84
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 well-crafted skill description with strong trigger terms and clear completeness. The explicit 'Use when...' clause and 'Triggers on:' section make it highly actionable for skill selection. The main weakness is limited specificity about what concrete actions the PRD generation involves beyond the high-level task.
Suggestions
Expand specificity by listing concrete PRD components: 'Generate PRDs including user stories, acceptance criteria, technical requirements, and success metrics'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (PRD/product requirements) and the core action (generate a PRD), but doesn't list multiple specific concrete actions like 'define user stories, outline acceptance criteria, specify technical requirements'. | 2 / 3 |
Completeness | Clearly answers both what ('Generate a Product Requirements Document for a new feature') and when ('Use when planning a feature, starting a new project, or when asked to create a PRD') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create a prd', 'write prd for', 'plan this feature', 'requirements for', 'spec out' - these are realistic phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on PRD generation with distinct triggers like 'prd', 'requirements', 'spec out' that are unlikely to conflict with general documentation or coding skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with clear workflow and excellent concrete examples. The main weakness is verbosity—the skill could be more concise by trimming explanatory content Claude already knows and potentially splitting the detailed example into a separate file. The lettered question format and complete PRD template are particularly strong.
Suggestions
Remove the 'Writing for Junior Developers' section—Claude can infer appropriate detail level from the PRD structure itself
Move the full example PRD to a separate EXAMPLE.md file and reference it, keeping only a brief snippet inline
Trim redundant explanations like 'This lets users respond with 1A, 2C, 3B for quick iteration'—the format is self-evident
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary explanation (e.g., 'The PRD reader may be a junior developer or AI agent' section, explaining what PRDs are for). The example PRD, while useful, is quite lengthy and could be trimmed. | 2 / 3 |
Actionability | Highly actionable with concrete templates, specific formatting examples, exact file naming conventions, and a complete example PRD. The lettered question format and markdown templates are copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear 4-step workflow (receive → ask questions → generate → save) with explicit validation checklist at the end. The 'Important: Do NOT start implementing' constraint is a clear checkpoint. Steps are well-sequenced. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, but everything is in one file. The lengthy example PRD and detailed section explanations could be split into separate reference files (e.g., EXAMPLES.md, SECTIONS.md) for better organization. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
- Repository
- snarktank/ralph
- Commit
6c53cb0
- 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.