Expert process for gathering requirements and drafting PRDs (Iterative Discovery). Use when creating a PRD, speccing a new feature, or clarifying requirements.
94
95%
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 solid description that clearly communicates both what the skill does and when to use it, with good trigger terms that users would naturally employ. Its main weakness is that the 'what' portion could be more specific about the concrete actions involved (e.g., stakeholder interviews, user story definition, scope prioritization). Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions to the capability description, e.g., 'gathering requirements through iterative questioning, defining scope, user stories, and acceptance criteria, and drafting structured PRDs'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (PRDs, requirements) and mentions 'gathering requirements' and 'drafting PRDs' as actions, but doesn't list multiple concrete sub-actions like defining user stories, acceptance criteria, scope, etc. | 2 / 3 |
Completeness | Clearly answers both what ('gathering requirements and drafting PRDs') and when ('Use when creating a PRD, speccing a new feature, or clarifying requirements') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'PRD', 'speccing a new feature', 'clarifying requirements', 'creating a PRD'. These are phrases users would naturally say when they need this skill. | 3 / 3 |
Distinctiveness Conflict Risk | PRD creation and iterative requirements discovery is a clear niche. The triggers (PRD, speccing a feature, clarifying requirements) are distinct and unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that is lean, well-structured, and highly actionable. It clearly sequences a multi-step process with validation checkpoints, provides concrete examples and anti-patterns, and appropriately delegates detailed content to referenced files. The telegraphic style respects Claude's intelligence while providing all necessary guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place. No unnecessary explanations of what a PRD is or how product management works. Telegraphic style with clear labels and minimal filler. | 3 / 3 |
Actionability | Provides concrete, specific guidance: exact directory paths (docs/specs/), template file to load (references/prd-template.md), output naming convention (prd-[feature-name].md), example question format with options, and specific anti-pattern corrections ('Fast' -> 'Load < 200ms'). | 3 / 3 |
Workflow Clarity | Clear three-phase sequence (Discovery → Drafting → Verification) with an explicit iterative loop in Discovery ('Repeat until Actionable State'), a mandatory verification checklist, and anti-patterns serving as guardrails. The feedback loop of asking questions until sufficient info is gathered is well-defined. | 3 / 3 |
Progressive Disclosure | Concise overview with well-signaled one-level-deep references to the full PRD template and validation checklist. Content is appropriately split—the skill file stays lean while pointing to detailed materials. | 3 / 3 |
Total | 12 / 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 — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
4c72e76
Table of Contents
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.