common-product-requirements
Expert process for gathering requirements and drafting PRDs (Iterative Discovery). Use when creating a PRD, speccing a new feature, or clarifying requirements. (triggers: PRD.md, specs/*.md, create prd, draft requirements, new feature spec)
90
87%
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 skill description that clearly communicates its purpose and when to use it. The explicit 'Use when' clause with parenthetical trigger terms is well done. The main weakness is that the specificity of concrete actions could be improved—it describes the process at a high level ('gathering requirements and drafting PRDs') without enumerating the specific steps or outputs involved.
Suggestions
Add more specific concrete actions, e.g., 'Conducts stakeholder interviews, defines acceptance criteria, structures PRD sections, and iterates on scope' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (PRDs, requirements) and mentions 'gathering requirements and drafting PRDs' with 'Iterative Discovery' as a process name, but doesn't list multiple concrete actions like reviewing stakeholder input, defining acceptance criteria, or structuring sections. | 2 / 3 |
Completeness | Clearly answers both 'what' (gathering requirements and drafting PRDs via iterative discovery) and 'when' (explicit 'Use when' clause with triggers for creating PRDs, speccing features, or clarifying requirements, plus parenthetical trigger terms). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'PRD', 'create prd', 'draft requirements', 'new feature spec', file patterns like 'PRD.md' and 'specs/*.md'. These cover common variations of how users would phrase requests related to product requirement documents. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to PRD creation and feature specification with distinct file-pattern triggers (PRD.md, specs/*.md). Unlikely to conflict with general coding, documentation, or other skills due to the specific domain focus. | 3 / 3 |
Total | 11 / 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 well-structured, concise skill that clearly defines an iterative discovery-then-drafting workflow for PRD creation. Its strengths are excellent token efficiency, clear phase sequencing with a verification checklist, and appropriate use of external references. The main weakness is that some key concepts (like 'Actionable State' criteria and the template structure) are left undefined, which slightly reduces actionability.
Suggestions
Define explicit criteria for 'Actionable State' (e.g., 'All sections of the template have answers or are explicitly marked TBD with owner') so Claude knows when to stop the discovery loop.
Include a brief outline or key sections of the PRD template inline so the skill remains functional even if the referenced template file doesn't exist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line is purposeful and dense. No unnecessary explanations of what a PRD is or how product management works. The telegraphic style (e.g., 'PRD = "What", Implementation Plan = "How"') is efficient and assumes Claude's competence. | 3 / 3 |
Actionability | Provides a clear process with concrete examples (e.g., the multi-choice question format), but relies on an external template (`references/prd-template.md`) without showing its structure. The guidance is specific but not fully self-contained—key details like what the template contains or what 'Actionable State' means concretely are missing. | 2 / 3 |
Workflow Clarity | The three-phase workflow (Discovery → Drafting → Verification) is clearly sequenced with explicit iteration ('Repeat until Actionable State'), filesystem operations, and a mandatory verification checklist that serves as a validation checkpoint before completion. | 3 / 3 |
Progressive Disclosure | The skill is a concise overview with well-signaled one-level-deep references to the full PRD template and validation checklist. Content is appropriately split between the overview and referenced files. | 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
- HoangNguyen0403/agent-skills-standard
- Commit
19a1140
- 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.