create-prd
Interactive PRD creation wizard with comprehensive question flow
42
30%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/product-design/skills/create-prd/SKILL.mdQuality
Discovery
32%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 identifies its core purpose (PRD creation) but lacks the explicit trigger guidance required for Claude to reliably select it from a large skill library. It's missing concrete action verbs, natural user keywords, and a 'Use when...' clause that would make it complete and discoverable.
Suggestions
Add a 'Use when...' clause with trigger terms like 'product requirements', 'PRD', 'requirements document', 'product spec', 'feature specification'
List specific concrete actions such as 'gather stakeholder requirements', 'define user stories', 'outline acceptance criteria', 'generate PRD document'
Include common variations of terminology users might use: 'spec', 'product specification', 'requirements gathering', 'feature requirements'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (PRD creation) and mentions it's interactive with a question flow, but doesn't list specific concrete actions like 'gather requirements', 'define user stories', or 'generate specifications'. | 2 / 3 |
Completeness | Describes what it does (PRD creation wizard) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'PRD' which is a relevant keyword, but misses common variations users might say like 'product requirements', 'requirements document', 'spec', 'product spec', or 'feature specification'. | 2 / 3 |
Distinctiveness Conflict Risk | 'PRD' and 'wizard' provide some distinctiveness, but 'interactive' and 'comprehensive question flow' are generic patterns that could overlap with other wizard-style skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is excessively verbose, treating Claude as if it cannot generate appropriate prompts, examples, or wizard flows on its own. The content would be far more effective as a concise specification pointing to the template file, with brief notes on special handling requirements. The current format wastes significant context window space on example text and prompt templates that Claude could easily generate.
Suggestions
Reduce to a concise overview (under 100 lines) that specifies: the 15 section names, required vs optional sections, output format requirements, and special handling notes - let Claude generate the actual prompts and examples
Move all example prompts and responses to the referenced template file (prd-template.md) or a separate examples file, using progressive disclosure
Add explicit validation checkpoints: 'Validate user provided substantive content before proceeding' and 'Confirm before allowing skip on P0 sections'
Include actual executable code snippets for file operations (reading template, saving progress, writing final output) rather than prose descriptions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive example text that Claude doesn't need. The 500+ line document includes full example responses for every section, lengthy prompt templates, and explanatory text that assumes Claude cannot generate appropriate prompts or examples on its own. | 1 / 3 |
Actionability | Provides concrete structure and flow for the wizard, but lacks executable code. The 'Implementation Tips' and 'Error Handling' sections are vague guidance rather than specific implementations. No actual code for reading templates, saving files, or managing state. | 2 / 3 |
Workflow Clarity | The 15-section flow is clearly sequenced with section numbers, but lacks validation checkpoints. No explicit verification steps for user input quality, no feedback loops for error recovery, and the 'auto-save every 3 sections' is mentioned but not implemented. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with all 15 sections fully expanded inline. The template reference to 'prd-template.md' suggests content should be split, but instead everything is duplicated here. No clear separation between overview and detailed section content. | 1 / 3 |
Total | 6 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (658 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- jpoutrin/product-forge
- Commit
0ebe7ae
- 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.