ai-product-patterns
Builds AI-native products using OpenAI's development philosophy and modern AI UX patterns. Use when integrating AI features, designing for model improvements, implementing evals as product specs, or creating AI-first experiences. Based on Kevin Weil (OpenAI CPO) on building for future models, hybrid approaches, and cost optimization.
80
76%
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 ./ai-product-patterns/SKILL.mdQuality
Discovery
67%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 description has good structure with explicit 'Use when' triggers and clear attribution to a specific source (Kevin Weil/OpenAI). However, the capabilities described are somewhat abstract ('AI-native products', 'modern AI UX patterns') rather than concrete actions, and the trigger terms could be expanded to include more natural user language variations.
Suggestions
Add more concrete actions like 'design streaming interfaces', 'implement fallback strategies', 'structure evaluation frameworks' to improve specificity
Expand trigger terms to include natural variations users might say: 'LLM integration', 'ChatGPT-style features', 'AI product roadmap', 'prompt optimization'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AI-native products, OpenAI philosophy) and mentions some actions like 'integrating AI features', 'implementing evals', 'designing for model improvements', but these are somewhat abstract rather than concrete specific actions like 'extract text' or 'create pivot tables'. | 2 / 3 |
Completeness | Clearly answers both what ('Builds AI-native products using OpenAI's development philosophy') and when ('Use when integrating AI features, designing for model improvements, implementing evals as product specs, or creating AI-first experiences') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'AI features', 'evals', 'AI-first experiences', 'cost optimization', but missing common variations users might say like 'LLM integration', 'prompt engineering', 'AI product design', or 'OpenAI API'. | 2 / 3 |
Distinctiveness Conflict Risk | The OpenAI-specific focus and Kevin Weil attribution provide some distinctiveness, but 'AI features' and 'AI-first experiences' are broad enough to potentially overlap with other AI/ML related skills. | 2 / 3 |
Total | 9 / 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 comprehensive, actionable skill with excellent code examples and clear workflows for building AI-native products. The main weakness is verbosity - the content could be 30-40% shorter while preserving all actionable guidance. The repetition of concepts across sections (hybrid approaches explained multiple times, similar examples repeated) inflates token count unnecessarily.
Suggestions
Consolidate the hybrid approach explanations - currently explained in section 3, the decision tree, and multiple examples with redundant content
Remove the 'Common Pitfalls' section as it largely repeats guidance already covered in the main frameworks
Trim explanatory text around code examples - the code is self-documenting and doesn't need extensive prose setup
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains valuable content but is verbose with repetitive explanations and excessive formatting. Many concepts are over-explained (e.g., the hybrid approach is explained multiple times with similar examples), and some sections like 'Common Pitfalls' repeat earlier content. | 2 / 3 |
Actionability | Provides concrete, executable code examples throughout including JavaScript/TypeScript patterns for hybrid approaches, evals as tests, streaming implementations, and cost optimization strategies. Templates are copy-paste ready with clear structure. | 3 / 3 |
Workflow Clarity | Clear decision tree for when to use AI vs traditional code, well-structured checklists (Before Building, During Build, Before Ship), and explicit validation steps in the evals approach. The sequential flow from spec to implementation to shipping is well-defined. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections progressing from core frameworks to templates to examples. References to related skills and further learning files are clearly signaled at the end. Content is appropriately structured for a comprehensive skill. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (539 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- menkesu/awesome-pm-skills
- Commit
53530ef
- 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.