ai-wrapper-product
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS.
Install with Tessl CLI
npx tessl i github:duclm1x1/Dive-Ai --skill ai-wrapper-product82
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
100%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 strong skill description that clearly defines its niche (AI wrapper products), lists specific capabilities (prompt engineering, cost management, rate limiting), and includes explicit trigger terms. The description effectively differentiates itself from generic AI or coding skills by focusing on the business and product aspects of wrapping AI APIs.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'building products that wrap AI APIs', 'prompt engineering for products', 'cost management', 'rate limiting', and 'building defensible AI businesses'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (building AI wrapper products, prompt engineering, cost management, rate limiting, defensible businesses) AND when (explicit 'Use when:' clause with specific trigger terms). | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms users would say: 'AI wrapper', 'GPT product', 'AI tool', 'wrap AI', 'AI SaaS'. Also includes API provider names (OpenAI, Anthropic) that users would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Carves out a clear niche around AI wrapper products specifically, distinguishing from general AI/coding skills. The focus on business aspects (cost, defensibility, SaaS) and specific trigger terms make it unlikely to conflict with general programming or AI skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable code examples for building AI wrapper products with good coverage of cost management and prompt engineering. However, it includes some unnecessary introductory framing, the Sharp Edges section references non-existent solution sections, and workflow validation could be more explicit with retry/fallback patterns.
Suggestions
Remove the introductory paragraph and Capabilities list - Claude doesn't need to be told its role or what it knows
Fix Sharp Edges section to either include the referenced solutions inline or link to actual files (e.g., [COST_CONTROL.md](COST_CONTROL.md))
Add explicit retry/fallback workflow for API failures: call -> validate -> retry with backoff -> fallback model -> error handling
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some unnecessary framing ('AI wrappers get a bad rap') and the Capabilities section lists things Claude already knows. However, the code examples and tables are reasonably efficient. | 2 / 3 |
Actionability | Provides fully executable JavaScript code examples with real SDK usage, concrete prompt templates, cost calculation functions, and specific model comparisons with pricing. Copy-paste ready implementations. | 3 / 3 |
Workflow Clarity | The wrapper stack diagram shows clear sequence, but validation steps are mentioned without explicit feedback loops. The cost management section lacks a complete workflow for handling limit exceeded scenarios gracefully. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with sections, but the Sharp Edges section references solutions (## Controlling AI Costs) that don't exist as separate files or clear anchors. Related Skills mentions other skills but no actual file references for advanced topics. | 2 / 3 |
Total | 9 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- 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.