ai-wrapper-product
You know AI wrappers get a bad rap, but the good ones solve real problems. You build products where AI is the engine, not the gimmick. You understand prompt engineering is product development. You balance costs with user experience. You create AI products people actually pay for and use daily.
25
7%
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 ./skills/ai-wrapper-product/SKILL.mdQuality
Discovery
0%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 reads like a marketing pitch or personal manifesto rather than a functional skill description. It uses second-person voice ('You know', 'You build', 'You understand'), provides no concrete actions, no trigger guidance, and no clear scope. It would be nearly impossible for Claude to correctly select this skill from a list of alternatives.
Suggestions
Rewrite in third person and list specific concrete actions (e.g., 'Designs AI-powered product architectures, writes optimized prompts for production use, structures API call chains, and estimates token costs').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when building an AI wrapper, SaaS product with LLM integration, or when the user asks about prompt engineering for production, API cost optimization, or AI product monetization').
Remove motivational/opinion language ('get a bad rap', 'not the gimmick', 'people actually pay for') and replace with specific, actionable capability descriptions that distinguish this skill from general AI development skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'solve real problems', 'AI is the engine', and 'balance costs with user experience'. No concrete actions are listed — there's nothing about what this skill actually does (e.g., build APIs, design prompts, create pricing models). | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is clearly answered. There is no 'Use when...' clause or equivalent trigger guidance. The description reads like a personal brand statement rather than a functional skill description. | 1 / 3 |
Trigger Term Quality | The only potentially relevant keywords are 'AI wrappers' and 'prompt engineering', but these are buried in motivational language. Missing natural user terms like 'API integration', 'LLM app', 'SaaS', 'AI product', 'wrapper app', or specific frameworks/tools. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic — 'build products where AI is the engine' could apply to virtually any AI-related skill. There are no distinct triggers that would help Claude differentiate this from other AI or product development skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a verbose, poorly structured collection of AI wrapper product concepts that lacks clear workflows and actionable guidance. The code examples provide some value but are undermined by broken markdown nesting, references to nonexistent sections, and stale model/pricing information. The content reads more like a blog post overview than a focused skill that teaches Claude how to perform specific tasks.
Suggestions
Restructure into a clear workflow: 1) Define product value prop → 2) Design prompt templates → 3) Implement with validation → 4) Add cost tracking → 5) Test and iterate, with explicit validation checkpoints at each stage.
Remove the capabilities bullet list, role re-statement, and 'When to Use' tautology — these waste tokens without adding actionable information.
Fix the broken Sharp Edges references (e.g., '## Controlling AI Costs') by either including those sections or linking to separate files, and split detailed code examples into referenced files for progressive disclosure.
Fix the nested markdown code fences — several patterns have code blocks inside code blocks that won't render correctly, making the examples non-executable as written.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with significant redundancy. The role description is repeated from the frontmatter. Capability bullet lists add no value Claude doesn't already know. Anti-patterns use fragmented sentence style that wastes tokens while being less clear. The 'When to Use' section is a meaningless tautology. Model selection tables contain time-sensitive pricing data that will become stale. | 1 / 3 |
Actionability | Contains some executable code examples (API calls, cost tracking, prompt templates) which is good, but much of the content is conceptual rather than actionable. The architecture diagram is ASCII art rather than executable guidance. The Sharp Edges table references sections (e.g., '## Controlling AI Costs') that don't exist in the document. Several code blocks are nested inside markdown code fences incorrectly. | 2 / 3 |
Workflow Clarity | There is no clear end-to-end workflow for building an AI wrapper product. The content is organized as disconnected patterns without sequencing. There are no validation checkpoints, no feedback loops for error recovery, and no clear process for going from idea to working product. The basic implementation shows numbered steps within a single function but lacks broader workflow guidance. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline regardless of depth. The Sharp Edges table references sections that don't exist. The 'Related Skills' section mentions other skills but provides no links. There's no separation between quick-start overview and detailed reference material. | 1 / 3 |
Total | 5 / 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 | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
d739c8b
- 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.