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.
38
24%
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/antigravity-ai-wrapper-product/SKILL.mdQuality
Discovery
22%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 reads more like a marketing tagline or persona statement than a functional skill description. It lacks concrete actions, has no 'Use when...' clause, and uses first-person-adjacent framing ('Expert in...') rather than describing what the skill does. The core concept of AI API wrapper products is a valid niche but is poorly articulated for skill selection purposes.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user wants to build a SaaS product, AI wrapper, or commercial tool on top of OpenAI, Anthropic, or other AI APIs.'
Replace the vague 'building products' with specific concrete actions, e.g., 'Designs API integration architectures, creates prompt engineering pipelines, plans pricing/monetization strategies, and structures AI-powered SaaS applications.'
Rewrite in third person describing capabilities rather than expertise, e.g., 'Guides development of commercial AI wrapper products...' instead of 'Expert in building products...'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'building products' and 'focused tools' without listing concrete actions. It describes a philosophy ('not just ChatGPT but different') rather than specific capabilities like 'designs API integration architectures, creates pricing models, builds prompt pipelines.' | 1 / 3 |
Completeness | The 'what' is vaguely stated (building products that wrap AI APIs) but lacks specifics, and there is no 'when' clause or explicit trigger guidance at all. The absence of a 'Use when...' clause caps this at 2, and the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'AI APIs', 'OpenAI', 'Anthropic', and 'products' that users might mention. However, it misses common natural terms like 'SaaS', 'wrapper', 'monetize', 'API integration', 'AI product', or 'startup' that users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The AI API wrapper product niche is somewhat specific, but 'building products' and 'solving specific problems with AI' are broad enough to overlap with general coding skills, AI development skills, or product management skills. | 2 / 3 |
Total | 6 / 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 long and monolithic, trying to cover too many topics (architecture, prompt engineering, cost management, differentiation, rate limiting, hallucination handling, latency, collaboration) in a single file without any progressive disclosure. While it provides some useful executable code examples, many are incomplete with undefined helper functions, and the overall structure is padded with generic advice and redundant headers that waste tokens. The skill would benefit enormously from being split into focused sub-files and trimmed of content Claude already knows.
Suggestions
Split the monolithic content into separate files (e.g., COST_MANAGEMENT.md, PROMPT_ENGINEERING.md, RATE_LIMITING.md) and reference them from a concise overview in SKILL.md
Remove the role-playing preamble, capabilities/expertise lists, 'When to Use' triggers, and generic strategy advice (thin wrappers table, differentiation strategies) that don't provide actionable technical guidance
Complete code examples by either implementing the helper functions (getUserPlan, hashPrompt, extractDates) or replacing them with inline logic so snippets are truly copy-paste ready
Add explicit validation checkpoints to the main product architecture workflow (e.g., 'verify API key works before proceeding', 'test prompt template with sample input before building UI')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Repeats section headers (e.g., 'AI Product Architecture' appears twice), includes unnecessary role-playing preamble, explains obvious concepts (what thin wrappers are, what rate limits are), and lists capabilities/expertise that add no actionable value. Tables like 'Avoid Thin Wrappers' and 'Use Cases to Avoid' are generic advice Claude already knows. | 1 / 3 |
Actionability | Provides concrete JavaScript code examples that are mostly executable (API calls, retry logic, streaming, caching), which is good. However, many snippets rely on undefined helper functions (getUserPlan, getDailyUsage, hashPrompt, extractDates) making them incomplete. The model selection table uses vague cost indicators ($, $$) rather than actual prices, and some code references outdated model names. | 2 / 3 |
Workflow Clarity | The 'Wrapper Stack' diagram provides a clear high-level sequence, and the Sharp Edges sections follow a problem→symptoms→fix pattern. However, there are no explicit validation checkpoints in the main architecture workflow, no feedback loops for the overall build process, and the collaboration workflows at the end are just numbered lists without verification steps. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files despite being extremely long. All content—architecture, prompt engineering, cost management, differentiation, sharp edges, validation checks, collaboration workflows—is crammed into a single file. There are no bundle files to offload detailed sections to, and the content would greatly benefit from splitting into separate reference documents. | 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 (689 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
- boisenoise/skills-collections
- Commit
431bfad
- 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.