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.

1.20x

Quality

78%

Does it follow best practices?

Impact

84%

1.20x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/ai-wrapper-product/SKILL.md

Evaluation results

76%

33%

Blog Post Generator Module

Structured output and prompt engineering

Criteria

Without context

With context

Correct SDK package

100%

Input validation present

100%

Input length limit

System prompt with role

100%

System prompt specifies format/tone

100%

JSON schema in prompt

70%

100%

No text outside JSON instruction

87%

100%

No placeholder text instruction

JSON parse with try/catch

100%

Regex fallback for JSON extraction

50%

100%

Cost-appropriate model

100%

Examples in prompt

100%

AI API Cost Management System

API cost tracking and usage limits

Criteria

Without context

With context

Logs input tokens

100%

Logs output tokens

100%

Logs cost per call

100%

Logs userId

100%

Logs model name

100%

Per-model rate table

100%

Cost formula uses 1M divisor

100%

Separate input/output rates

100%

Monthly window for limit check

100%

Limit throws before API call

100%

Per-user limit lookup

100%

Correct SDK package

100%

78%

Job Description Analyzer

Domain expertise, retry logic, and output validation

Criteria

Without context

With context

Structured output returned

100%

Output parsing present

80%

100%

Domain-specific post-processing

25%

Retry on failure

100%

70%

Fallback model configured

Input validation

100%

System prompt defines role

100%

JSON schema in prompt

60%

100%

Correct SDK package

100%

Appropriate model choice

100%

design-notes explains domain logic

100%

Repository: haniakrim21/everything-claude-code
Commit: ae2cadd

Evaluated: 18 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Blog Post Generator Module AI API Cost Management System Job Description Analyzer

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.