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. Cov...

Install with Tessl CLI

npx tessl i github:sickn33/antigravity-awesome-skills --skill ai-wrapper-product

What are skills?

Review — 48%

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/skill

Learn more

Evaluation — 92%

Agent success when using this skill

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

76%

Recipe Suggestion API Module

Prompt templates and structured output parsing

Criteria

Without context

With context

Anthropic SDK import

100%

Prompt template object

20%

50%

System prompt has role, format, tone

62%

100%

No placeholder text

100%

JSON schema in system prompt

70%

100%

Primary JSON.parse call

100%

Regex fallback for JSON

100%

Input validation

62%

max_tokens set

100%

Examples in prompt

100%

25%

Output validation after parse

Haiku model used

100%

75%

Without context: $0.6926 · 2m 18s · 28 turns · 27 in / 9,737 out tokens

With context: $0.3590 · 1m 11s · 18 turns · 301 in / 3,815 out tokens

100%

36%

AI Writing Assistant — Usage Metering Service

API cost tracking and usage limits

Criteria

Without context

With context

callWithCostTracking wrapper

100%

Logs userId

50%

100%

Logs input tokens

100%

Logs output tokens

100%

Cost calculated per call

100%

Haiku input rate 0.25/1M

100%

Haiku output rate 1.25/1M

100%

Monthly usage sum

100%

Limit enforced before API call

100%

Caching layer present

100%

max_tokens or output limit set

50%

100%

Model logged in usage record

100%

Without context: $0.4432 · 1m 48s · 15 turns · 64 in / 7,408 out tokens

With context: $0.9013 · 3m 40s · 29 turns · 61 in / 14,362 out tokens

100%

Job Application Screener — AI Backend Service

AI product architecture and domain differentiation

Criteria

Without context

With context

Input validation layer

100%

Prompt template with context

100%

Domain-specific system prompt

100%

Output parsing step

100%

Output validation step

100%

Fallback / error handling on bad output

100%

Retry logic present

100%

Post-processing step

100%

Model selection justified

100%

Workflow integration

100%

No thin wrapper

100%

Role/format/tone in system prompt

100%

Without context: $0.3164 · 1m 22s · 14 turns · 14 in / 4,650 out tokens

With context: $0.5276 · 1m 56s · 24 turns · 275 in / 5,991 out tokens

Evaluated: 1 day ago
Agent: Claude Code

Table of Contents

Recipe Suggestion API Module AI Writing Assistant — Usage Metering Service Job Application Screener — AI Backend Service

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.