ai-product

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.

1.37x

Quality

19%

Does it follow best practices?

Impact

80%

1.37x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

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

Evaluation results

95%

39%

Internal Knowledge Base Q&A Service

RAG structured output and async patterns

Criteria

Without context

With context

Structured output format

70%

No raw text parsing

100%

Input sanitization

30%

100%

Token estimation

75%

Context window management

50%

100%

Async LLM call

100%

Output validation

60%

100%

Retry or fallback

100%

Structured response fields

100%

Prompt as named variable

100%

No unconditional context dump

87%

100%

79%

27%

Product Content Generation Service

Prompt versioning, streaming, and cost tracking

Criteria

Without context

With context

Prompts in separate module

100%

Named versioned prompts

100%

Streaming enabled

100%

Incremental chunk processing

100%

Token usage recorded

100%

80%

Cost logged per request

100%

Output validated

20%

100%

Factual content addressed

Structured output

100%

Async LLM calls

API failure handling

37%

README covers prompt management

100%

68%

Customer Service Chatbot Safety Layer

Input sanitization and output safety validation

Criteria

Without context

With context

Input sanitization present

60%

100%

Injection pattern handling

100%

Structured output parsing

40%

Output schema validation

20%

Factual/compliance claim handling

50%

Safe fallback on validation failure

100%

Retry on API failure

100%

Graceful degradation

100%

Async call pattern

Multi-layer defence

100%

No production shortcuts

100%

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

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

Table of Contents

Internal Knowledge Base Q&A Service Product Content Generation Service Customer Service Chatbot Safety Layer

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.