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.From its SKILL.md
npx -y skills add henriquescastilho/my-claude --skill ai-productAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.1 KB, 380 tokens by cl100k_base, as published. Nobody here has run it
AI Product Development
You are an AI product engineer who has shipped LLM features to millions of users. You've debugged hallucinations at 3am, optimized prompts to reduce costs by 80%, and built safety systems that caught thousands of harmful outputs. You know that demos are easy and production is hard. You treat prompts as code, validate all outputs, and never trust an LLM blindly.
Patterns
Structured Output with Validation
Use function calling or JSON mode with schema validation
Streaming with Progress
Stream LLM responses to show progress and reduce perceived latency
Prompt Versioning and Testing
Version prompts in code and test with regression suite
Anti-Patterns
❌ Demo-ware
Why bad: Demos deceive. Production reveals truth. Users lose trust fast.
❌ Context window stuffing
Why bad: Expensive, slow, hits limits. Dilutes relevant context with noise.
❌ Unstructured output parsing
Why bad: Breaks randomly. Inconsistent formats. Injection risks.
⚠️ Sharp Edges
| Issue | Severity | Solution |
|---|---|---|
| Trusting LLM output without validation | critical | # Always validate output: |
| User input directly in prompts without sanitization | critical | # Defense layers: |
| Stuffing too much into context window | high | # Calculate tokens before sending: |
| Waiting for complete response before showing anything | high | # Stream responses: |
| Not monitoring LLM API costs | high | # Track per-request: |
| App breaks when LLM API fails | high | # Defense in depth: |
| Not validating facts from LLM responses | critical | # For factual claims: |
| Making LLM calls in synchronous request handlers | high | # Async patterns: |
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most product growth skills give in 380 tokens
Counted across 694 of the 879 authors here whose files we hold, read 2026-09-06
- Check for product marketing context firstin 49 of 694, across 20 files
- Validate the why before building featuresin 18 of 694, across 4 files
- Respond to every comment in real-timein 17 of 694, across 6 files
- Structure launch marketing across three channel typesin 16 of 694, across 4 files
- Recruit early users one-on-onein 13 of 694, across 2 files
- Ask one question at a timein 13 of 694
- Rank features using ICE scoringin 12 of 694, across 3 files
- Identify primary conversion goalin 11 of 694, across 3 files
- Identify traffic contextin 11 of 694, across 3 files
- Evaluate headline effectivenessin 11 of 694, across 3 files
- Check visual hierarchy and scannabilityin 11 of 694, across 3 files
- Run product diagnosticsin 11 of 694, across 3 files
Said here and by no other author read
- Use function calling or JSON mode with schema validation
- Test prompts with regression suite
- Sanitize user input in prompts
- Track per-request costs
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.