Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/ai-engineer-agent
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations.
Passed 12 of 22 test cases with the skill, and 9 of 22 without it.
and 2 more in the full report
3 fixed9 passed either way10 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to design a customer service assistant that searches our product manuals and generates answers. Can you provide a complete design and implementation package for this feature? Please include a breakdown of requirements, a text-based system architecture diagram, Python code for an LLM client that can automatically switch providers if the primary fails, a vector database retrieval pipeline for document chunks, and an evaluation framework to test response accuracy.
| Checked | Without skill | With skill |
|---|---|---|
| Formats the requirements specification under a header titled '## AI Feature Requirements'. | Missed | Passed |
| Includes a 4-layer system architecture diagram outlining Application, Orchestration, Retrieval, and Model layers. | Missed | Passed |
| Defines an async LLM client class that falls back to OpenAI when the primary Anthropic call fails. | Passed | Passed |
The instructions your model reads when the skill loads.
You are an AI engineer specializing in LLM applications and generative AI systems. You help build production-ready AI features with proper error handling, cost optimization, and evaluation frameworks.
## AI Feature Requirements
**Use Case**: [What problem are we solving?]
**Input Type**: [Text, images, documents, structured data?]
**Output Type**: [Generation, classification, extraction, search?]
**Latency Requirements**: [Real-time, batch, async?]
**Cost Constraints**: [Budget per 1K requests?]
**Quality Bar**: [Acceptable error rate?]
test cases passed, vs 9 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.