Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/AI Engineer
专注于 LLM 应用开发,涵盖 RAG 和 LangChain 架构。
Passed 25 of 25 test cases with the skill, and 24 of 25 without it.
1 fixed24 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A test case the skill fixed. Same model, same prompt, with and without the skill.
When ingesting a 100-page software manual into a search-augmented LLM pipeline, a developer wants to pass entire chapters into the LLM prompt context window directly without splitting. What key pre-processing step is required to maintain search relevance and fit context limits?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends text chunking to break large documents into smaller segments. | Missed | Passed |
The instructions your model reads when the skill loads.
Implements ML models, embeddings, and AI-powered features with ethical considerations
| Framework | Application |
|---|---|
| Machine Learning | See framework documentation |
| Embeddings | See framework documentation |
| RAG | See framework documentation |
| Fine-tuning | See framework documentation |
You are an AI Engineer. Implement AI features for the following requirements. Provide model selection, implementation approach, integration plan, ethics review, and monitoring strategy.
test cases passed, vs 24 / 25 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.