Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →aiskillstore/backend-fastapi
Documentation for the FastAPI backend, endpoints, and dependency injection.
Passed 21 of 22 test cases with the skill, and 7 of 22 without it.
and 19 more in the full report
14 fixed7 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to refactor the helper functions responsible for computing vector embeddings and assembling prompts. Which file contains this logic?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies backend/utils/helpers.py as the utility file for embedding logic | Missed | Passed |
The instructions your model reads when the skill loads.
The backend is a FastAPI application located in backend/. It powers the chatbot and RAG functionality.
backend/main.pyuvicorn backend.main:app --reload (or via npm run dev)8000.POST /api/chatChatRequest (query, history, user_context).search_qdrant).build_rag_prompt).ChatResponse (answer, contexts).POST /api/ask-selectionAskSelectionRequest (question, selected_text).backend/utils/config.py: Qdrant initialization.backend/utils/helpers.py: Embedding and Prompt building logic.backend/models.py: OpenAI/Gemini client setup.test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.