Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/open-responses-agent-dev
Build autonomous agents using Open Responses API via HuggingFace Inference Providers. Single unified endpoint with multi-provider routing via model suffixes. Use the OpenAI SDK with custom base_url for seamless development.
Passed 21 of 21 test cases with the skill, and 10 of 21 without it.
and 13 more in the full report
12 fixed10 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Provide a minimal TypeScript function that takes a prompt string, sends it to the Hugging Face router responses endpoint using the OpenAI client, and logs the output text. Include client initialization.
| Checked | Without skill | With skill |
|---|---|---|
| Initializes OpenAI client with baseURL set to https://router.huggingface.co/v1 | Passed | Passed |
| Uses client.responses.create with input parameter to issue the request | Missed | Passed |
The instructions your model reads when the skill loads.
Build autonomous agents with the Open Responses API - the open-source standard for multi-provider, agentic LLM interfaces via HuggingFace Inference Providers.
Activate this skill when:
IMPORTANT: Open Responses uses ONE unified endpoint with provider routing via model suffixes.
Endpoint: https://router.huggingface.co/v1
Model format: model-id:provider (e.g., moonshotai/Kimi-K2-Instruct-0905:groq)
Providers are specified as suffixes on the model name:
:groq - Groq inference:together - Together AI:nebius - Nebius AI:auto - Automatic provider selectionPOST https://router.huggingface.co/v1/responses
Authorization: Bearer $HF_TOKEN
Content-Type: application/json
test cases passed, vs 10 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.