Individual skill
tooluniverse-ml-inference-utility
Generic ML/NLP/vision inference against any HuggingFace-hosted model (serverless hf-inference provider) — text classification/sentiment, dense text embeddings for semantic similarity, masked-token prediction (including protein language models), summarization, zero-shot classification against caller-supplied labels, named entity recognition, extractive question answering, translation, image classification, and object detection. Use when someone asks to "classify this text with a HuggingFace model", "embed this text for similarity search", "run NER on this passage", "summarize this with model X", "zero-shot classify this against these labels", "predict the masked token", "classify/detect objects in this image", or names a specific HuggingFace model_id to run inference with. NOT a domain-analysis skill itself — this is a generic cross-domain utility other skills should reach for as a supporting step, the same way tooluniverse-clinical-terminology-lookup is a supporting lookup step rather than a research domain. NOT for training/fine-tuning models (inference only, against already-hosted models). Honest: as of this writing, HuggingFace's serverless inference API requires a valid HF_TOKEN for every one of these 10 tools, on every model tested — live-verified, not assumed from the "optional" wording in the tools' own descriptions. Also covers finding a model_id first via HuggingFace Hub search (HuggingFace_search_models/get_model/search_datasets — a separate, token-free catalog API) and running inference on Replicate-hosted models (Replicate_run_prediction/get_prediction) as an alternative platform when a model isn't served by HuggingFace's hf-inference provider.
skills/tooluniverse-ml-inference-utility/SKILL.md
Source commit 5598a9fc97e32964fe9b703818e7d0747142f179
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 5, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,777
- Repository last updated
- Nov 8, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agents Repository topic
- reasoning-agent Repository topic
- reasoning-language-models Repository topic
- tool-use Repository topic
- ai-agents Repository topic
- ai-scientists Repository topic
- automated-science Repository topic
- co-pilot Repository topic
- co-scientist Repository topic
- ai-for-science Repository topic
- writing Derived category
- research Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 15,443 bytesSKILL.mdcore · 15,443 bytesreferences/hf_inference_tool_reference.mddoc · 7,154 bytes
Read excerpt
# Generic ML/NLP/Vision Inference (HuggingFace)
Run any HuggingFace-hosted model for a standard inference task via ToolUniverse's
10 `HFInference_*` tools. This is a **utility skill**: reach for it as a supporting
step inside another workflow (e.g. summarizing a batch of retrieved abstracts,
extracting entities from clinical text, embedding sentences for a similarity
search) rather than treating it as a research domain in its own right.
## Honesty contract (read first) — the token requirement is not actually optional
Every tool's own JSON description says `HF_TOKEN` is an *optional* API key that
merely "raises rate limits." **Live testing on this date contradicts that**: all
10 tools, tested against the exact model IDs in their own `test_examples`, fail
with the identical error with no token set: