“Hugging Face”

Detect and defend against indirect prompt injection hidden in web pages, documents, and images consumed by an agent, via content extraction (HTML/PDF/OCR)…

Search traceable academic papers, download legally accessible PDFs from arXiv and open-access sources, convert PDFs or page images to Markdown with a…

Refuse an arena.ai scrape.

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity…

Generate the canonical AI Runtime handoff at migrate/output/air_workload from an approved TRL template.

Retired compatibility skill for the former agent-side UC model-materialization workflow.

Build transformer fine-tuning run plans with task settings, hyperparameters, and model-card outputs.

Empirically tune GGUF model's llama-swap/llama.cpp config for multi-GPU rig — card placement, KV-cache quant, context length, batch sizes, prompt-cache…

Disposable meta-skill (delete after the harness is built): scaffolds an opinionated, reproducible Python data-science project and its agent harness.

Aggregate and summarize AI/LLM/Agent news from multiple sources.