nemo-curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
deep-research-synthesizer
Given outputs from 5 research sub-agents (time-sliced or partitioned), validate and synthesize them into a coherent, citation-backed Markdown deep research report with deduplication, contradiction handling, and explicit debug visibility when inputs are missing or malformed.
zotero-mcp-code
Search Zotero library using code execution for efficient multi-strategy searches without crash risks. Use this skill when the user needs comprehensive Zotero searches with automatic deduplication and ranking.