AlexWortega

Autonomously research, implement, train and ship ML code using the Hugging Face ecosystem. Port of huggingface/ml-intern as a Claude Code skill. Triggers when the user asks to implement, train, fine-tune, or reproduce an ML model / paper / dataset workflow (e.g. "implement DeepSeek-V3 at 100M", "fine-tune Qwen on dataset X", "reproduce paper Y"). Clarifies ambiguous tasks before starting, runs under an explicit experiment budget, explores multiple viable solution paths in parallel via implementation subagents, and diagnoses + retries failed runs. HF-native: pulls datasets/models/papers from the Hub, pushes trained checkpoints + run logs back to the Hub. Emits Telegram + Slack milestone alerts via scripts/notify.sh.

Use when the user asks for a peer review, critique, or meta-review of an academic paper (PDF, DOCX, or extracted text). Spawns N independent reviewer subagents in parallel under anonymized NATO codenames, then synthesizes a meta-review identifying common and unique concerns plus a CSV concerns table. Adapted from poldrack/ai-peer-review. Triggers on phrases like "peer review this paper", "critique this PDF", "review like a reviewer would", "meta-review this manuscript", "act as reviewer 2".