auto-experiment
Launch an autonomous THINK→EXECUTE→REFLECT experiment loop on a GPU project
Search papers from top AI/ML conferences
$ npx -y skills add Xiangyue-Zhang/auto-deep-researcher-24x7 --skill conf-search --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/conf-searchContext preview
The summary Claude sees to decide when to auto-load this skill.
Search papers from top AI/ML conferences
name: conf-search description: "Search papers from top AI/ML conferences"
Search for papers from top venues.
Claude Code: /conf-search --venue CVPR2025 --query "gesture generation" Claude Code: /conf-search --venue NeurIPS2025 --query "diffusion models" Codex: $conf-search
CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI, IJCAI, ACL, EMNLP, NAACL, SIGGRAPH, and more.
1. Parse venue and query from user input 2. Search via Semantic Scholar API with venue filter 3. Sort by relevance and citation count 4. Present results with title, authors, abstract snippet, citation count 5. Offer to do deep analysis on any paper of interest
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
Launch an autonomous THINK→EXECUTE→REFLECT experiment loop on a GPU project
Refresh Obsidian dashboard and daily notes from current experiment state
Deep analysis of a single paper with figure extraction from arXiv source