auto-experiment
Launch an autonomous THINK→EXECUTE→REFLECT experiment loop on a GPU project
Daily arXiv paper recommendations with automatic deduplication
Claude Code
$ npx -y skills add Xiangyue-Zhang/auto-deep-researcher-24x7 --skill daily-papers --agent claude-code
Codex
$ npx skills add Xiangyue-Zhang/auto-deep-researcher-24x7 --skill daily-papers -a codex -y
Cursor
$ npx skills add Xiangyue-Zhang/auto-deep-researcher-24x7 --skill daily-papers -a cursor -y
Gemini CLI
$ npx skills add Xiangyue-Zhang/auto-deep-researcher-24x7 --skill daily-papers -a gemini-cli -y
GitHub Copilot
$ npx skills add Xiangyue-Zhang/auto-deep-researcher-24x7 --skill daily-papers -a github-copilot -y
OpenCode
$ npx skills add Xiangyue-Zhang/auto-deep-researcher-24x7 --skill daily-papers -a opencode -y
Windsurf
$ npx skills add Xiangyue-Zhang/auto-deep-researcher-24x7 --skill daily-papers -a windsurf -y
name: daily-papers description: "Daily arXiv paper recommendations with automatic deduplication"
Search arXiv for the latest papers relevant to the user's research interests.
Invoke as `/daily-papers` in Claude Code or `$daily-papers` in Codex.
1. Ask the user for topics if not provided (or use defaults from config) 2. Search arXiv for papers published in the last 1-3 days 3. Check against previously recommended papers (dedup) 4. Rank by relevance to the user's research 5. For top 5: provide detailed analysis (motivation, method, key results, insights) 6. For next 5: provide brief summaries 7. Save recommendations to a dated markdown file
Maintain a list of previously recommended paper IDs. Never recommend the same paper twice.
# Daily Paper Recommendations — YYYY-MM-DD ## Top Picks (Detailed) ### 1. [Paper Title](arxiv_url) **Authors**: ... **Relevance**: Why this matters for your research **Motivation**: What problem they solve **Method**: Key technical approach **Results**: Main findings **Insight**: What you can learn from this ### 2. ... ## Also Worth Reading ### 6. [Paper Title](arxiv_url) — One-line summary ...
🔥 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
Check GPU status, running experiments, and available resources
Refresh Obsidian dashboard and daily notes from current experiment state
Deep analysis of a single paper with figure extraction from arXiv source
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…