auto-experiment
Launch an autonomous THINK→EXECUTE→REFLECT experiment loop on a GPU project
Generate structured research progress reports
$ npx -y skills add Xiangyue-Zhang/auto-deep-researcher-24x7 --skill progress-report --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/progress-reportContext preview
The summary Claude sees to decide when to auto-load this skill.
Generate structured research progress reports
name: progress-report description: "Generate structured research progress reports"
Generate a structured progress report for the current research project.
Invoke as `/progress-report` in Claude Code or `$progress-report` in Codex.
1. Read the project's MEMORY_LOG.md for milestones and decisions 2. Check recent experiment logs in workspace 3. Compile results into a structured report
# Progress Report — YYYY-MM-DD ## Current Status - Best result: [metric] - Total experiments: [N] - Current direction: [description] ## Recent Experiments | # | Config | Metric | Date | Notes | |---|--------|--------|------|-------| ## Key Insights - What we learned - What works / doesn't work ## Next Steps 1. Planned experiments 2. Open questions ## Blockers - Any issues or risks
🔥 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