progress-report
The progress-report skill generates structured research progress reports by extracting milestones and decisions from a project's MEMORY_LOG.md file and recent experiment logs, then compiling them into a standardized markdown report. Use this skill to regularly summarize research project status, including best results, experiment history, key insights, planned next steps, and identified blockers.
git clone --depth 1 https://github.com/Xiangyue-Zhang/auto-deep-researcher-24x7 /tmp/progress-report && cp -r /tmp/progress-report/skills/progress-report ~/.claude/skills/progress-reportSKILL.md
# progress-report Generate a structured progress report for the current research project. Invoke as `/progress-report` in Claude Code or `$progress-report` in Codex. ## Behavior 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 ## Output Format ```markdown # 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 ```
Experiment implementation, execution, and monitoring
Literature search and hypothesis formation
Central decision-maker that plans experiments and reflects on results
Report generation and paper writing
Launch an autonomous THINK→EXECUTE→REFLECT experiment loop on a GPU project
Search papers from top AI/ML conferences
Daily arXiv paper recommendations with automatic deduplication
Check status of running autonomous experiment loops