auto-experiment
Launch an autonomous THINK→EXECUTE→REFLECT experiment loop on a GPU project
Refresh Obsidian dashboard and daily notes from current experiment state
$ npx -y skills add Xiangyue-Zhang/auto-deep-researcher-24x7 --skill obsidian-sync --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/obsidian-syncContext preview
The summary Claude sees to decide when to auto-load this skill.
Refresh Obsidian dashboard and daily notes from current experiment state
name: obsidian-sync description: "Refresh Obsidian dashboard and daily notes from current experiment state"
Refresh progress notes for a Deep Researcher project.
Claude Code: /obsidian-sync --project /path/to/project Claude Code: /obsidian-sync --project /path/to/project --dashboard-only Claude Code: /obsidian-sync --project /path/to/project --daily-only Codex: $obsidian-sync
1. Read project config and check `obsidian.enabled` 2. Read `PROJECT_BRIEF.md`, `workspace/MEMORY_LOG.md`, `workspace/state.json`, and `.cycle_counter` 3. Refresh `Dashboard.md` in Obsidian, or `workspace/progress_tracking/Dashboard.txt` if no vault is configured 4. Optionally append a new daily note entry
python -m core.obsidian --project /path/to/project
If progress export is disabled, tell the user to set `obsidian.enabled: true`. If `obsidian.vault_path` is empty, notes fall back to project-local text files.
🔥 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
Deep analysis of a single paper with figure extraction from arXiv source