Skill1.2k estrellas del repoactualizado 10d ago

obsidian-sync

The obsidian-sync skill updates Obsidian vault documentation for Deep Researcher projects by reading project configuration, memory logs, and state files, then refreshing a Dashboard note with current progress. Use it to keep Obsidian synchronized with active experiment states, or enable optional daily note entries, with fallback to local text files if no vault is configured.

Ver fuente Repositorio: auto-deep-researcher-24x7

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/Xiangyue-Zhang/auto-deep-researcher-24x7 /tmp/obsidian-sync && cp -r /tmp/obsidian-sync/skills/obsidian-sync ~/.claude/skills/obsidian-sync

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

# obsidian-sync

Refresh progress notes for a Deep Researcher project.

## Usage

```bash
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
```

## Behavior

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

## Command

```bash
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.

Del mismo repositorio

code_agentSubagent

Experiment implementation, execution, and monitoring

idea_agentSubagent

Literature search and hypothesis formation

leaderSubagent

Central decision-maker that plans experiments and reflects on results

writing_agentSubagent

Report generation and paper writing

auto-experimentSkill

Launch an autonomous THINK→EXECUTE→REFLECT experiment loop on a GPU project

conf-searchSkill