Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Manage Obsidian Vaults Via Couchdb Livesync

ASecurity

Manage Obsidian vaults via LiveSync CouchDB — capture notes, AI-enrich and file them, manage tasks, audit and tidy vault structure. Use when working with Obsidian vaults through CouchDB/LiveSync (not local filesystem). Requires CouchDB with Obsidian LiveSync plugin. AI features…

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsrustgobashnodegitapidatabasesecurity

Works with

cliapi

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill manage-obsidian-vaults-via-couchdb-livesync --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Manage Obsidian Vaults Via Couchdb Livesync?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Manage Obsidian Vaults Via Couchdb Livesync
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-manage-obsidian-vaults-via-couchdb-livesync/badge)](https://www.skillsdirectory.com/skills/rondoflow-manage-obsidian-vaults-via-couchdb-livesync)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: manage-obsidian-vaults-via-couchdb-livesync
description: "Manage Obsidian vaults via LiveSync CouchDB — capture notes, AI-enrich and file them, manage tasks, audit and tidy vault structure. Use when working with Obsidian vaults through CouchDB/LiveSync (not local filesystem). Requires CouchDB with Obsidian LiveSync plugin. AI features…"
category: "Productivity"
author: community
version: "0.1.1"
icon: check-square
---

# obsidian-curator

Manage Obsidian vaults through the CouchDB database that powers [Obsidian LiveSync](https://github.com/vrtmrz/obsidian-livesync). Capture, process, file, audit, tidy, and manage tasks — all via CLI or Node.js API.

**Prerequisites:** CouchDB with LiveSync configured, E2EE disabled.

## Security & Trust

- **Open source:** [github.com/philmossman/obsidian-curator](https://github.com/philmossman/obsidian-curator) (MIT)
- **npm provenance:** Published via GitHub Actions OIDC with [Sigstore attestation](https://www.npmjs.com/package/obsidian-curator) — cryptographically verifiable build provenance
- **No lifecycle scripts:** No `preinstall`, `install`, or `postinstall` scripts — `npm install` only copies files
- **Minimal dependencies:** Only `nano` (CouchDB client) and `date-fns` (date parsing)
- **Local network only:** Connects to your CouchDB instance (user-configured host/port). No external telemetry, no phone-home, no data leaves your network
- **Credentials:** Stored locally in `~/.obsidian-curator/config.json` — never transmitted except to your own CouchDB
- **E2EE note:** LiveSync E2EE must be disabled because the tool reads/writes vault documents directly via CouchDB. This is a LiveSync architectural requirement, not a security compromise by this tool

## Setup

Run the interactive wizard — it tests the CouchDB connection live:

```bash
obsidian-curator init
```

Configures: CouchDB connection, vault structure preset (PARA/Zettelkasten/Johnny Decimal/Flat/Custom), AI provider (OpenAI/Anthropic/Ollama/None), task projects.

Config location: `~/.obsidian-curator/config.json`

## Commands

### Capture (no AI needed)

```bash
obsidian-curator capture "Quick thought about project X"
obsidian-curator capture "Meeting notes from standup" --source meeting
```

### Process inbox (AI required)

Enrich inbox notes with tags, summary, and suggested folder:

```bash
obsidian-curator process
obsidian-curator process --limit 5 --dry-run
obsidian-curator process --force   # re-process already-processed notes
```

### File notes (AI required)

Route processed notes to canonical vault folders:

```bash
obsidian-curator file
obsidian-curator file --dry-run --min-confidence 0.8
```

### Audit (no AI needed)

Check vault structure against configured canonical folders:

```bash
obsidian-curator audit
```

### Tidy (AI optional)

Find duplicates, structure violations, dead notes. With AI, ambiguous cases are triaged automatically:

```bash
obsidian-curator tidy --dry-run
obsidian-curator tidy --checks dupes,stubs
```

### Tasks (no AI needed)

```bash
obsidian-curator tasks                          # list open tasks
obsidian-curator tasks --project Work --priority high
obsidian-curator task "call dentist next Tuesday"   # create task (parses dates, priority, project)
obsidian-curator done "dentist"                     # mark done by partial title match
```

### Config

```bash
obsidian-curator config show
obsidian-curator config set ai.provider ollama
obsidian-curator config set vault.host 192.168.1.100
```

## Programmatic API

```js
const { VaultClient, Curator, createAIAdapter, loadConfig } = require('obsidian-curator');

const config = loadConfig();
const vault = new VaultClient(config.vault);
await vault.ping();
const ai = createAIAdapter(config);
const curator = new Curator({ vault, ai, config });

await curator.capture('Quick thought');
await curator.process({ limit: 5 });
await curator.file({ dryRun: true });
await curator.audit();
await curator.tidy({ checks: ['dupes', 'stubs'], dryRun: true });

const tasks = await curator.tasks({ status: 'open', project: 'Work' });
await curator.createTask('call Alice next Friday');
await curator.taskBrief();  // markdown summary
```

## AI Providers

| Provider | Cost | Privacy | Setup |
|----------|------|---------|-------|
| `none` | Free | Local | Default — rule-based features only |
| `ollama` | Free | Local | `config set ai.provider ollama` + model name |
| `openai` | Pay-per-use | Cloud | `config set ai.provider openai` + API key |
| `anthropic` | Pay-per-use | Cloud | `config set ai.provider anthropic` + API key |
| Custom/OpenRouter | Varies | Varies | Use `openai` provider with custom `baseUrl` |

## Vault Structure Presets

- **PARA:** inbox → Projects / Areas / Resources / Archives
- **Zettelkasten:** inbox → Slipbox / References / Projects / Archives
- **Johnny Decimal:** inbox → numbered category folders (00-09, 10-19, ...)
- **Flat:** inbox only, no enforced structure
- **Custom:** define your own canonical folders

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →