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

Save Markdown To Obsidian Via Ssh

DSecurity

Saves markdown content to remote Obsidian vault via SSH

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

Works with

api

Security Analysis

D50/100
criticalAccesses sensitive system or user directories
criticalReads or references SSH private keys

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill save-markdown-to-obsidian-via-ssh --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Save Markdown To Obsidian Via Ssh?

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

Security grade badge for Save Markdown To Obsidian Via Ssh
[![Security: D — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-save-markdown-to-obsidian-via-ssh/badge)](https://www.skillsdirectory.com/skills/rondoflow-save-markdown-to-obsidian-via-ssh)

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

Download with Pro
Files
SKILL.md
---
name: save-markdown-to-obsidian-via-ssh
description: "Saves markdown content to remote Obsidian vault via SSH"
category: "Productivity"
author: community
version: "1.0.0"
icon: check-square
---

# Save to Obsidian

Saves markdown content to remote Obsidian vault via SSH.

## Prerequisite

**This skill is for machines WITHOUT iCloud sync** (e.g., Linux/Ubuntu servers). If your machine already has iCloud Desktop sync enabled and direct access to the Obsidian vault, you don't need this skill — just copy files directly to the vault path.

## When to Use

User says: "save to obsidian", "send to obsidian", "copy to obsidian"

## Process

1. Write content to a temp .md file (enforce formatting rules below)
2. Copy to remote vault: `scp <filepath> user@remote-host:/path/to/obsidian/vault/`
3. Confirm success to user

**Example:**
```bash
# Write content to temp file
cat > /tmp/my-note.md << 'EOF'
# My Note
Content here
EOF

# Copy to remote Obsidian vault
scp /tmp/my-note.md myuser@vault.example.com:~/Obsidian/MyVault/

# Clean up
rm /tmp/my-note.md
```

**Configuration:** The agent should use the SSH host and vault path configured in workspace TOOLS.md

## Formatting Rules

All content saved to Obsidian MUST follow these rules:

### Diagrams: Use Mermaid (mandatory)
- **Never** use ASCII box diagrams, ASCII art, or plaintext diagrams
- **Always** use Mermaid fenced code blocks (` ```mermaid `)
- Obsidian renders Mermaid natively — ASCII diagrams look broken
- Supported types: flowchart, sequence, state, class, ER, gantt, pie, mindmap, timeline, quadrant, graph

### Tables: Use Markdown tables
- Obsidian renders markdown tables natively
- For complex data, prefer tables over bullet lists

### Links: Use wiki-links or relative links
- Link between Obsidian notes: `[[note-name]]`
- External links: standard markdown `[text](url)`

### General
- Use headers (##) for structure — Obsidian outline panel relies on them
- Use YAML frontmatter if metadata is needed
- Keep filenames kebab-case (no spaces) for cross-platform compatibility

## Agent Owner
This skill is executed by the main OpenClaw agent session. The `save-to-obsidian.sh` script
runs as a shell command via the exec tool. No sub-agents are spawned. iCloud sync is handled
automatically after file transfer — no agent action needed.

## Success Criteria
Save succeeds when:
1. scp exits with code 0
2. File appears in vault directory with correct filename
3. iCloud sync propagates the file (typically 1-2 minutes; not verified by skill)

Failure conditions: SSH unreachable, vault path does not exist, disk full, filename
contains characters invalid for iCloud sync (handled by sanitization in script).

## Edge Cases
- **SSH failure**: script exits with error message and non-zero code; agent should report and stop
- **Duplicate filename**: overwrites silently — scp does not warn; user must check if overwrite is desired
- **Special characters in filename**: sanitized by script (spaces → hyphens, invalid chars stripped)
- **Empty content**: scp will transfer a 0-byte file; not an error but should be flagged
- **No clear title**: if content has no H1 header, agent should prompt user for filename before saving
- **iCloud sync delay**: file appears in vault within 1-2 min; if not visible after 5 min, check iCloud status

## Notes

- Uses existing SSH key auth (no password)
- Target: remote-host → Obsidian vault location
- Files sync via iCloud automatically (if vault is in iCloud folder)

## Configuration

This skill reads SSH and vault configuration from your workspace TOOLS.md:

| Variable | Description | Where to set |
|----------|-------------|--------------|
| SSH host | Hostname/IP of the remote machine hosting the Obsidian vault | TOOLS.md (e.g., `myserver.local`) |
| SSH user | Username on the remote machine | TOOLS.md (e.g., `your-username`) |
| SSH key path | Path to SSH private key (default: `~/.ssh/id_rsa`) | TOOLS.md |
| Vault path | Absolute path to Obsidian vault on remote machine | TOOLS.md (e.g., `~/Obsidian/MyVault/`) |

**Example TOOLS.md entry:**
```
## Obsidian Remote Vault
- SSH host: myserver.local
- SSH user: your-username
- Vault path: ~/Obsidian/MyVault/
```

No API keys or tokens required — uses SSH key authentication only.

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 →