Agent skill
obsidian
Manage prompts in your Obsidian vault. Use for saving, listing, and loading reusable prompts. Triggers on /obsidian commands, Obsidian vault operations, or prompt management requests.
Install this agent skill to your Project
npx add-skill https://github.com/leweii/obsidian-prompt-manager/tree/main/skills/obsidian
SKILL.md
Obsidian Prompt Manager
Manage reusable prompts in your Obsidian vault from Claude Code using native tools.
Configuration
Configuration is stored in the skill's config.json:
{
"vaultPath": "/path/to/your/vault",
"promptsFolder": "Claude-Prompts"
}
Config location: ~/.claude/skills/obsidian/config.json (personal) or .claude/skills/obsidian/config.json (project)
Commands
/obsidian setup <vault-path>
Configure your Obsidian vault path.
Steps to execute:
-
Validate path exists:
Use Bash: ls -la <vault-path>If path doesn't exist, inform user and stop.
-
Create prompts folder:
Use Bash: mkdir -p <vault-path>/Claude-Prompts -
Save configuration: Use Write tool to update config.json:
json{ "vaultPath": "<vault-path>", "promptsFolder": "Claude-Prompts" } -
Confirm to user: "Vault configured: Prompts folder: /Claude-Prompts"
/obsidian save "<title>" [--tags tag1,tag2]
Save a prompt to your Obsidian vault.
Steps to execute:
-
Read config: Use Read tool on config.json to get vaultPath. If vaultPath is empty, ask user to run
/obsidian setupfirst. -
Get prompt content: Ask user: "What content should I save for this prompt?"
-
Create markdown file: Use Write tool to create
<vaultPath>/Claude-Prompts/<title>.md:markdown--- title: "<title>" date: <YYYY-MM-DD> tags: - claude-prompt - <additional tags if provided> --- # <title> <prompt content> -
Confirm to user: "Saved: <vaultPath>/Claude-Prompts/.md"
/obsidian list [--search <keyword>]
List all saved prompts from your vault.
Steps to execute:
-
Read config: Use Read tool on config.json to get vaultPath. If vaultPath is empty, ask user to run
/obsidian setupfirst. -
Find prompts: Use Glob tool:
<vaultPath>/Claude-Prompts/**/*.md -
If --search provided: Use Grep tool to filter files containing the keyword.
-
For each file found: Use Read tool to extract:
- Title (from frontmatter or filename)
- Preview (first line of content after frontmatter)
-
Display formatted list:
Found X prompt(s): <Title 1> Path: <relative-path> Preview: <first 60 chars>... <Title 2> ...
/obsidian use "<prompt-name>"
Load and execute a saved prompt.
Steps to execute:
-
Read config: Use Read tool on config.json to get vaultPath. If vaultPath is empty, ask user to run
/obsidian setupfirst. -
Find the prompt: Use Glob tool:
<vaultPath>/Claude-Prompts/**/*.mdMatch filename or title (case-insensitive) to . -
If not found: List available prompts and ask user to choose.
-
Read prompt file: Use Read tool to get file contents.
-
Extract content: Remove YAML frontmatter (everything between
---markers). Remove the title header line (starts with#). -
Execute the prompt: Treat the extracted content as if the user typed it. Respond to it as a new instruction.
Examples
Setup Example
User: /obsidian setup ~/Documents/MyVault
Claude: Let me configure your Obsidian vault...
[Uses Bash to verify path exists]
[Uses Bash to create Claude-Prompts folder]
[Uses Write to save config.json]
Vault configured: /Users/you/Documents/MyVault
Prompts folder: /Users/you/Documents/MyVault/Claude-Prompts
Save Example
User: /obsidian save "Code Review Checklist" --tags review,quality
Claude: What content should I save for this prompt?
User: Review this code for: 1) bugs 2) performance 3) security
Claude: [Uses Write to create the markdown file]
Saved: /Users/you/Documents/MyVault/Claude-Prompts/Code Review Checklist.md
List Example
User: /obsidian list
Claude: [Uses Glob to find .md files]
[Uses Read to extract titles and previews]
Found 3 prompt(s):
Code Review Checklist
Path: Code Review Checklist.md
Preview: Review this code for: 1) bugs 2) performance...
Debug Helper
Path: Debug Helper.md
Preview: Help me debug this issue by...
Use Example
User: /obsidian use "Code Review Checklist"
Claude: [Uses Glob to find the file]
[Uses Read to get contents]
[Extracts content, removing frontmatter]
Now executing prompt: "Review this code for: 1) bugs 2) performance 3) security"
[Claude then responds as if user typed that prompt]
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Didn't find tool you were looking for?