c-obsidian
About
The c-obsidian skill enables developers to use their Obsidian vault as persistent memory within Claude, allowing for knowledge capture, daily notes, and session logging. It provides CLI commands to search, create, and edit notes directly from the development workflow. Use this skill to maintain a searchable second brain across coding sessions and projects.
Quick Install
Claude Code
Recommendednpx skills add daxaur/openpaw -a claude-code/plugin add https://github.com/daxaur/openpawgit clone https://github.com/daxaur/openpaw.git ~/.claude/skills/c-obsidianCopy and paste this command in Claude Code to install this skill
Documentation
Obsidian — Knowledge Base & Memory
Manage your Obsidian vault as a persistent memory layer. Use it for daily notes, session logs, knowledge capture, and searching your second brain.
CLI Commands
# Search before creating (avoid duplicates)
obsidian-cli search "query"
obsidian-cli search --tag "project" --folder "Work"
# Create and edit
obsidian-cli create "Title" --content "Body"
obsidian-cli create "Title" --template "Daily Note"
obsidian-cli append "Note Title" "Additional content"
# Open, list, vault
obsidian-cli open "Note Title"
obsidian-cli list --folder "Projects"
obsidian-cli tags
obsidian-cli vault --list
Daily Notes Integration
When the user starts a session, check for today's daily note:
obsidian-cli search --folder "Daily Notes" "$(date +%Y-%m-%d)"
If none exists, create one:
obsidian-cli create "$(date +%Y-%m-%d)" --folder "Daily Notes" --content "# $(date +%Y-%m-%d)\n\n## Tasks\n\n## Notes\n\n## Session Log\n"
Append a session log entry at the end of each session:
obsidian-cli append "$(date +%Y-%m-%d)" "### Session $(date +%H:%M)\n- [summary of what was done]\n"
Memory Sync (Auto)
If both c-memory and c-obsidian are installed (check ls ~/.claude/skills/c-memory/), keep them in sync automatically:
Bidirectional Sync
~/.claude/memory/→ ObsidianAI/folder (on every memory write)- Obsidian
AI/→~/.claude/memory/(on session start, if Obsidian has newer content)
Sync Commands
# Push memory to Obsidian
obsidian-cli create "AI/Memory" --content "$(cat ~/.claude/memory/MEMORY.md)"
obsidian-cli create "AI/People" --content "$(cat ~/.claude/memory/people.md)"
# Pull from Obsidian to check for updates
obsidian-cli search --folder "AI" "Memory"
# Append session log to daily note
obsidian-cli append "$(date +%Y-%m-%d)" "### Claude Session $(date +%H:%M)\n- [summary]"
Rules
- When the user says "remember this", save to both systems
- Obsidian is the long-term archive;
~/.claude/memory/is the quick-access cache - MEMORY.md is authoritative for quick facts; Obsidian is richer context
Guidelines
- Always search before creating to avoid duplicate notes
- Use frontmatter tags:
tags: [project, active] - File paths are relative to vault root
- Obsidian app does not need to be running
- Keep daily notes in a consistent folder (default:
Daily Notes/)
GitHub Repository
Related Skills
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.
cost-optimization
OtherThis Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.
quantizing-models-bitsandbytes
OtherThis skill quantizes LLMs to 8-bit or 4-bit precision using bitsandbytes, achieving 50-75% memory reduction with minimal accuracy loss. It's ideal for running larger models on limited GPU memory or accelerating inference, supporting formats like INT8, NF4, and FP4. The skill integrates with HuggingFace Transformers and enables QLoRA training and 8-bit optimizers.
dispatching-parallel-agents
OtherThis Claude Skill dispatches multiple agents to investigate and fix 3+ independent problems concurrently. It is designed for scenarios involving unrelated failures that can be resolved without shared state or dependencies. The core capability is parallel problem-solving, assigning one agent per independent problem domain to maximize efficiency.
