c-obsidian
关于
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.
快速安装
Claude Code
推荐npx skills add daxaur/openpaw -a claude-code/plugin add https://github.com/daxaur/openpawgit clone https://github.com/daxaur/openpaw.git ~/.claude/skills/c-obsidian在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
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 仓库
Frequently asked questions
What is the c-obsidian skill?
c-obsidian is a Claude Skill by daxaur. Skills package instructions and resources that Claude loads on demand, so Claude can perform c-obsidian-related tasks without extra prompting.
How do I install c-obsidian?
Use the install commands on this page: add c-obsidian to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does c-obsidian belong to?
c-obsidian is in the Other category, tagged obsidian, notes, knowledge-base, memory and daily-notes.
Is c-obsidian free to use?
Yes. c-obsidian is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
LlamaGuard是Meta推出的7-8B参数内容审核模型,专门用于过滤LLM的输入和输出内容。它能检测六大安全风险类别(暴力/仇恨、性内容、武器、违禁品、自残、犯罪计划),准确率达94-95%。开发者可通过HuggingFace、vLLM或Sagemaker快速部署,并能与NeMo Guardrails集成实现自动化安全防护。
这个Claude Skill帮助开发者优化云成本,通过资源调整、标记策略和预留实例来降低AWS、Azure和GCP的开支。它适用于减少云支出、分析基础设施成本或实施成本治理策略的场景。关键功能包括提供成本可视化、资源规模调整指导和定价模型优化建议。
该Skill为开发者提供体育博彩数据分析工具,可分析盘口、大小球和特殊投注,识别价值投注机会。它整合历史数据和情景统计,生成包含时间戳的结构化Markdown报告。适用于需要快速获取博彩市场洞察的娱乐或教育类应用开发。
这个Skill使用bitsandbytes库量化大语言模型,能在GPU内存有限时通过8位或4位量化减少50-75%内存占用,同时保持精度损失最小。它支持INT8、NF4、FP4等多种量化格式,可与HuggingFace Transformers无缝集成,适用于需要部署更大模型或加速推理的场景。还提供QLoRA训练和8位优化器支持,让开发者能轻松实现高效模型压缩。
