skills/make-note/SKILL.md
Create well-structured notes in Obsidian with intelligent tag suggestions. Use when the user asks to create a note, make a note, or save content to Obsidian. Scans existing vault for common tags and presents suggestions before creating the note in the Resources folder.
npx skillsauth add glnds/claude-config make-noteInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create or edit notes in Obsidian's Resources folder with intelligent tag management based on existing vault patterns.
Before creating any note, scan the vault to understand existing tag patterns:
mcp-obsidian and invoke the tool obsidian_get_tags
to get a list of all available tagsThe MCP tool obsidian_get_tags returns a JSON with tag frequencies. Focus on tags that appear
more than 3 times to identify genuine patterns rather than one-off tags.
This is an example of the JSON return:
{
"tags": {
"#tag1": 24,
"#tag2/subtagx": 37,
"#tag3": 104,
"#tag4": 62
}
}
Based on the note content and existing tag patterns:
Tag suggestion format:
ai/code-agent, dpg/strategy)Present suggested tags to the user for confirmation:
"I suggest these tags for your note:
Would you like to use these tags, modify them, or add additional tags?"
Wait for user confirmation before proceeding.
Once tags are confirmed:
mcp-obsidian tool
obsidian_append_contenttags: field formatted as listcreated: field with current date in format DD-MM-YYYY HH:MM# [[Title]]## References section with relevant external links (if any)## Related Notes section with wiki-links to other notes in the vault (if any). DO NOT add dead links!MANDATORY Frontmatter format:
---
tags:
- tag1
- tag2
- tag3
created: DD-MM-YYYY HH:MM
---
Bottom sections format:
## References
- [Link title](URL)
- [Another link](URL)
## Related Notes
- [[Related Note 1]]
- [[Related Note 2]]
Only include these sections if there are relevant links or related notes to add. If no references or related notes exist, omit those sections entirely.
After creating the note, inform the user:
Follow these conventions observed in the vault:
cloud/aws, ai/agentic,
music/modular)platform-engineering,
code-agent)Based on vault analysis, common tag patterns include:
Work/DPG Related:
secdevops, dpg/strategy, dpg/development-enablement, platform-engineeringTechnical:
cloud/aws, ai/code-agent, ai/agentic, coding/sddPersonal/Hobbies:
music/modular, learning, productivityContext Tags:
ai/code-agent vs just ai)testing
Prompt engineering technique to overcome mode collapse in LLM responses by generating multiple answers with probabilities. Use when you want to see alternative responses beyond the top-ranked answer, explore the full distribution of possible responses, discover unexpected solutions, or understand the probability range of different answers. Particularly useful for creative tasks, complex decision-making, brainstorming, and situations where conventional top-ranked answers may be limiting.
content-media
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
content-media
QQBot 富媒体收发能力。使用 <qqmedia> 标签,系统根据文件扩展名自动识别类型(图片/语音/视频/文件)。
content-media
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).