#5555th of 455 in Skills, plugins and prompts
obsidian-skills
Agent Skills that teach coding agents Obsidian file formats and CLIs
- Stars
- 51.7k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Shell
Missed the latest GitHub check; these facts may be older.
Overview
Seven Agent Skills for working with Obsidian vaults: Obsidian Flavored Markdown, Bases (.base), JSON Canvas (.canvas), the Obsidian CLI, Obsidian Headless, Defuddle web extraction and Knap templating. They follow the Agent Skills specification and install through the Claude Code and Codex marketplaces, Cursor, npx skills, or by copying the skills directory.
Who it is for: Obsidian users who work in their vault with Claude Code, Codex or OpenCode
Strengths
- Covers Markdown, Bases, Canvas, CLI, Headless, Defuddle and Knap in one repo
- Follows the Agent Skills spec, so it works with Claude Code, Codex and OpenCode
- Several install paths: Claude Code and Codex marketplaces, Cursor, npx skills, manual copy
- Published under the obsidianmd organization with an MIT license
Weaknesses
- Useful only if you work with Obsidian vaults
- CLI, Headless, Defuddle and Knap skills depend on those separate tools
- OpenCode install needs the full repo cloned, not only the skills folder
- README shows no example outputs or evaluation of skill quality
What it needs
- no GPU
- Needs Obsidian, Obsidian CLI, Obsidian Headless, Defuddle, Knap
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |