What does this skill do, and when should you use it?
This skill is focused on Obsidian Flavored Markdown files (`.md`). It guides agents in using properties, wikilinks, embeds, callouts, tags, comments, highlights, math, Mermaid diagrams, and footnotes. It is a good fit for users who want an agent to maintain an Obsidian vault directly. Standard Markdown is assumed knowledge, and the skill does not cover Obsidian Bases, JSON Canvas, or the Obsidian CLI.
Creates and edits .md notes; adds YAML properties at the top of a file; connects vault notes with [[Note]] wikilinks; embeds notes, images, or PDF pages with ![[...]]; adds callouts, tags, comments, highlights, LaTeX, Mermaid diagrams, and footnotes; and instructs the agent to check rendering in Obsidian’s reading view.
- An Obsidian user creates a new note with title, tags, aliases, and date properties.
- A knowledge-base maintainer connects related notes through tracked internal wikilinks.
- A researcher embeds images, PDF pages, or sections from other notes.
- A project team highlights risks, reminders, questions, or decisions with callouts.
- A documentation author adds equations, Mermaid diagrams, and footnotes to Obsidian notes.
How do you install this skill?
- The instruction to verify Reading View rendering cannot be established from these files alone; users must check against their target Obsidian version.
- External image and link examples may introduce network, privacy, or availability risks, but the skill provides no confirmation, source-review, or recovery procedure.
- Supported Obsidian versions and an explicit maintenance or update commitment are not stated.
- Local filesystem
This skill is part of the kepano/obsidian-skills multi-skill repository, and the source provides repository-level installation methods. Marketplace: run /plugin marketplace add kepano/obsidian-skills, then /plugin install obsidian@obsidian-skills. npx skills: run npx skills add https://github.com/kepano/obsidian-skills. Claude Code: place the repository contents in /.claude at the root of the Obsidian vault. Codex: copy the skills/ directory to the usual ~/.codex/skills skills path. OpenCode: run git clone https://github.com/kepano/obsidian-skills.git ~/.opencode/skills/obsidian-skills, then restart OpenCode.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/kepano/obsidian-skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/obsidian-markdown" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Use it in an Agent Skills-compatible client while working on Obsidian .md files, or mention wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes. Example: Create an Obsidian note with frontmatter, wikilinks, a callout, and an embedded image. The source does not document additional client-specific trigger behavior beyond the installation instructions.
What are this skill's strengths and limitations?
- Covers common Obsidian Markdown features for links, embeds, properties, and visual annotations.
- Provides a step-by-step note-creation workflow with usable syntax examples.
- Uses standard SKILL.md frontmatter containing only `name` and `description`.
- The repository is licensed under MIT.
- Covers Obsidian Markdown extensions only; standard Markdown is assumed knowledge.
- Does not provide Obsidian Bases, JSON Canvas, Obsidian CLI, or web-content extraction capabilities.
- The source provides no automated test suite, platform matrix, or failure-recovery procedure.
- Rendering verification is listed as a workflow step, but no automated validation method is described.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Obsidian Markdown Editor this page | 57 · Use with care | ★ 50k | 1mo ago | MIT |
| Obsidian Wiki Health Check | 48 · Use with care | ★ 16k | 1mo ago | MIT |
| Obsidian Markdown Syntax Assistant | 45 · Not recommended | ★ 16k | 1mo ago | MIT |
| Obsidian Vault Organizer | 49 · Use with care | ★ 10k | 14d ago | MIT |
| Compound Vault Methodology Modes | 56 · Use with care | ★ 16k | 1mo ago | MIT |
How did FollowSkills review this skill?
The skill only instructs Markdown editing, linking, embedding, and properties; there is no evidence of malware, credential theft, exfiltration, or disproportionate permissions. It lacks user-confirmation guidance, sensitive-data handling, rollback, and data-flow disclosure, so points are deducted.
The workflow and examples are largely self-consistent, with dedicated references for properties, embeds, and callouts. However, there are no tests, compatibility matrix, abnormal-input handling, or diagnosable failure messages; static review therefore keeps the score below 10.
The name, description, and intended Obsidian Markdown scenarios are clear, and standard Markdown is identified as a prerequisite. Non-fit boundaries, precise trigger conditions, Chinese-language guidance, and environment-compatibility evidence are limited, so points are deducted.
The documentation uses progressive disclosure through a workflow and topic references, and includes installation guidance, examples, official references, and an MIT license. It lacks versioning, changelog, maintenance ownership, update path, and troubleshooting guidance.
Reusable examples cover core wikilinks, embeds, callouts, properties, tags, math, and Mermaid tasks, making the skill plausibly useful. There is no execution or representative-output verification, so the static-review cap limits this to 7.
Concrete syntax, complete examples, and links to official Obsidian documentation provide limited auditability. There are no committed tests, CI coverage, or independent reproduction evidence, so the static score is capped at 5.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →