obsidian-cli

An agent skill by kepano, from kepano/obsidian-skills. Tags: automation, debugging, developer-tools, devops, documents.

What it does

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add kepano/obsidian-skills --skill obsidian-cli

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/kepano/obsidian-skills
cp -r obsidian-skills/skills/obsidian-cli ~/.claude/skills/obsidian-cli

Safety box score

Grade C, moderate risk: 32 of 100 risk points, rated 2026-09-22. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill controls a running Obsidian instance to read, create, search, and edit vault content, and it also includes developer commands that can run JavaScript inside the app. The main risks are access to whatever is in the vault (including sensitive notes) and arbitrary code execution through the `eval` command.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	3 (high)	The skill explicitly exposes `obsidian eval code="..."`, which runs JavaScript in the Obsidian app context.
Network access	0 (none)	The files do not define any commands that send data to remote hosts or download code; the only external reference is documentation (`https://help.obsidian.md/cli`).
Filesystem reach	2 (moderate)	It can read and modify vault files with commands like `read`, `create`, `append`, and `property:set`, targeting notes by `file=` or `path=`.
Secrets & credentials	2 (moderate)	Because it can read/search/backlink notes inside the user’s vault, it may expose private content already stored there.
Privilege & persistence	0 (none)	There is no sudo, service install, shell startup editing, or OS-level configuration in the skill text.
Instruction hijack surface	0 (none)	The skill does not instruct the agent to ignore higher-priority instructions, follow hidden content, or skip confirmations.
Irreversible actions	1 (low)	It can directly change notes and reload plugins, but it does not publish, send messages, pay, or deploy outside the local vault/app.
Transparency	0 (none)	The shipped file is plain text markdown; no binaries, bundled installers, or decoded runtime code are present.

Before installing

Read `SKILL.md` and be comfortable with `obsidian eval` running code in your Obsidian session.
Test it in a scratch vault or non-sensitive profile first.
Assume any note the CLI can see may be read by the agent; keep secrets out of that vault.
Do not use the developer commands unless you trust the plugin/theme code being debugged.

Rated 2026-09-22 by an automated review of 1 file from the skill's repository.

Source

Repository: kepano/obsidian-skills (all skills from this repository)
Path: skills/obsidian-cli/SKILL.md
Branch: main
Updated: 2026-09-19

harness-engineering — This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs.
hyperframes-cli — Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes.
agents-deploy — Use when deploying your agent to AWS, or when a deploy has failed.
code-improver — Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names.
devcontainer-setup — Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes.
pr-improver — Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean.