HKUDS/CLI-Anything/skills/cli-anything-obsidian/SKILL.md
cli-anything-obsidian
Command-line interface for Obsidian — Knowledge management and note-taking via Obsidian Local REST API. Designed for AI agents and power users who need to manage notes, search the vault, and execute commands without the GUI.
- Source repository stars
- 46,599
- Declared platforms
- 0
- Static risk flags
- 1
- Last source update
- 2026-08-03
- Source checked
- 2026-08-04
Decision brief
What it does—and where it fits
Knowledge management and note-taking via the Obsidian Local REST API. Designed for AI agents and power users who need to manage notes, search the vault, and execute commands without the GUI.
Not for
- Tasks that require unconfirmed production actions or broad system permissions.
- Environments where the pinned source and install steps cannot be inspected.
Compatibility matrix
Platform support, with evidence labels
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
Inspect first. Install second.
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/HKUDS/CLI-Anything --skill "skills/cli-anything-obsidian"Inspect the Agent Skill "cli-anything-obsidian" from https://github.com/HKUDS/CLI-Anything/blob/39634a640cf20bc603b4faae4d31069c44821a9a/skills/cli-anything-obsidian/SKILL.md at commit 39634a640cf20bc603b4faae4d31069c44821a9a. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
What the source asks the agent to do
- 01
Usage
Review the “Usage” section in the pinned source before continuing.
Review and apply the “Usage” source section. - 02
Installation
This CLI is installed as part of the cli-anything-obsidian package:
Python 3.10+Obsidian must be installed and running with the Local REST API plugin enabledThis CLI is installed as part of the cli-anything-obsidian package: - 03
Basic Commands
Review the “Basic Commands” section in the pinned source before continuing.
Review and apply the “Basic Commands” source section. - 04
Show help
cli-anything-obsidian --help
cli-anything-obsidian --help - 05
Start interactive REPL mode
Review the “Start interactive REPL mode” section in the pinned source before continuing.
Review and apply the “Start interactive REPL mode” source section.
Permission review
Static risk signals and limitations
Runs scripts
The documentation asks the agent to run terminal commands or scripts.
| `execute` | Execute a command by its ID |Runs scripts
The documentation asks the agent to run terminal commands or scripts.
# Execute a command by IDEvidence record
Why each signal appears
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 89/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 46,599 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- HKUDS/CLI-Anything
- Skill path
- skills/cli-anything-obsidian/SKILL.md
- Commit
- 39634a640cf20bc603b4faae4d31069c44821a9a
- License
- Apache-2.0
- Collected
- 2026-08-04
- Default branch
- main
View the original SKILL.md
cli-anything-obsidian
Knowledge management and note-taking via the Obsidian Local REST API. Designed for AI agents and power users who need to manage notes, search the vault, and execute commands without the GUI.
Installation
This CLI is installed as part of the cli-anything-obsidian package:
pip install cli-anything-obsidian
Prerequisites:
- Python 3.10+
- Obsidian must be installed and running with the Local REST API plugin enabled
Usage
Basic Commands
# Show help
cli-anything-obsidian --help
# Start interactive REPL mode
cli-anything-obsidian
# List vault files
cli-anything-obsidian vault list
# Run with JSON output (for agent consumption)
cli-anything-obsidian --json vault list
REPL Mode
When invoked without a subcommand, the CLI enters an interactive REPL session:
cli-anything-obsidian
# Enter commands interactively with tab-completion and history
Command Groups
Vault
Vault file management commands.
| Command | Description |
|---|---|
list | List files in the vault or a subdirectory |
read | Read the content of a note |
create | Create a new note |
update | Overwrite an existing note |
delete | Delete a note from the vault |
append | Append content to an existing note |
Search
Vault search commands.
| Command | Description |
|---|---|
query | Search using Obsidian query syntax |
simple | Plain text search across the vault |
Note
Active note commands.
| Command | Description |
|---|---|
active | Get the currently active note in Obsidian |
open | Open a note in the Obsidian editor |
Command
Obsidian command palette commands.
| Command | Description |
|---|---|
list | List all available Obsidian commands |
execute | Execute a command by its ID |
Server
Server status and info commands.
| Command | Description |
|---|---|
status | Check if the Obsidian Local REST API is running |
Session
Session state commands.
| Command | Description |
|---|---|
status | Show current session state |
Examples
List and Read Notes
# List all vault files
cli-anything-obsidian vault list
# List files in a subdirectory
cli-anything-obsidian vault list "Daily Notes"
# Read a note
cli-anything-obsidian vault read "Projects/my-project.md"
Create and Update Notes
# Create a new note
cli-anything-obsidian vault create "Projects/new-project.md" --content "# New Project"
# Update (overwrite) a note
cli-anything-obsidian vault update "Projects/new-project.md" --content "# Updated Content"
# Append to a note
cli-anything-obsidian vault append "Projects/new-project.md" --content "\n## New Section"
Search
# Plain text search (GET /search/simple/)
cli-anything-obsidian search simple "meeting notes"
# Dataview DQL query — default --type dql, sent as
# application/vnd.olrapi.dataview.dql+txt
cli-anything-obsidian search query 'TABLE file.link FROM "Projects"'
# JsonLogic query — application/vnd.olrapi.jsonlogic+json
cli-anything-obsidian search query --type jsonlogic \
'{"==":[{"var":"frontmatter.status"},"active"]}'
Commands
# List available commands
cli-anything-obsidian command list
# Execute a command by ID
cli-anything-obsidian command execute "editor:toggle-bold"
Interactive REPL Session
Start an interactive session for exploratory use.
cli-anything-obsidian
# Enter commands interactively
# Use 'help' to see available commands
API Key Configuration
# Via flag
cli-anything-obsidian --api-key YOUR_KEY vault list
# Via environment variable (recommended for agents)
export OBSIDIAN_API_KEY=YOUR_KEY
cli-anything-obsidian vault list
State Management
The CLI maintains lightweight session state:
- API key: Configurable via
--api-keyorOBSIDIAN_API_KEYenvironment variable - Host URL: Defaults to
https://localhost:27124; configurable via--host
Output Formats
All commands support dual output modes:
- Human-readable (default): Tables, colors, formatted text
- Machine-readable (
--jsonflag): Structured JSON for agent consumption
# Human output
cli-anything-obsidian vault list
# JSON output for agents
cli-anything-obsidian --json vault list
For AI Agents
When using this CLI programmatically:
- Always use
--jsonflag for parseable output - Check return codes - 0 for success, non-zero for errors
- Parse stderr for error messages on failure
- Set
OBSIDIAN_API_KEYenvironment variable to avoid passing--api-keyon every call - Verify Obsidian is running with
server statusbefore other commands
More Information
- Full documentation: See README.md in the package
- Test coverage: See TEST.md in the package
- Methodology: See HARNESS.md in the cli-anything-plugin
Version
1.1.0
Alternatives
Compare before choosing
coreyhaines31/marketingskills
ab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
alirezarezvani/claude-skills
app-store-optimization
App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklist
dotnet/skills
migrate-vstest-to-mtp
Migrates .NET test projects from VSTest to Microsoft.Testing.Platform (MTP). Use when user asks to "migrate to MTP", "switch from VSTest", "enable Microsoft.Testing.Platform", "use MTP runner", set OutputType=Exe only for test projects in Directory.Build.props, or mentions EnableMSTestRunner, EnableNUnitRunner, or UseMicrosoftTestingPlatformRunner. USE FOR: MTP behavioral differences vs VSTest (exit code 8, zero tests discovered, --ignore-exit-code, TESTINGPLATFORM_EXITCODE_IGNORE); centralizing
JasonColapietro/suede-creator-skills
suede-ab-testing
Suede-owned experimentation discipline for hypotheses, sample sizing, test duration, significance, and repeatable experiment programs. Use when comparing variants, deciding whether a result is reliable, or building an experiment backlog and cadence. NOT FOR: analytics instrumentation (use suede-analytics), post-click conversion diagnosis (use suede-site-alchemy), or writing the variant copy itself (use suede-copy).