Skip to main content
hc
Submit
skillsSource-backedReview first Safety ✓ Privacy ✓

Obsidian Agent Skills

Agent Skills for Obsidian by Steph Ango, teaching Claude Code, Codex, OpenCode, and skills-compatible agents to work with Obsidian Flavored Markdown, Bases, JSON Canvas, Obsidian CLI, vaults, plugins, themes, and Defuddle-powered web-to-markdown extraction.

by Steph Ango·added 2026-06-18·
Claude CodeCodexWindsurfGeminiCursorCLI
HarnessClaude CodeCodexWindsurfGeminiCursorCLI
Level:expertType:capability-packVerified:validated
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • Obsidian vaults often contain personal notes, private research, customer context, credentials in notes, meeting records, and unpublished plans; scope agent access carefully.
  • The Obsidian CLI skill can guide vault operations, plugin work, and theme development, so review commands before running them against a real vault.
  • JSON Canvas and Bases edits can alter knowledge organization, saved views, formulas, and linked note structures; review generated files before syncing or publishing.
  • Defuddle-powered extraction can bring third-party web content into a vault; check source attribution, copyright, and cleanup before sharing extracted notes.

Privacy notes

  • Using the skills can expose note contents, backlinks, properties, canvases, Base queries, plugin code, theme files, vault paths, web extracts, and personal knowledge workflows to the configured model provider.
  • Do not share private journals, client notes, regulated data, secret recovery phrases, API keys, unreleased plans, or internal knowledge bases unless the agent environment is approved for that data.
  • When committing or publishing generated vault files, review embedded links, frontmatter properties, canvas text, extracted quotes, and metadata for private information.

Prerequisites

  • An Obsidian vault or project folder where an agent is allowed to read and write Markdown, Base, Canvas, plugin, or theme files.
  • Claude Code plugin support, `npx skills`, Codex skills path access, OpenCode skills directory access, or another Agent Skills compatible host.
  • Obsidian CLI only for workflows that explicitly need vault interaction, plugin development, or theme development through the CLI.
  • A backup, git history, or review workflow before allowing an agent to edit important vault notes or canvases.

Schema details

Install type
package
Reading time
6 min
Difficulty score
68
Troubleshooting
Yes
Breaking changes
No
Source repository stats
Scope
Source repo
Package metadata
Skill and platform metadata
Skill type
capability-pack
Skill level
expert
Verification
validated
Verified at
2026-06-18
Retrieval sources
https://github.com/kepano/obsidian-skillshttps://raw.githubusercontent.com/kepano/obsidian-skills/main/README.mdhttps://raw.githubusercontent.com/kepano/obsidian-skills/main/.claude-plugin/marketplace.jsonhttps://raw.githubusercontent.com/kepano/obsidian-skills/main/LICENSE
Tested platforms
Claude CodeCodexOpenCodeAgent Skills compatible hosts
PlatformSupportInstall path
claude-codeNative.claude/skills/<skill-name>/SKILL.md
codexNative.agents/skills/<skill-name>/SKILL.md
windsurfNative.windsurf/skills/<skill-name>/SKILL.md
geminiNative.gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md
cursorAdapter.cursor/rules/<skill-name>.mdc
cliManualAGENTS.md or tool-specific context file
Tool listing metadata
Full copyable content
/plugin marketplace add kepano/obsidian-skills
/plugin install obsidian@obsidian-skills

# npx skills with HTTPS
npx skills add https://github.com/kepano/obsidian-skills

About this resource

Obsidian Agent Skills

kepano/obsidian-skills is an Agent Skills repository for Obsidian workflows. It teaches skills-compatible agents how to work with Obsidian Flavored Markdown, Obsidian Bases, JSON Canvas, Obsidian CLI, and clean web-to-markdown extraction through Defuddle.

Use this listing when the agent task touches Obsidian vault structure, note syntax, Bases, Canvas files, plugin/theme development, or Obsidian-specific Markdown conventions.

Knowledge Freshness

Obsidian Flavored Markdown, Bases syntax, JSON Canvas conventions, Obsidian CLI commands, plugin APIs, theme workflows, and Defuddle behavior can change. Use the skills as workflow guidance, then verify exact syntax and command behavior against current Obsidian docs, JSON Canvas docs, and local CLI help before editing important vault files.

Because vaults often hold sensitive personal or organizational knowledge, treat the local vault and git history as the source of truth. Review generated note, Base, Canvas, plugin, and theme changes before syncing, publishing, or sharing.

Retrieval Sources

This listing is grounded in:

  • The upstream kepano/obsidian-skills README.
  • The Claude Code marketplace metadata for plugin name, owner, version, and description.
  • Repository license and GitHub metadata.

Core Workflow

Install through Claude Code:

/plugin marketplace add kepano/obsidian-skills
/plugin install obsidian@obsidian-skills

Install with npx skills over HTTPS:

npx skills add https://github.com/kepano/obsidian-skills

For Codex, copy the skills/ directory into the Codex skills path. For OpenCode, clone the full repository into the OpenCode skills directory so the repository structure remains intact.

Capability Scope

The README lists five skills:

Skill Use It For
obsidian-markdown Creating and editing Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and Obsidian-specific syntax
obsidian-bases Creating and editing Obsidian Bases with views, filters, formulas, and summaries
json-canvas Creating and editing JSON Canvas .canvas files with nodes, edges, groups, and connections
obsidian-cli Interacting with Obsidian vaults through Obsidian CLI, including plugin and theme development
defuddle Extracting clean Markdown from web pages with Defuddle to remove clutter and reduce tokens

This pack does not replace Obsidian, guarantee current CLI behavior, or make vault edits safe by itself. It gives agents Obsidian-specific operating knowledge that still needs local review and backup discipline.

Production Rules

  • Work in a git-backed vault or backup copy when changing important notes, Bases, Canvas files, plugins, or themes.
  • Review generated Markdown properties, wikilinks, embeds, callouts, Bases formulas, and Canvas connections before syncing.
  • Keep private notes, credentials, client records, and sensitive research out of public prompts, screenshots, PRs, or shared generated examples.
  • Verify Obsidian CLI commands and plugin/theme steps before running them in a real vault.
  • Preserve source attribution and copyright boundaries when extracting web content into vault notes.

Use Cases

  • Ask Claude Code to convert messy notes into Obsidian Flavored Markdown with properties, wikilinks, callouts, and embeds.
  • Have Codex create a JSON Canvas map that links related research notes.
  • Use an agent to draft or adjust an Obsidian Base view and formulas.
  • Ask OpenCode to scaffold an Obsidian plugin or theme workflow using the Obsidian CLI skill.
  • Extract a clean Markdown note from a web page for personal research using the Defuddle skill.

Source Review

Verified on 2026-06-18:

  • The README says the skills follow the Agent Skills specification and can be used by skills-compatible agents including Claude Code, Codex, and OpenCode.
  • The README documents Claude Code marketplace installation, npx skills installation over SSH or HTTPS, manual Claude Code setup, Codex skills-path setup, and OpenCode clone setup.
  • The README lists five skills: obsidian-markdown, obsidian-bases, json-canvas, obsidian-cli, and defuddle.
  • The marketplace metadata names the plugin obsidian, version 1.0.1, with the description "Claude Skills for Obsidian."
  • GitHub reports MIT licensing for the repository.

Duplicate Review

Checked current content/skills/, content/tools/, content/mcp/, content/agents/, open pull requests, and repository-wide content for kepano/obsidian-skills, Obsidian Agent Skills, Obsidian Claude Code skills, Obsidian Codex skills, Obsidian Markdown skill, JSON Canvas skill, Obsidian Bases skill, Obsidian CLI skill, and Defuddle skill. No dedicated Obsidian Agent Skills entry, exact source URL duplicate, target file, or open duplicate PR was found.

Disclosure

Editorial listing. No paid placement or affiliate link is used. The repository is maintained by Steph Ango and published under the MIT License.

#obsidian#skills#markdown#json-canvas#bases#claude-code#codex#knowledge-management

Source citations

Add this badge to your README

Show that Obsidian Agent Skills is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/skills/obsidian-agent-skills.svg)](https://heyclau.de/entry/skills/obsidian-agent-skills)

How it compares

Obsidian Agent Skills side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

FieldObsidian Agent Skills

Agent Skills for Obsidian by Steph Ango, teaching Claude Code, Codex, OpenCode, and skills-compatible agents to work with Obsidian Flavored Markdown, Bases, JSON Canvas, Obsidian CLI, vaults, plugins, themes, and Defuddle-powered web-to-markdown extraction.

Open dossier 		Dart Agent Skills

Official Dart team Agent Skills for AI coding agents working on Dart unit tests, CLI apps, coverage, runtime errors, mocks, package conflicts, static analysis, Native Assets, FFI, ffigen, and pattern matching.

Open dossier 		Google Agents CLI Skills

Google Agents CLI skill suite for coding agents that build, scaffold, evaluate, deploy, publish, and observe ADK agents on Gemini Enterprise Agent Platform, Agent Runtime, Cloud Run, GKE, and Google Cloud.

Open dossier 		Google Cloud Agent Skills

Google Agent Skills catalog for AI agents working with Google Cloud, Gemini Enterprise Agent Platform, Gemini APIs, Skill Registry, Cloud Run, BigQuery, Firebase, GKE, Cloud SQL, AlloyDB, gcloud, auth, onboarding, and Well-Architected Framework guidance.

Open dossier
Trust
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Categoryskillsskillsskillsskills
Sourcesource-backedsource-backedsource-backedsource-backed
AuthorSteph AngoDart TeamGoogleGoogle
Added2026-06-182026-06-182026-06-182026-06-18
Platforms
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Source repo————
Safety notes✓Obsidian vaults often contain personal notes, private research, customer context, credentials in notes, meeting records, and unpublished plans; scope agent access carefully. The Obsidian CLI skill can guide vault operations, plugin work, and theme development, so review commands before running them against a real vault. JSON Canvas and Bases edits can alter knowledge organization, saved views, formulas, and linked note structures; review generated files before syncing or publishing. Defuddle-powered extraction can bring third-party web content into a vault; check source attribution, copyright, and cleanup before sharing extracted notes.✓Dart skills can modify source code, tests, pubspec dependencies, analysis options, generated mocks, coverage output, native hooks, FFI bindings, and package constraints. `dart fix --apply`, formatter runs, mock generation, build_runner, ffigen, and Native Assets hooks can create broad mechanical diffs; inspect changes before committing. Native Assets and FFI workflows may compile C/C++ code, run local toolchains, download precompiled binaries, and link dynamic or static libraries. Downloaded binaries should use cryptographic hash validation and offline fallbacks as the skill describes. Package conflict fixes can upgrade or downgrade dependencies and affect transitive package behavior across Dart and Flutter projects.✓The skills intentionally guide agents through scaffold, eval, deploy, publish, CI/CD, infrastructure, datastore, and observability workflows that can create or modify cloud resources. Deployment and infrastructure commands may provision service accounts, IAM bindings, Terraform resources, Cloud Run services, Agent Runtime deployments, GKE resources, Artifact Registry images, Secret Manager entries, and CI/CD runners. The workflow skill explicitly requires clarifying goals and writing a spec before scaffolding a new project; skipping that step can create wrong infrastructure or unsafe agent behavior. Evaluation guidance may invoke LLM-as-judge, synthetic datasets, and prompt optimization; treat cost, data exposure, and nondeterminism as production concerns. Do not run deploy, publish, infrastructure, datastore, or CI/CD commands without explicit human approval and a known Google Cloud target.✓Google Cloud skills can create, update, delete, deploy, query, or configure cloud resources, datasets, IAM policies, service accounts, APIs, containers, jobs, and networking. The gcloud skill requires command validation and safety guardrails before invoking Google Cloud CLI commands; do not let agents improvise cloud commands from memory. Skill Registry guidance includes skill lifecycle management such as upload, update, and permanent delete operations; validate environment and approval before use. Cloud Run, GKE, BigQuery, Firebase, Cloud SQL, AlloyDB, and Gemini API workflows can create cost, expose endpoints, alter data, or change production behavior. The repository notes active development, so verify exact commands, product names, API availability, and launch-stage limits before production use.
Privacy notes✓Using the skills can expose note contents, backlinks, properties, canvases, Base queries, plugin code, theme files, vault paths, web extracts, and personal knowledge workflows to the configured model provider. Do not share private journals, client notes, regulated data, secret recovery phrases, API keys, unreleased plans, or internal knowledge bases unless the agent environment is approved for that data. When committing or publishing generated vault files, review embedded links, frontmatter properties, canvas text, extracted quotes, and metadata for private information.✓Dart projects may contain private package names, API schemas, service URLs, test fixtures, generated mocks, coverage paths, stack traces, native library names, and build logs. Runtime-error workflows can expose stack traces, local paths, active app state, logs, and user-input data from the running program. FFI and Native Assets workflows may include proprietary C/C++ source, platform-specific build settings, binary hashes, and downloaded artifact URLs. Keep credentials, private package registries, source paths when sensitive, proprietary native code, test data, and generated coverage reports out of public prompts, issues, PRs, and examples.✓Agents CLI projects can contain Google Cloud credentials, AI Studio keys, Secret Manager names, service account emails, project IDs, regions, Terraform state, eval traces, prompts, tool outputs, logs, traces, user data, embeddings, and datastore contents. Eval artifacts and observability exports can include full prompts, tool calls, responses, failure rationales, trace IDs, and private application data. Publishing to Gemini Enterprise, deploying to Agent Runtime, Cloud Run, or GKE, and enabling analytics can move agent traffic into Google Cloud services subject to separate terms and access controls. Keep project IDs, credentials, Terraform state, traces, eval datasets, user data, private prompts, and secret names out of public issues, PRs, examples, and screenshots.✓Google Cloud workflows may expose project IDs, service account emails, OAuth tokens, API keys, ADC credentials, Terraform state, dataset names, table schemas, query text, logs, traces, prompts, model outputs, embeddings, and customer data. BigQuery, Firebase, Cloud SQL, AlloyDB, GKE, and Agent Platform workflows may process regulated or proprietary data; review data residency, IAM, retention, audit logging, and sharing rules before use. Gemini API and Agent Platform skills can send prompts, files, images, audio, video, tool inputs, structured outputs, cached contexts, and batch datasets to Google services. Keep credentials, project IDs when sensitive, private queries, logs, trace payloads, Terraform state, customer data, and generated datasets out of public prompts, issues, PRs, and screenshots.
Prerequisites
  • An Obsidian vault or project folder where an agent is allowed to read and write Markdown, Base, Canvas, plugin, or theme files.
  • Claude Code plugin support, `npx skills`, Codex skills path access, OpenCode skills directory access, or another Agent Skills compatible host.
  • Obsidian CLI only for workflows that explicitly need vault interaction, plugin development, or theme development through the CLI.
  • A backup, git history, or review workflow before allowing an agent to edit important vault notes or canvases.
  • Dart SDK and project-local tooling installed for the package being edited.
  • An AI coding assistant or skill host compatible with Agent Skills, preferably using the standard `.agents/skills` install target.
  • Project `pubspec.yaml`, `analysis_options.yaml`, test structure, package constraints, and platform targets available before modifying code.
  • For FFI or Native Assets work, compatible host compiler toolchains, package hooks, native source, binding generation configuration, and platform targets.
  • Coding assistant or skill host that can consume Agent Skills, or a local terminal where `uvx google-agents-cli setup` can install the CLI plus skills.
  • Python 3.11+, uv, and Node.js for the documented setup flow.
  • Google Cloud project, billing, credentials, APIs, IAM, region, and deployment target decisions when moving beyond local development.
  • Clear agent requirements before scaffolding: purpose, external APIs, tools, safety constraints, data sources, and deployment preference.
  • AI coding assistant or skill host compatible with the Agent Skills standard and the skills CLI.
  • Google Cloud project, credentials, billing, enabled APIs, IAM roles, and target region when a selected skill touches cloud resources.
  • Current gcloud, bq, kubectl, Terraform, SDK, or product-specific tooling required by the selected Google Cloud workflow.
  • Clear approval boundary before any agent runs cloud deployment, IAM, data, billing, registry, or destructive operations.
Install
/plugin marketplace add kepano/obsidian-skills
npx skills add dart-lang/skills --skill '*' --agent universal --yes
npx skills add google/agents-cli
npx skills add google/skills
Config————
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.