obsidian-skills-agent
```markdown
What this skill does
```markdown --- name: obsidian-skills-agent description: Teach AI coding agents to work with Obsidian vaults using Markdown, Bases, JSON Canvas, and the Obsidian CLI triggers: - work with obsidian vault - create obsidian notes - edit obsidian markdown - use obsidian bases - create json canvas - interact with obsidian cli - add obsidian agent skills - teach agent obsidian syntax --- # Obsidian Skills for AI Agents > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. `obsidian-skills` is a collection of agent skills that teach AI coding agents (Claude Code, Codex CLI, OpenCode, Cursor, etc.) how to work with Obsidian vaults. It covers Obsidian Flavored Markdown, Bases, JSON Canvas, and the Obsidian CLI — following the [Agent Skills specification](https://agentskills.io/specification). --- ## Installation ### Via Marketplace (if supported) ``` /plugin marketplace add kepano/obsidian-skills /plugin install obsidian@obsidian-skills ``` ### Via npx ```bash npx skills add [email protected]:kepano/obsidian-skills.git ``` ### Claude Code (Manual) Copy the repo contents into a `/.claude` folder at the root of your Obsidian vault: ```bash git clone https://github.com/kepano/obsidian-skills.git /path/to/vault/.claude ``` ### Codex CLI (Manual) Copy the `skills/` directory into your Codex skills path: ```bash git clone https://github.com/kepano/obsidian-skills.git /tmp/obsidian-skills cp -r /tmp/obsidian-skills/skills/* ~/.codex/skills/ ``` ### OpenCode (Manual) Clone the full repo into the OpenCode skills directory: ```bash git clone https://github.com/kepano/obsidian-skills.git ~/.opencode/skills/obsidian-skills ``` > Do **not** copy only the inner `skills/` folder. Clone the full repo so the path resolves to: > `~/.opencode/skills/obsidian-skills/skills/<skill-name>/SKILL.md` > > OpenCode auto-discovers all `SKILL.md` files under `~/.opencode/skills/`. Restart OpenCode after cloning. --- ## Available Skills | Skill | File | Description | |---|---|---| | `obsidian-markdown` | `skills/obsidian-markdown/SKILL.md` | Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties | | `obsidian-bases` | `skills/obsidian-bases/SKILL.md` | Obsidian Bases (`.base`) with views, filters, formulas, summaries | | `json-canvas` | `skills/json-canvas/SKILL.md` | JSON Canvas (`.canvas`) with nodes, edges, groups, connections | | `obsidian-cli` | `skills/obsidian-cli/SKILL.md` | Obsidian CLI for vault, plugin, and theme interaction | | `defuddle` | `skills/defuddle/SKILL.md` | Extract clean markdown from web pages using Defuddle | --- ## Obsidian Flavored Markdown Obsidian uses a superset of standard Markdown. Key syntax additions: ### Properties (Frontmatter) ```markdown --- title: My Note tags: - research - ai date: 2026-03-01 status: draft aliases: - My Research Note --- ``` ### Wikilinks ```markdown [[Note Name]] [[Note Name|Display Text]] [[Folder/Note Name]] [[Note Name#Heading]] ``` ### Embeds ```markdown ![[Note Name]] ![[image.png]] ![[Note Name#Section]] ![[Note Name#^block-id]] ``` ### Callouts ```markdown > [!note] > This is a note callout. > [!warning] Custom Title > This is a warning with a custom title. > [!tip]- Collapsible Tip > This callout is collapsible by default (closed). > [!info]+ Expanded Collapsible > This callout is collapsible and starts open. ``` Callout types: `note`, `abstract`, `info`, `tip`, `success`, `question`, `warning`, `failure`, `danger`, `bug`, `example`, `quote` ### Block IDs ```markdown This paragraph has a block ID. ^my-block-id - List item with block ID ^list-block ``` Reference with: `[[Note#^my-block-id]]` ### Tags ```markdown #tag #nested/tag #multi-word-tag ``` --- ## Obsidian Bases (`.base` files) Bases are database-like views over your vault's markdown files, using `.base` file format. ### Basic Base File ```yaml # my-projects.base view: table filter: type: eq field: type value: project fields: - name - status - due - priority sort: - field: due order: asc ``` ### Views ```yaml view: table # Spreadsheet-style view: list # Simple list view: board # Kanban-style (requires groupBy) view: gallery # Card/image grid view: calendar # Calendar (requires date field) ``` ### Filters ```yaml # Single filter filter: type: eq field: status value: active # Compound filter filter: type: and conditions: - type: eq field: type value: project - type: neq field: status value: archived ``` Filter operators: `eq`, `neq`, `gt`, `gte`, `lt`, `lte`, `contains`, `not_contains`, `starts_with`, `ends_with`, `is_empty`, `is_not_empty` ### Formulas ```yaml fields: - name: days_remaining formula: "dateDiff(now(), due, 'days')" - name: full_name formula: "concat(first_name, ' ', last_name)" ``` ### Summaries ```yaml summary: - field: budget type: sum - field: status type: count_by_value ``` --- ## JSON Canvas (`.canvas` files) JSON Canvas is an open format for infinite canvas data. Files use the `.canvas` extension. ### Minimal Canvas ```json { "nodes": [ { "id": "node1", "type": "text", "x": 0, "y": 0, "width": 250, "height": 100, "text": "Hello, Canvas!" } ], "edges": [] } ``` ### Node Types ```json { "nodes": [ { "id": "text-node", "type": "text", "x": 0, "y": 0, "width": 250, "height": 100, "text": "## Markdown content\nSupports **bold**, *italic*, [[wikilinks]]" }, { "id": "file-node", "type": "file", "x": 300, "y": 0, "width": 400, "height": 300, "file": "Notes/My Note.md" }, { "id": "link-node", "type": "link", "x": 0, "y": 200, "width": 400, "height": 200, "url": "https://obsidian.md" }, { "id": "group-node", "type": "group", "x": -50, "y": -50, "width": 600, "height": 400, "label": "My Group", "background": "#ff6b6b", "backgroundStyle": "solid" } ] } ``` ### Edges (Connections) ```json { "edges": [ { "id": "edge1", "fromNode": "node1", "fromSide": "right", "toNode": "node2", "toSide": "left", "label": "connects to", "color": "#ff0000" } ] } ``` Edge sides: `top`, `right`, `bottom`, `left` ### Node Colors ```json { "color": "1" } ``` Preset colors: `"1"` (red), `"2"` (orange), `"3"` (yellow), `"4"` (green), `"5"` (cyan), `"6"` (purple) Custom: `"color": "#ff6b6b"` ### Full Canvas Example ```json { "nodes": [ { "id": "idea-central", "type": "text", "x": 200, "y": 200, "width": 300, "height": 150, "color": "4", "text": "# Central Idea\nThe core concept here." }, { "id": "note-ref", "type": "file", "x": 600, "y": 100, "width": 400, "height": 300, "file": "Research/Background.md" }, { "id": "web-ref", "type": "link", "x": -200, "y": 150, "width": 350, "height": 200, "url": "https://example.com/source" } ], "edges": [ { "id": "e1", "fromNode": "idea-central", "fromSide": "right", "toNode": "note-ref", "toSide": "left", "label": "supported by" }, { "id": "e2", "fromNode": "web-ref", "fromSide": "right", "toNode": "idea-central", "toSide": "left", "label": "references" } ] } ``` --- ## Obsidian CLI The Obsidian CLI lets you interact with vaults programmatically. ### Common Commands ```bash # Open a vault obsidian open /path/to/vault # Open a specific note obsidian open /path/to/vault --file "Notes/My Note.md" # Create a new note obsidian new /path/to/vault --file "Notes/New Note.md" --content "# New Note" # List all notes in vault obsidian list /path/to/vault # Search vault obsidian search /path/to/vault --query "se
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.