claude-obsidian

Run an autonomous research loop on a topic. Searches the web, synthesizes findings, and files everything into the wiki as structured pages.

Open, create, or update a visual canvas — add images, text, PDFs, wiki pages, and banana-generated assets to Obsidian canvas files.

Save the current conversation or a specific insight into the wiki vault as a structured note.

Bootstrap or check the claude-obsidian wiki vault. Reads the wiki skill and runs setup workflow.

Pre-commit audit specialist. Dispatched by a workstream owner AFTER staging changes but BEFORE committing. Reads the staged diff plus every precedent file the diff touches; applies the /best-practices six-cut engineering kernel and the agent kernel; returns findings in four tiers (BLOCKER / HIGH / MEDIUM / LOW) with file:line citations and recommended fixes. Closes the loop the v1.7 audit revealed: code went worker → commit with no separate verifier pass, which is exactly how BLOCKER B1 (data-egress consent gap) slipped through. <example>Context: Owner has staged a refactor across 4 files and wants a second opinion before committing. user: "Verify the staged diff before I commit." assistant: "I'll dispatch the verifier agent against the staged diff." </example> <example>Context: Owner finished a feature workstream and is about to cut a commit. user: "Run the verifier on this slice." assistant: "Dispatching the verifier with the workstream context." </example>

Parallel batch ingestion agent for the Obsidian wiki vault. Dispatched when multiple sources need to be ingested simultaneously. Processes one source fully (read, extract, file entities and concepts, update index) then reports what was created and updated. Use when the user says "ingest all", "batch ingest", or provides multiple files at once. <example>Context: User drops 5 transcript files into raw/ and says "ingest all of these" assistant: "I'll dispatch parallel agents to process all 5 sources simultaneously." </example> <example>Context: User says "process everything in raw/ that hasn't been ingested yet" assistant: "I'll use wiki-ingest agents to handle each source in parallel." </example>

Comprehensive wiki health check agent. Scans for orphan pages, dead links, stale claims, missing cross-references, frontmatter gaps, and empty sections. Generates a structured lint report. Dispatched when the user says "lint the wiki", "health check", "wiki audit", or "clean up". <example>Context: User says "lint the wiki" after 15 ingests assistant: "I'll dispatch the wiki-lint agent for a full health check." </example> <example>Context: User says "find all orphan pages" assistant: "I'll use the wiki-lint agent to scan for pages with no inbound links." </example>

精准对齐信息差。无需 query MCP，通过 Index-First Traversal + grep-based 检索， 快速定位知识缺口、矛盾点、已知边界。生成结构化对齐报告，自动创建 gap 页面。 触发词: align, 对齐, 我知道多少, check my understanding, what gaps, knowledge gap, 信息差, 我对X了解多少, audit my knowledge, where am I on X.

Autonomous iterative research loop. Takes a topic, runs web searches, fetches sources, synthesizes findings, and files everything into the wiki as structured pages. Based on Karpathy's autoresearch pattern: program.md configures objectives and constraints, the loop runs until depth is reached, output goes directly into the knowledge base. Triggers on: "/autoresearch", "autoresearch", "research [topic]", "deep dive into [topic]", "investigate [topic]", "find everything about [topic]", "research and file", "go research", "build a wiki on".

Visual layer of the wiki. Add images, text cards, PDFs, and wiki pages to Obsidian canvas files with auto-positioning inside zones. Integrates with /banana for image capture. Triggers on: /canvas, canvas new, canvas add image, canvas add text, canvas add pdf, canvas add note, canvas zone, canvas list, canvas from banana, add to canvas, put this on the canvas, open canvas, create canvas.

Strip clutter from web pages before ingesting into the wiki. Removes ads, navigation, headers, footers, and boilerplate: leaving clean readable markdown that saves 40-60% tokens. Triggers on: defuddle, clean this page, strip this url, fetch and clean, clean web content before ingesting, strip ads, remove clutter, clean URL content, readable markdown from URL.

为 concept/source 页面生成 Flux 概念插画（交互式工作流）

6 hooks across 4 events