By qhuang20
Initialize Obsidian-specific skills environment for Claude Code on session start inside a vault, loading predefined patterns like Karpathy's LLM Wiki for automated LLM interaction.
A Claude Code plugin that turns Claude into a better collaborator inside your Obsidian vault.
Whenever you start Claude Code in a directory that is inside an Obsidian vault (any folder with a .obsidian/ subdirectory, searched upward from your working directory), this plugin automatically loads a shared working style so Claude acts like a disciplined note-taking partner instead of a generic assistant. Outside a vault, it does nothing — your other projects are unaffected.
No commands to remember, no configuration, no folder layout imposed on you.
llm-wikiLoads Andrej Karpathy's LLM Wiki pattern as a mental model for the session. The idea: instead of retrieving from raw documents every time you ask a question, Claude helps you build a persistent, interlinked wiki of markdown pages that compounds over time — summaries, entity pages, concept pages, an index, and a log of what's been added.
Three lightweight operations anchor the workflow:
The skill is a pure guide — it does not define slash commands, enforce a directory layout, or write to your vault on its own. Claude co-evolves the specifics (page formats, folders, tooling) with you based on your domain.
Inside a running Claude Code session:
/plugin marketplace add qhuang20/obsidian-skills
/plugin install obsidian-skills@obsidian-skills
That's it. Next time you start a session from inside any Obsidian vault, the llm-wiki working style loads automatically.
To verify it's working, start Claude Code from a vault folder and ask: "Did the obsidian-skills plugin inject any context at session start?"
/plugin uninstall obsidian-skills@obsidian-skills
.obsidian/ subdirectory). Obsidian itself is optional — the plugin only looks for the marker directory.More Obsidian-related skills are planned (daily notes, link management, publishing workflows). Each will auto-activate in the same unobtrusive way: helpful in a vault, silent everywhere else.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub qhuang20/obsidian-skills --plugin obsidian-skillsA Claude Code plugin for planning, architecture, bug triage, and development workflows. Just shout SHAZAM!
Compare AI coding skills head-to-head to find which one works best for your task
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Make your AI agent code with your project's architecture, rules, and decisions.