By noopz
LLM-maintained knowledge base for Obsidian vaults. Auto-triggers on paper sharing, vault health queries, concept compilation, research questions, and domain management.
Analyzes a research paper's methodology section in depth from extracted text. Dispatched by the paper-analyzer skill during multi-stage paper analysis. Produces a structured breakdown of research design, datasets, baselines, metrics, setup, and limitations with specific numbers and table references.
Reviews a combined paper-analysis (methodology + results) for completeness and quality, scores it 0–100, and identifies specific gaps for revision. Dispatched by the paper-analyzer skill as the final reflection pass before the analysis is committed to the vault.
Interprets a research paper's results tables, figures, and claims to validate whether conclusions follow from the data. Dispatched by the paper-analyzer skill during multi-stage paper analysis. Produces a quantitative breakdown with specific numbers, claim validation, and flagged overstatements.
Proposes per-genre quality rules for `.wiki/conventions.json` by reading sample notes from each genre and synthesizing patterns the user actually uses. Dispatched directly by the user, by the indexer when new genres cross the 3-note threshold without rules, or in response to a SessionStart warning about empty rules.
Identifies cross-domain concept bridges surfaced by a newly ingested source and adds connection callouts to affected notes in other domains. Dispatched after wiki-ingest when `cross-domain.ts` reports bridge concepts. Receives the script's JSON output inline.
Autonomous vault improvement loop (writes changes). Use when user says 'improve the vault', 'autoimprove', 'fix what you can', 'what's the vault score'. Do NOT use for read-only diagnostics — that's wiki-lint.
Deep paper breakdown (does not write vault notes). Use when user says 'analyze this paper', 'break down this paper', 'is this paper any good', or sends an arXiv ID/PDF with no save intent. Do NOT use when user wants the paper saved — that's wiki-ingest.
Fill concept stubs with citation-grounded definitions. Use when user says 'fill in the stubs', 'compile concepts', 'flesh out concepts', or as follow-up after wiki-lint reports stubs. Do NOT use for new sources not yet in vault — that's wiki-ingest.
User-invoked: surface hidden concept connections via local embeddings (Ollama + nomic-embed-text). Flags related-but-unlinked (sentence, concept) pairs, then adds wikilinks where the connection holds. Invoke explicitly via /wiki-deep-link.
Set up, list, rename, or merge research domains. Use when user says 'add a domain for X', 'set up a domain', 'what domains exist', 'change scope of X domain', 'merge X and Y domains'. Do NOT speculatively fire on ingest prompts — wiki-ingest hands off explicitly when no domain matches.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
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.
A Claude Code plugin that turns any folder into an LLM-maintained knowledge base. Inspired by the commonplace book tradition and Karpathy's approach to using LLMs for personal wiki management.
Works on any directory — Obsidian vault, plain folder, whatever. Obsidian is not required; it's just a good browser for [[wikilink]] markdown if you use it.
.wiki/, discover initial domainsSkills auto-trigger from natural conversation. You never type slash commands — just chat and the right skill activates.
┌─────────────┐
│ wiki-init │ (one-time setup)
└──────┬──────┘
│ writes .vault-path
▼
┌──────────────────────────────────────┐
│ (vault is active) │
└──────────────────────────────────────┘
│
┌──────────────────┼──────────────────────────┐
│ │ │
▼ ▼ ▼
┌────────────┐ ┌─────────────┐ ┌──────────────┐
│ wiki-domain│ │ wiki-ingest │ ◀───┐ │ wiki-query │
└────────────┘ └──────┬──────┘ │ └──────┬───────┘
(new domain │ paper? │ │ pivot Q
when ingest │ ─yes──▶ paper-analyzer │ "how does
finds none) │ (returns │ this relate
│ analysis) │ to X?")
▼ │
┌──────────────┐ │ ◀────┘
│ supersession │ (post-ingest pivot
│ declared in │ auto-fires wiki-query)
│ body? ──yes┼─▶ wiki-supersede
└──────┬───────┘
│ no
▼
┌────────────────┐
│ post-write hook│
│ (deterministic)│
└──────┬─────────┘
│ dispatches
┌───────────────┼─────────────────┐
▼ ▼ ▼
wiki-moc-updater wiki-impact-checker wiki-cross-domain-linker
│
└─ supersession candidate ──▶ wiki-supersede
Read-only path: Autonomous-write path:
┌──────────────┐ ┌──────────────┐
│ wiki-lint │ ◀── if fixes ──▶ │ autoimprove │
│ (diagnose) │ wanted │ (score loop) │
└──────────────┘ └──────┬───────┘
│ dispatches per round
┌─────────────────┼────────────────┬──────────────────┐
▼ ▼ ▼ ▼
wiki-linter wiki-pruner wiki-moc-updater wiki-deep-linker
(refuses retired (semantic
→ wiki-supersede) candidates)
│
▼
wiki-compile (inline at main-model cost)
│
▼
wiki-freshness-checker (post-loop)
Bottom-up triggers (any skill → wiki-supersede):
• wiki-query lands on retired note
• wiki-pruner asked to delete retired
• wiki-impact-checker flags candidate
• commonplace lint reports retired-but-referenced
Structural outline plugin for Claude Code — entropy-guided structural outlines for large files, reducing context consumption on first reads
Shape your Obsidian vault - create notes, search tags, analyze links, and manage frontmatter
npx claudepluginhub noopz/stray-bits-sanctuary --plugin commonplacePersistent, compounding knowledge base maintained by LLMs in Obsidian — agent-first edition. Four task-oriented agents (Researcher / Advisor / Curator / Scribe) with citations, confidence, supersession, and rolling session cache. Inspired by Karpathy's LLM Wiki pattern.
Build and maintain LLM-powered knowledge bases as Obsidian wikis with compile, query, lint, and evolve workflows
AI thinking partner for your Obsidian vault — process, recall, synthesize, research with evidence-backed learning science
Bidirectional knowledge flow between Claude Code and Obsidian — 20 MCP tools, skills, and hooks for PKM
Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills
Turn your Markdown vault into a searchable knowledge graph that any AI agent can query.