By monte9
Turn a folder of markdown documents into an interactive visual graph. Use AI to review, iterate on, and synthesize your thinking — then see how everything connects.
Set up and build an interactive graph visualization for a folder of markdown files. Use this skill whenever the user wants to visualize relationships between documents, build or rebuild the doc graph, set up the graph viewer, or see how their documents reference each other. Also use when the user mentions 'build the graph', 'rebuild the graph', 'update the graph', 'graph viewer', 'doc graph', 'knowledge map', or wants to explore connections between notes, docs, or any collection of interlinked markdown files.
Create an interactive HTML chart for the graph viewer, paired with a chart-*.md doc so it wires into the graph. Use when the user asks to make a chart, build a visualization, add a heatmap/matrix/scatter, turn an analysis into a chart, or create any standalone HTML visualization that should open from a node in the graph. Also use when adding a chart to accompany an existing analysis doc (the common pattern: an analysis doc describes trends; a chart renders them). The skill covers the non-obvious iframe-download contract and the shared visual vocabulary — without these, charts render but the viewer's download button silently fails and the design drifts. Rebuilds the graph after creation so the new chart shows up immediately.
Create a new document in the user's docs folder with the right format for the graph viewer. Use when the user asks to write a doc, add a guide, capture a reference, save a review/critique, add a review of a Notion page, or otherwise add a markdown file to their folder. Also use when the user says 'create a doc', 'write a note', 'capture this', 'add a guide', 'add a ref', 'review this page', or wants to save any structured markdown document. Regenerates the graph index after creation.
Produce a single-dimension landscape analysis across the 24 Rosebud competitors in data/competitors/ — an analysis doc with a tight overview + named-evidence bullets, paired with a chart that renders the pattern. Use whenever the user says things like 'analyze the X dimension', 'do the next dimension', 'compile trends for X across competitors', 'build the landscape for Y', 'what does the landscape look like for Z', or 'let's do <dimension_name> next'. Also use iteratively — one dimension at a time — when building toward the full landscape report. Chart type is a deliberate judgment call based on the shape of the data, not a fixed template. Delegates file creation to create-doc and create-chart; this skill owns the data extraction and the pattern synthesis.
Research a competitor following the Rosebud competitive research system (mental-health practitioner tools). Use when a Rosebud team member says 'research <competitor>', 'analyze <competitor>', 'competitive research on X', 'research wysa', 'research quenza', or similar. Delegates to the dimensions reference doc — all research instructions (what to measure, how to structure the writeup, voice rules) live there. Rosebud-specific: not intended for general-purpose competitor research.
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 Cowork plugin that turns a folder of markdown documents into an interactive visual graph. See how your documents connect to each other — rendered as a single HTML file you can open in any browser.
Option A — From GitHub (recommended):
Monte9/docs-graph and click SyncOption B — Manual upload:
.zip file_graph/index.html in your browserAsk Claude to "rebuild the graph" after adding or editing documents.
To get the latest version after an update:
Monte9/docs-graphThe version number on the plugin page shows which version you have installed.
The plugin expects three sibling directories at the root of your folder. docs/ and data/ are required; _graph/ is auto-generated.
your-folder/
├── _graph/ ← the viewer lives here (auto-generated)
├── docs/ ← your documents go here
│ ├── 2026-03-01/
│ │ └── doc-kickoff.md
│ └── 2026-04-10/
│ └── review-proposal.md
└── data/ ← optional research data folders
└── product-research/
├── source1.md
└── facts.csv
Each markdown file starts with a metadata block:
---
name: My Document Title
date: 2026-04-10
type: doc
description: A one-sentence summary
references:
- https://notion.so/some-page
- 2026-04-02/other-doc.md
---
Your content here...
Types:
doc — default dated timeline entry (analysis, synthesis, brief, draft, working notes)review — critique or review of another doc or pageguide — how-to / process / style; pinned in the top stripref — canonical domain context; pinned in the top stripchart — visualization paired with a parent doc via the chart: fieldReferences create edges between documents in the graph. Add notion_id: <32-char-id> on a ref or guide to mark it as synced to a Notion page.
./build.sh
Creates docs-graph.zip for sharing. Also auto-built on every push to main via GitHub Actions.
Python 3 and a modern web browser.
MIT
npx claudepluginhub monte9/docs-graph --plugin docs-graphBuild and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
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).
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.