By wrxck
Generate and insert Mermaid diagrams into READMEs by analyzing your project's codebase, dependencies, and flows — covering architecture, data models, and sequences.
Analyses project structure, dependencies, and flows to suggest appropriate diagrams. Use when needing to understand a codebase before generating diagrams.
Reviews project READMEs and improves them with Mermaid diagrams and visual documentation. Use when the user wants to enhance existing README files.
A Claude Code plugin that generates detailed, accurate Mermaid diagrams from your codebase and improves READMEs with visual documentation.
claude plugin marketplace add wrxck/claude-plugins
claude plugin install diagram-expert@wrxck-claude-plugins
/diagram <description>Generate a Mermaid diagram from a description or by analysing your codebase.
/diagram architecture
/diagram sequence for the auth flow
/diagram erd
/diagram deployment
/diagram:readme [path]Analyse a project and suggest README improvements with diagrams.
/diagram:readme
/diagram:readme ./packages/api
| Type | Mermaid keyword | Best for |
|---|---|---|
| Flowchart | graph TD/LR | Architecture, deployment, data pipelines |
| Sequence | sequenceDiagram | API flows, auth chains, multi-service interactions |
| ERD | erDiagram | Database schemas, data models |
| State | stateDiagram-v2 | Order flows, document lifecycles |
| Class | classDiagram | Service interfaces, component APIs |
| Gantt | gantt | Project timelines |
| Gitgraph | gitgraph | Branching strategies |
| Pie | pie | Proportional breakdowns |
| Provider | Mermaid support |
|---|---|
| GitHub | Native rendering |
| GitLab | Native rendering |
| Azure DevOps | Native rendering |
| Bitbucket | No native support (plugin offers alternatives) |
The plugin includes two specialised agents:
MIT
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.
npx claudepluginhub wrxck/claude-plugins --plugin diagram-expertAutonomous security auditor. Scans a GitHub repo for vulnerabilities, triages false positives, writes a PoC, fixes each confirmed bug in its own PR, independently reviews the fix, and merges when the review is clean.
Learns from your corrections and writes hooks so Claude never repeats the same mistake
Git workflow - commit validation, conventional commits, PR creation, releases, code review
Mines your Claude Code history, config, and session transcripts, spots the workflows you keep repeating, and forges them into the right artifact — a skill, subagent, hook, slash command, workflow, or a full publishable plugin. Local-only analysis; hands off to mcp-forge, behavior-hooks, and matts-second-brain where they fit.
Turn any repo into rich, brand-matched promo videos. Scaffolds a config-driven Remotion + ffmpeg pipeline, inherits the repo's colours, fonts, logo and copy, and renders multiple aspect ratios (16:9, 9:16, 1:1, 4:5) with a live in-browser tuning UI.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
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.
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.
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.
Build 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.