By acaprino
Enforce TypeScript best practices, detect dead code with Knip, and generate type-safe production code using advanced generics, Zod validation, and modern toolchains (Vite, pnpm, ESLint).
Knip finds unused files, dependencies, exports, and types in JavaScript/TypeScript projects. Plugin system for frameworks (React, Next.js, Vite), test runners (Vitest, Jest), and build tools. TRIGGER WHEN: cleaning up TypeScript/JavaScript codebases, optimizing bundle size, or enforcing strict dependency hygiene in CI. DO NOT TRIGGER WHEN: the target is a Python codebase (use python-dead-code with vulture/ruff instead).
Enterprise-grade TypeScript depth covering the advanced type system (generics, mapped/conditional types, satisfies operator, branded types, discriminated unions, template literal types), JS-to-TS migration playbooks, modern toolchain setup (tsconfig strict, Vite 7, Vitest, ESLint 9 flat config, pnpm), validation patterns with Zod, type-safe React integration, NestJS API design, and LangChain.js typing. TRIGGER WHEN: migrating a JavaScript codebase to TypeScript, bootstrapping a new TS project (tsconfig + ESLint + Vite/Vitest), writing or refactoring code that uses advanced type patterns (generics, mapped/conditional types, satisfies, branded types), designing Zod schemas for runtime validation, building type-safe NestJS APIs, doing deep React + TypeScript work (typed hooks, generic components, discriminated props), or typing LangChain.js applications. Also trigger when comparing TypeScript with Java/Python enterprise approaches. DO NOT TRIGGER WHEN: writing routine TS/JS without advanced type work (use typescript-development:typescript-write), reviewing React performance specifically (use react-development:review-react), tuning Node.js bundling/packaging unrelated to TS, or doing dead-code detection alone (use typescript-development:knip).
Write TypeScript and JavaScript code following modern best practices and coding standards. TRIGGER WHEN: writing or reviewing TypeScript/JavaScript code, including types, generics, async patterns, module boundaries, and style conventions. DO NOT TRIGGER WHEN: the task is framework-specific React performance (use react-development), Node.js build/packaging, or enterprise-grade deep-dive (use mastering-typescript skill).
Uses power tools
Uses Bash, Write, or Edit tools
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
43 specialized plugins that augment Claude Code into a specialized toolkit -- so you spend less time prompting and more time shipping.
The Daodan is the symbiote that enhances its host. This marketplace is the Daodan of Claude Code.
# Add the marketplace
claude plugin marketplace add acaprino/claude-code-daodan
# Install the plugins you need
claude plugin install python-development@claude-code-daodan
claude plugin install senior-review@claude-code-daodan
claude plugin install react-development@claude-code-daodan
That's it. Plugins activate automatically when relevant -- or invoke them directly:
# Slash commands
/code-review # Multi-agent architecture + security + pattern review
/agent-teams:team-feature # Decompose -> spawn agents -> implement -> verify
/python-scaffold # Scaffold a production-ready Python project
# Agents
"Use the python-engineer agent to implement rate limiting"
"Ask the rust-engineer to review my Tauri backend"
| Plugin | Description | A | S | C |
|---|---|---|---|---|
| python-development | TDD, refactoring, async patterns, packaging, performance, dead code, Pydantic v2, /python-audit | 3 | 9 | 3 |
| senior-review | 9 agents review architecture, security, patterns, distributed flows, logic integrity, API contracts, startup cycles, UI races, and codebase hygiene in parallel | 9 | 1 | 4 |
| codebase-mapper | Generate 10 narrative docs with Mermaid diagrams from any codebase | 10 | 1 | 4 |
| ai-tooling | Brainstorm, plan, execute, optimize prompts, Agent SDK | 1 | 5 | 1 |
| tauri-development | Tauri 2 desktop + mobile, Rust backend, IPC optimization | 3 | 1 | - |
| digital-marketing | SEO + AEO (AI Overviews/Perplexity/ChatGPT Search), GA4/GTM with Consent Mode v2, content strategy, brand naming, domain hunting, text humanization | 5 | 5 | 7 |
| react-development | React 19 performance, state management, bundle optimization | 1 | 1 | 1 |
| rag-development | RAG system design -- chunking, embeddings, vector DBs, advanced patterns | 2 | 1 | 1 |
| marketplace-ops | Audit, scaffold, review, and manage plugins in this ecosystem | 1 | 2 | 4 |
| learning | Mind maps in MarkMind format and interactive force-graphs | - | 3 | 1 |
| deep-dive-analysis | 7-phase systematic codebase analysis with pattern detection | - | 1 | 1 |
| git-worktrees | Parallel development with git worktrees -- create, pause, resume, merge | 1 | 1 | 1 |
| business | Tech law, compliance, privacy docs, contracts, SaaS business planning | 3 | 1 | - |
| stripe | Stripe payments, subscriptions, Connect, revenue optimization, /audit-webhooks | 3 | 1 | 1 |
| research | Quick search and deep multi-source investigation with shared web-search techniques skill | 2 | 1 | - |
| project-setup | Create and maintain CLAUDE.md with ground truth verification | 1 | - | 2 |
| clean-code | Rewrite code for readability without changing behavior | 1 | - | 1 |
| app-analyzer | Analyze Android apps via ADB and webapps via Playwright | 1 | - | - |
| xterm | Build and debug xterm.js terminal emulators | - | 1 | 2 |
npx claudepluginhub acaprino/claude-code-daodan --plugin typescript-developmentReact performance optimization, React 19 API adoption, state management audit, bundle analysis, re-render detection, and Vercel best practices checklist
Cross-platform development rulebook -- security (validation, auth tokens, passkeys/WebAuthn, API security, XSS/CSP, secrets), architecture (client-server, REST vs GraphQL, offline-first, monolith-first, CI/CD), and performance (bundles, images, Core Web Vitals, SSR/SSG, CDN caching) for SPA, PWA, mobile, Electron (with Fuses + asar integrity), and Tauri; includes /platform-review standalone command
Claude Code Daodan session hooks -- skill awareness injection, PreToolUse security gate that BLOCKS hardcoded secrets before they reach disk, autocompact when context is high, cleanup of duplicate built-in plugins, review gate for PR/merge operations, docs gate for documentation auditing, and team spawn gate with runtime-generated agent catalog from marketplace.json (no more drift from hardcoded lists)
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code Agent Teams. Includes the team-review pipeline (deep-dive + interconnect map + parallel reviewers + codebase-hygiene auditor + consolidation) for finding cross-component logic bugs plus dead code / orphan assets / VCS cruft / phantom deps, the team-codebase-map pipeline (context brief + interconnect map + parallel writers + drift-aware review) for producing accurate codebase documentation, and the team-deep-dive pipeline (partition detection + parallel per-partition workers + synthesis + global interconnect map) for monorepo-scale deep-dive analysis.
Generic Claude Code plugin marketplace manager -- auditing, validation, AI quality review, upstream sync, plugin scaffolding, and health monitoring. Works against any project with the standard .claude-plugin/marketplace.json + plugins/<name>/ layout; reads project-specific conventions (author, license, category taxonomy, upstream sources) from the target marketplace.json and CLAUDE.md
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.