Full-stack development plugin for welld Spring Boot Kotlin + React TypeScript projects. Bundles a spec-driven workflow (spec/plan/tasks commands), a 7-role agent team (PO, architect, designer, FE/BE dev, devops, QE) with an orchestrator command, a Copier-based scaffolder command with connection checklists, skills, security and ADR specialist agents, lifecycle hooks, and MCP servers (sequential-thinking, playwright, github).
Adopt WellForge in an existing (brownfield) project — AI-readiness, spec workflow, calibrated quality gates
Scaffold a new welld project — interview, stack recommendation, generation, connections
Orchestrate the full agent team on a goal (spec → plan → tasks → implementation → QE verdict)
Create the technical plan for a spec, following the **spec-driven** skill conventions
Write a feature specification (spec-driven workflow, step 1 of 3)
Architecture Decision Record (ADR) specialist. Fires automatically when a significant design decision is made during a cc-sdd session — technology choices, pattern adoptions, trade-off resolutions, API design decisions, or any choice that will constrain future work. Also invoke manually with: "write an ADR for [decision]". Outputs a versioned ADR file and optionally updates CLAUDE.md with a summary reference.
Software Architect for the welld spec-driven workflow. Use to turn an APPROVED spec into a technical plan (specs/NNN-slug/plan.md): architecture, data model, API contracts, test strategy, risks. Also use for stack-fit evaluations and to flag decisions that need an ADR. Trigger phrases: "plan the implementation of", "act as architect", "design the solution for".
Backend Developer for the welld spec-driven workflow. Use to implement backend tasks from a specs/NNN-slug/tasks.md — Spring Boot + Kotlin + jOOQ + Liquibase per the kotlin-springboot-welld skill, or Hono + TypeScript per the hono-ts-backend skill. Invoke with one or more task IDs. Trigger phrases: "implement T2", "act as backend dev", "build the API for task".
UX/UI Designer for the welld spec-driven workflow. Use for features with a user interface: UX flows, screen/state inventory, component reuse mapping (Mantine), and accessibility requirements. Runs between spec approval and task derivation. Can drive the running app with Playwright to audit current UI. Trigger phrases: "design the UX for", "act as designer", "map the screens for".
DevOps Engineer for the welld spec-driven workflow. Use for CI/CD pipelines, Docker and infrastructure files, environment configuration, release wiring, and connecting projects to ecosystem tools (GitHub settings, MCP servers, registries, observability). Trigger phrases: "set up CI", "act as devops", "wire up the pipeline", "connect this project to".
Standardized checklists for connecting a welld project to its ecosystem tools — GitHub (repo, branch protection, secrets), CI, MCP servers, environments and databases. Use during /welld-dev:new stage 5, when the user asks to "connect", "set up", or "wire up" a tool/integration for a project, or when the devops agent needs the standard procedure. Every checklist ends with a verification command: a connection is established only when that command's output says so.
Hono + TypeScript best practices for modern backend services. Use this skill whenever building or reviewing Hono TypeScript APIs, setting up a new service, defining routes, implementing middleware, handling validation, or managing database operations. Covers project setup with modern tooling (pnpm, tsx, Biome), Hono routing patterns, Zod validation, functional error handling with Effect TS, Drizzle ORM with PostgreSQL, OpenAPI documentation, and Docker deployment. Always trigger this skill for any Hono TypeScript task — even partial ones like "add a route", "create middleware", or "set up validation".
Kotlin and Spring Boot development. Trigger this skill for ANY task involving Kotlin, Spring Boot, JVM, Maven, jOOQ, Liquibase, database migrations, REST APIs, or backend services. Covers welld-style best practices including functional error handling with Result/DomainError, Spring Modulith module boundaries, repository patterns, and Spring configuration. Use for writing code, reviewing code, setting up new services, defining migrations, configuring dependencies, scaffolding modules, or debugging Spring applications. Always trigger for partial tasks like "add a repository", "create a migration", "set up a new module", "add an endpoint", or "fix a Spring Boot issue".
mise (dev tools version manager) expert for welld monorepos. Use this skill whenever the user asks to set up mise, add tools to mise, create or edit a mise.toml, define mise tasks, manage Java/Node/pnpm/Maven versions, or replace npm scripts / Makefile with mise tasks. Also trigger for phrases like "pin the node version", "add a task for", "run with mise", "how do I manage tool versions", "set up dev environment", or any question about .mise.toml configuration. Always use this skill proactively when scaffolding new projects or services — every welld project should have a mise.toml.
Expert React + TypeScript + Vite frontend development skill. Use this skill whenever the user asks to build, scaffold, extend, or refactor a React application using TypeScript. Triggers include: "create a React component", "build a page with React", "add a feature to my React app", "scaffold a new Vite project", "write a custom hook", "set up React Context", "add TanStack Query/Router", "style with Tailwind", "refactor this component", "use Effect TS in React", or any time the user describes frontend work in a React/TypeScript codebase. Always use this skill proactively whenever frontend React/TypeScript code is being produced — even if the user just says "create a form" or "add a new page". Prefer this skill over generic coding responses for any React work.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
External network access
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.
Connects to servers outside your machine
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
welld's internal platform for reproducible, standard, fast AI-assisted project setup: product idea → building, CI-gated, spec-driven, AI-ready repository in minutes — with a fleet that stays upgradeable as standards evolve.
brew tap matteocodogno/wellforge https://github.com/matteocodogno/wellforge
brew install matteocodogno/wellforge/wellforge
wellforge setup # toolchain + repo + plugin, verified
| Doc | For |
|---|---|
| Features | what WellForge does — the 6 pillars in detail |
| Installation | machine setup — brew fast path or manual |
| Quick start | scaffold a greenfield project (~30 min) |
| PLAN.md | build roadmap, per-phase status, honest deviations |
/welld-dev:new idea → interview → stack pick → scaffold → verified build → connections
/welld-dev:spec|plan|tasks standardized spec-driven feature workflow (2 human gates)
/welld-dev:orchestrate full agent team on a goal (PO → Architect → Devs ∥ → QE verdict)
/welld-dev:upgrade re-template a project to a newer release, AI-resolved conflicts
| Piece | Where |
|---|---|
| Claude Code plugin (commands, 9 agents, skills, hooks, MCP) | welld-dev-plugin/ |
Project templates — Copier monorepo, root copier.yml | templates/ (contract) |
| Quality gates — reusable workflows + central thresholds | .github/workflows/ + gates/ |
| Fleet status script | scripts/fleet-status.sh |
Status: all 6 pillars built and E2E-tested (template release v0.1.0, gates
gates-v0). Outstanding before v1.0.0: the Phase 7 pilot on a real project — see
PLAN.md.
Internal welld tooling. Contributions: PRs only for templates/ and gate thresholds
(that review is the single discretion point of the quality system).
npx claudepluginhub matteocodogno/wellforge --plugin welld-devComprehensive 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.
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
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.
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.
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.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques