Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By Ratler
Orchestrate structured software project workflows: brainstorm features conversationally, generate execution specs, and build via sequential solo agents, delegated sub-agents, or parallel agent teams. Automates git branches, task dependencies, coding, debugging, reviews, security audits, testing, and docs.
npx claudepluginhub ratler/dream-team --plugin dream-teamExecute an implementation plan — reads a spec file, detects mode from frontmatter, runs the appropriate strategy
Systematic debugging — reproduce the issue, investigate root cause, apply targeted fix, verify resolution
Start here — brainstorm and plan a new feature or task through interactive conversation
Show build progress for a spec
Write a delegated execution spec from the current brainstorming session
Use this agent when code needs to be written, files created, or features implemented. Executes ONE task at a time with full read/write access. Uses TDD. Follows specs exactly.
Use this agent for design decisions, architectural analysis, solution proposals, and structural recommendations. Read-only — produces designs, not code.
Use this agent for systematic debugging. Reproduces issues, forms hypotheses, investigates root causes, applies targeted fixes, and verifies resolution. Interactive and methodical — understand it before fixing it.
Use this agent after all code is written to produce and update project documentation. Reviews changes against the spec's Documentation Requirements section and writes README updates, changelog entries, API docs, and inline comments for complex logic. Read-write — modifies documentation files only.
Use this agent for branch integration in delegated mode. Merges builder worktree branches back into the feature branch with tiered conflict resolution. Dispatched by the orchestrator after builder completion and review approval.
Use when the user wants to execute an implementation plan. Reads a spec file, detects the execution mode (sequential, delegated, or team) from frontmatter, and runs the appropriate strategy. Pass the spec file path as an argument.
Use when encountering a bug, test failure, unexpected behavior, or when the user asks for help debugging. Hypothesis-driven — reproduce, investigate, fix, verify. Standalone — works outside the plan/spec/build workflow.
Use when the user wants to build something new or plan a feature. Collaborative brainstorming that explores requirements, constraints, and approach through natural dialogue before any spec is written.
Use after /dream-team:plan to write a delegated execution spec (orchestrator + sub-agents). No arguments needed — picks up conversation context from the brainstorming session.
Use after /dream-team:plan to write a sequential execution spec. No arguments needed — picks up conversation context from the brainstorming session.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Multi-agent team orchestration for parallel task execution, research, and implementation
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
AI-powered cascading development framework with design document system and multi-agent collaboration. Breaks down projects into Features (Mega Plan), Features into Stories (Hybrid Ralph), with auto-generated technical design docs, dependency-driven batch execution, Git Worktree isolation, and support for multiple AI agents (Codex, Amp, Aider, etc.).
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
Give soul to your workflow. 58 AI-powered skills across 17 roles — PM, Dev, Backend, Frontend, QA, UX, Data, Detect, WordPress, Release, Security, DevOps, and Core. Spec-to-ship pipeline: scaffold, implement, test, secure, deploy. Features two-phase workflow with human approval, quality-reviewer agent, token optimization, and continuous improvement via LEARN.md system.
A Claude Code plugin for planning and executing development projects across three execution modes.
Dream Team provides structured planning skills that generate spec files, and a universal build skill that reads the spec and executes it using the appropriate strategy. It ships with eight specialized agents for common development roles.
For all features to work — especially the Team execution mode — you need to enable experimental agent teams in Claude Code:
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
See the Agent Teams documentation for details.
A terminal multiplexer like tmux or iTerm2 is recommended, as agent teams spawn multiple Claude instances that benefit from separate panes/windows for monitoring.
If your specs set playwright: true, builder and tester agents will use Playwright to verify UI changes visually
(navigate pages, take screenshots, interact with elements, check for console errors). Install the
Playwright MCP server to enable this:
claude mcp add playwright npx @playwright/mcp@latest
Without it, agents will skip visual verification and note it in their reports.
For frontend/UI work, the planning skill asks about aesthetic direction (Minimal, Editorial, Brutalist,
Retro-Futuristic, and others) along with color palette, dark/light mode, and typography preferences. When the spec
sets frontend-design: true, the build skill injects comprehensive design guidelines into builder prompts — covering
anti-generic rules, typography, animation timing, interaction patterns, accessibility, and component library
recommendations. This prevents the default "AI look" of generic cards and purple gradients.
Register the repository as a local marketplace, then install:
claude plugin marketplace add Ratler/dream-team-marketplace
claude plugin install dream-team@dream-team-marketplace
Brainstorm your idea:
/dream-team:plan Build a REST API for user management
Write the spec (after brainstorming completes):
/dream-team:spec-delegated
Execute:
/dream-team:build specs/2026-02-08-user-management.md
| Area | Dream Team |
|---|---|
| Philosophy | Turn Claude into a project lead |
| Skills | 6 pipeline-connected skills (plan, spec x3, build, debug) |
| Agents | 8 named roles with per-agent model and tool policies |
| Execution modes | Sequential, Delegated, Team |
| Planning | Formal specs with YAML frontmatter |
| Task tracking | TaskCreate/TaskUpdate with dependency graph |
| Git workflow | Built into execution (branch, commit, review gates) |
| Code review | Configurable review policy with retry loops |
| Team support | Parallel Claude instances via experimental agent teams |
| Playwright | First-class integration (opt-in per spec) |
| Frontend design | Aesthetic direction, anti-generic rules, guidelines |
| Validation | Structural spec checks, dep graph, preflight hooks |
| Build resume | Interrupted builds resume from last completed task |
Dream Team separates the workflow into three distinct phases: brainstorm, spec, build. Each phase has its own command and produces a clear handoff to the next.
/dream-team:plan starts an interactive conversation. It explores the codebase, asks clarifying questions one at
a time, proposes 2-3 approaches with trade-offs, and walks through the task breakdown section by section. No files are
created; the output is a shared understanding between you and Claude. At the end, it recommends which execution mode
fits best.
Once brainstorming is complete, run the spec command for your chosen execution mode. The command you pick determines how the build phase will run:
/dream-team:spec-sequential — produces a spec for single-session execution/dream-team:spec-delegated — produces a spec with agent assignments for orchestrated execution/dream-team:spec-team — produces a spec with team configuration for parallel Claude instances