Launches a specialized agent team for a specific development phase using the Claude Code Agent Teams feature.
Install
mkdir -p .claude/skills/start-dev-team && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16711" && unzip -o skill.zip -d .claude/skills/start-dev-team && rm skill.zipInstalls to .claude/skills/start-dev-team
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Claude Code Agent Teamsで開発チームを起動。フェーズごとに必要最小限のロールを選んでleadに編成プロンプトを発火する。 「開発チーム起動」「Agent Team作って」「フェーズ別チーム」と言われた時、または `/start-dev-team --phase requirements|design|implementation|review|release` 形式で呼ばれた時に使用Key capabilities
- →Launch agent teams for development phases
- →Formulate phase-specific team composition prompts
- →Manage team cleanup between phases
- →Define roles for requirements gathering, design, implementation, review, and release
- →Ensure teammates have bounded deliverables
How it works
The skill parses a phase argument and generates a specific natural language prompt for the lead, which then forms an agent team with defined roles and instructions for that development phase.
Inputs & outputs
When to use start-dev-team
- →Starting a dev team
- →Orchestrating multi-agent tasks
- →Managing development phase workflows
About start-dev-team
Automates the initialization of a professional development team with defined roles (e.g., architect, engineer, reviewer). It assigns specific phase-based tasks and ensures teammates follow bounded deliverables.
>
When not to use it
- →When CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS is not set
- →When Claude Code version is below 2.1.32
- →When a preceding team has not been cleaned up
Prerequisites
Limitations
- →1 session 1 team
- →Nested teams are not possible
- →Session resumption does not restore in-process teammates
How it compares
This workflow automates the setup and configuration of multi-agent teams for distinct development phases, ensuring specialized roles and clear instructions for each stage, unlike a manual, ad-hoc team assembly.
Compared to similar skills
start-dev-team side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| start-dev-team (this skill) | 0 | 3mo | No flags | Advanced |
| workflow-router | 1 | 8mo | Review | Intermediate |
| loki-mode | 1 | 8mo | Review | Advanced |
| wg | 0 | 4mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
workflow-router
parcadei
Goal-based workflow orchestration - routes tasks to specialist agents based on user goals
loki-mode
davila7
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
wg
graphwork
Use this skill for task coordination with WG. Triggers include "wg", task graphs, multi-step projects, tracking dependencies, coordinating agents, or when you see a .wg directory.
run-tasks
JeremyKalmus
Orchestrate task execution via beads and sub-agents. Gets ready work from beads, spawns appropriate agents based on labels, monitors completion, and updates status. Use after /approve-spec has created tasks.
rudhra-swarm
Abhishek21g
Orchestrate multiple specialized agents or agent roles for a project. Use when the user says "rudhra swarm", "spin multiple agents", "orchestrate agents", "parallel agents", "agent team", "multi-agent review", or asks Rudhra to split work across mapper, researcher, implementer, tester, reviewer, and
sprint-checkin
twardcox
Start of sprint: carry-over, goals, blockers, sprint plan artifact; get_slash_command: sprint-checkin