dev-team
Orchestrate a multi-agent dev/agency team with shared memory, handoffs, and OpenClaw sessions. Use when (1) First-time onboarding — follow references/OPENCLAW_TEAM_SETUP_GUIDE.md (guided variables + master prompt) and references/SKILL-SETUP.md, (2) Running specialized agents (PM, dev, QA, security) on customer or Shopware tasks, (3) Setting up shared team folders and SOUL.md identities, (4) sessions_spawn/sessions_send or control channels (e.g. Telegram), (5) Solo-founder multi-agent pattern from awesome-openclaw-usecases.
Best for multi-agent setupsWorks with GitHub
⌘source
- author
@LeoYeAI- language
- Python
★2kstars
306forks
May 6, 2026
✦overview.md
Key Features
- ·Multi-role agent orchestration
- ·Shared project memory on disk
- ·Traceable handoffs between agents
- ·Customer/ client workspace isolation
Use Cases
- →Onboard a new team member by running the setup guide
- →Run a PM agent to manage requirements and a Dev agent to implement features
- →Use QA and Security agents to review code and run scans
- →Isolate work for different customers in separate folders
Best for
- ✓multi-agent setups
- ✓OpenClaw workflows
- ✓team-based dev tasks
Not ideal for
- !single-agent tasks
- !binaries or secrets management
FAQs
name
dev_team
description
Orchestrate a multi-agent dev/agency team with shared memory, handoffs, and OpenClaw sessions. Use when (1) First-time onboarding — follow references/OPENCLAW_TEAM_SETUP_GUIDE.md (guided variables + master prompt) and references/SKILL-SETUP.md, (2) Running specialized agents (PM, dev, QA, security) on customer or Shopware tasks, (3) Setting up shared team folders and SOUL.md identities, (4) sessions_spawn/sessions_send or control channels (e.g. Telegram), (5) Solo-founder multi-agent pattern from awesome-openclaw-usecases.
metadata:{"version":"1.0.1","openclaw":{"skillKey":"dev-team"}}
Dev team (OpenClaw)
Introduction
What this skill is
dev_team is an OpenClaw skill guide (plain text: Markdown plus JSON schema notes). It helps you run a multi-role dev or agency “team” of specialized AI agents: instead of mixing everything in one generic chat, you get clear roles, shared project memory on disk, and traceable handoffs between agents.
The skill does not install binaries and does not create secrets. It describes folder layout, workflow, and prompt snippets — you or OpenClaw create the files (see OPENCLAW_TEAM_SETUP_GUIDE.md).
What you can do with it
- Separate roles (e.g. Lead, PM, Dev, QA, Security): each OpenClaw agent with its own workspace, persona, and scope.
- Manage customers / clients cleanly:
TEAM_ROOT/team/customers/<customer>/CONTEXT.md(repos, Shopware staging, rules). - Bundle work into tasks: under
…/tasks/<task_id>/e.g.SPEC.md→HANDOFF.md→QA_NOTES.md— the next agent knows where to continue.
$install
1-click copynpx skills add LeoYeAI/openclaw-master-skills --skill dev-teamSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.