← Back to Skills Marketplace
sunlearndev

DevTeam Command

by SunlearnDev · GitHub ↗ · v1.2.0
cross-platform ✓ Security Clean
289
Downloads
0
Stars
1
Active Installs
3
Versions
Install in OpenClaw
/install devteam-command
Description
Runs a full Dev Team pipeline from planning to release for any coding task, producing plans, code, tests, fixes, and release notes.
README (SKILL.md)

DevTeam Command - Reusable Pipeline

🚀 Quick Start

Call Anytime

// Import skill
import { spawnDevTeam } from '@/skills/devteam-command'

// Spawn full pipeline
await spawnDevTeam('Your task description here')

Or Use Command

# Full pipeline
/devteam "Fix UI rendering issue"

# Specific agent
/devteam planner "Analyze requirements"
/devteam coder "Implement feature"
/devteam tester "Write tests"

📋 Pipeline Steps

Step Agent Time Output
1 Planner 10 min PLAN.md
2 PM 15 min TASKS.md
3 Coder 60 min Code
4 Tester 20 min BUGS.md
5 Fixer 30 min Fixed Code
6 Reporter 10 min RELEASE.md

Total: ~2.5 hours


🎯 Usage Examples

Example 1: Bug Fix

await spawnDevTeam(`
  Bug: Homepage không hiển thị comics
  
  Details:
  - API: 200 OK, 24 items
  - UI: Không render
  - Error: React #418
`)

Example 2: New Feature

await spawnDevTeam(`
  Add search functionality:
  - Search input component
  - API: GET /api/search?keyword=
  - Search results page
  - Debounce input
`)

Example 3: Testing

await spawnDevTeam(`
  Write E2E tests:
  - Test homepage loading
  - Test category navigation
  - Test comic detail
  - Target: All critical paths
`)

🔧 Configuration

Models

const MODELS = {
  planner: 'bailian/qwen3-coder-plus',
  pm: 'bailian/qwen3.5-plus',
  coder: 'bailian/qwen3-coder-plus',
  tester: 'bailian/qwen3.5-plus',
  fixer: 'bailian/qwen3-coder-plus',
  reporter: 'bailian/kimi-k2.5',
}

Timeouts

const TIMEOUTS = {
  planner: 600000,      // 10 minutes
  pm: 900000,           // 15 minutes
  coder: 3600000,       // 60 minutes
  tester: 1200000,      // 20 minutes
  fixer: 1800000,       // 30 minutes
  reporter: 600000,     // 10 minutes
}

📊 Output Files

After pipeline completes:

docs/
├── PLAN.md          # Requirements & plan
├── TASKS.md         # Detailed tasks
├── BUGS.md          # Bug reports (if any)
└── RELEASE.md       # Release notes

💡 Best Practices

✅ Do

  • Clear, detailed task description
  • Include acceptance criteria
  • Provide context and links
  • Wait for completion before next task

❌ Don't

  • Vague descriptions
  • Multiple unrelated tasks
  • Skip testing phase
  • Ignore bug reports

🔄 Reuse Anytime

Skill is reusable! Call anytime:

// Task 1
await spawnDevTeam('Fix bug A')

// Task 2 (later)
await spawnDevTeam('Add feature B')

// Task 3 (anytime)
await spawnDevTeam('Write tests for C')

Skill Version: 1.0.0 Created: 2026-03-06 Reusable: Yes

Usage Guidance
This skill appears to do what it says (spawn a multi-agent DevTeam pipeline) and does not request credentials or install anything. Before installing or using it: 1) Test on non-sensitive tasks — the skill spawns subagents that will receive your task text and could send that content to whatever models the platform routes to. 2) Confirm your platform has access to the listed models (the code references 'bailian/...' models) or update the model names to ones you trust. 3) Be aware getAgentOutput is a stub (returns null), so automatic retrieval of BUGS.md is not implemented; outputs may not be written to docs/ unless your platform's subagents do so. 4) If you plan to run private or proprietary tasks, avoid passing secrets in taskDescription since subagents will process the text. If you need higher assurance, ask the author for a complete implementation and clarity on model/provider usage before enabling on production agents.
Capability Analysis
Type: OpenClaw Skill Name: devteam-command Version: 1.2.0 The skill implements a multi-agent development pipeline (Planner, PM, Coder, Tester, etc.) designed to automate software development tasks. The code in index.ts uses standard OpenClaw session management functions (sessions_spawn, subagents) to orchestrate these agents, and the instructions in SKILL.md are entirely consistent with this purpose without any signs of malicious intent or unauthorized data access.
Capability Assessment
Purpose & Capability
Name/description (run a Planner→PM→Coder→Tester→Fixer→Reporter pipeline) matches the code: spawnDevTeam spawns labeled subagents and waits for them. The pipeline, timeouts, and outputs described are represented in code.
Instruction Scope
SKILL.md shows how to call spawnDevTeam and lists CLI usage and output files. The code implements spawn functions that call platform APIs (sessions_spawn, subagents) and polls for completion. However: getAgentOutput() is a stub that always returns null (so BUGS.md retrieval is not implemented), and the README-style CLI examples (e.g. /devteam) are not backed by any install or binary. The skill will spawn subagents that run for long timeouts — those subagents will receive the task text and can perform arbitrary work within the platform.
Install Mechanism
No install spec; instruction-only plus a single TypeScript file. Nothing is downloaded or written to disk by an installer — lowest install risk.
Credentials
The skill requests no environment variables or credentials. It does reference explicit model names (e.g., 'bailian/qwen3-coder-plus', 'bailian/kimi-k2.5') which may imply use of external model providers or platform model routing; no credentials or config for those providers are declared. This is not necessarily malicious but is an implementation ambiguity you should verify (does your platform have access to these models?).
Persistence & Privilege
always is false and the skill does not request to alter other skills or persist configuration. It spawns subagents (normal behavior for a pipeline skill) but does not request elevated platform privileges in the code.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install devteam-command
  3. After installation, invoke the skill by name or use /devteam-command
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
Added tracking, reporting, memory system, rules & constraints, task checklist, real-time monitoring
v1.1.0
Use user's default models + added detailed setup guide
v1.0.0
Initial release - Full Dev Team pipeline with configurable models
Metadata
Slug devteam-command
Version 1.2.0
License
All-time Installs 1
Active Installs 1
Total Versions 3
Frequently Asked Questions

What is DevTeam Command?

Runs a full Dev Team pipeline from planning to release for any coding task, producing plans, code, tests, fixes, and release notes. It is an AI Agent Skill for Claude Code / OpenClaw, with 289 downloads so far.

How do I install DevTeam Command?

Run "/install devteam-command" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is DevTeam Command free?

Yes, DevTeam Command is completely free (open-source). You can download, install and use it at no cost.

Which platforms does DevTeam Command support?

DevTeam Command is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created DevTeam Command?

It is built and maintained by SunlearnDev (@sunlearndev); the current version is v1.2.0.

💬 Comments