team-projects
Multi-agent project management with task boards, @-mention routing, WBS, and orchestrated team collaboration. Includes a Control UI plugin tab with project dashboard and a right-edge Team Chat drawer for live activity. Enables a coordinator agent to plan projects, break down work into phases and tasks, assign to specialist agents, dispatch via sessions_spawn, and track progress to completion. Use when: (1) managing work across multiple OpenClaw agents, (2) creating project plans with work breakdown structures, (3) assigning and tracking tasks across agents, (4) coordinating multi-agent workflows with dependencies, (5) running team-based projects with progress tracking.
What this skill does
# Team Projects ๐
Multi-agent project management for OpenClaw. Run agent teams that plan, assign, execute, and track work together. Includes a **Control UI plugin tab** for visual project tracking and a **right-edge Team Chat drawer** for live agent activity.
## Overview
This skill enables a **coordinator agent** to manage projects across multiple specialist agents:
```
User โ Coordinator (Koda) โ dispatches tasks via sessions_spawn
โโโ @researcher โ web research, data analysis
โโโ @coder โ writing code, building features
โโโ @writer โ copy, documentation, content
โโโ ... any configured agent
```
Each agent works independently with their own tools and workspace. The coordinator tracks progress, manages dependencies, and advances the project.
## UI Components
### 1. Projects Tab (sidebar)
A full project dashboard registered as a plugin tab in the Control sidebar under the "Control" group. Shows project cards, task boards with phase sections, team overview, and progress stats.
### 2. Team Chat Drawer (right edge)
A slide-out panel accessible from a vertical "Team" tab fixed to the right edge of the screen. Shows:
- Live agent activity feed (sub-agent sessions, messages)
- Project progress bar
- Task overview (collapsible)
- Quick message input to send commands
## Installation
### Step 1: Config Prerequisites
Add to `openclaw.json`:
```json
{
"tools": {
"agentToAgent": {
"enabled": true,
"allow": ["*"]
}
}
}
```
Add `subagents.allowAgents` to the **coordinator agent's list entry** (NOT on `agents.defaults`):
```json
{
"agents": {
"list": [
{
"id": "main",
"default": true,
"name": "Koda",
"subagents": {
"allowAgents": ["*"]
}
}
]
}
}
```
> โ ๏ธ **Critical:** `allowAgents` must be on the agent's own entry in `agents.list`. Setting it on `agents.defaults.subagents` does NOT work. The code reads `resolveAgentConfig(cfg, requesterAgentId)?.subagents?.allowAgents` which resolves the per-agent config, not defaults.
### Step 2: Gateway Plugin Installation (for Projects tab)
The Projects tab requires installing a gateway plugin. This involves 4 registration points in the OpenClaw source:
#### 2a. Plugin SDK entry
Create `src/plugin-sdk/team-projects.ts`:
```typescript
export { emptyPluginConfigSchema } from "../plugins/config-schema.js";
export type {
OpenClawPluginApi,
PluginViewRegistration,
} from "../plugins/types.js";
```
#### 2b. Plugin extension
Create `extensions/team-projects/openclaw.plugin.json`:
```json
{
"id": "team-projects",
"configSchema": {
"type": "object",
"additionalProperties": false,
"properties": {}
}
}
```
Create `extensions/team-projects/index.ts` โ see `gateway-plugin/index.ts`.
#### 2c. Register in build pipeline (4 files)
**`tsdown.config.ts`** โ Add `"team-projects"` to the `pluginSdkEntrypoints` array.
**`src/plugins/loader.ts`** โ Add to the `pluginSdkScopedAliasEntries` array:
```typescript
{
subpath: "team-projects",
srcFile: "team-projects.ts",
distFile: "team-projects.js",
},
```
**`scripts/write-plugin-sdk-entry-dts.ts`** โ Add `"team-projects"` to the entrypoints array.
**`package.json`** โ Add to the exports map:
```json
"./plugin-sdk/team-projects": {
"types": "./dist/plugin-sdk/team-projects.d.ts",
"default": "./dist/plugin-sdk/team-projects.js"
},
```
#### 2d. Enable in config
```json
{
"plugins": {
"allow": ["telegram", "discord", "team-projects"],
"entries": {
"team-projects": {
"enabled": true
}
}
}
}
```
### Step 3: UI View Installation
#### 3a. Team Projects view
Copy `gateway-plugin/team-projects-view.ts` to `ui/src/ui/views/team-projects.ts`.
#### 3b. Team Chat Drawer
Copy `gateway-plugin/team-chat-drawer.ts` to `ui/src/ui/views/team-chat-drawer.ts`.
> โ ๏ธ **Critical: No Shadow DOM** โ The OpenClaw app uses `createRenderRoot() { return this; }`, so Lit `css` tagged templates are NOT applied. All styles must be embedded as inline `<style>` tags in the rendered HTML. The team-chat-drawer uses an inline `<style>` block inside `renderTeamChatEdgeTab()` so styles are present even when the drawer is closed.
#### 3c. Wire into app-render.ts
See `gateway-plugin/app-render-patch.ts` for the integration points:
1. Import `renderTeamChatDrawer` and `renderTeamChatEdgeTab` from `./views/team-chat-drawer.ts`
2. Before `</main>`, add `${renderPluginTabContent(state)}`
3. After `</main>`, add the edge tab and drawer renders
4. Add the `renderPluginTabContent()` function
#### 3d. Wire into app-gateway.ts
See `gateway-plugin/app-gateway-patch.ts` for the integration points:
1. Import `uiPluginRegistry` from `./plugins/registry.ts`
2. Import `renderTeamProjects` from `./views/team-projects.ts`
3. In `onHello`, after `applySnapshot()`, call `registerTeamProjectsPlugin()`
4. Add the `registerTeamProjectsPlugin()` function
#### 3e. Add view state fields
In `ui/src/ui/app-view-state.ts`, add to `AppViewState`:
```typescript
teamChatOpen: boolean;
teamChatProject: unknown;
teamChatSessions: unknown[];
teamChatActivity: unknown[];
teamChatLoading: boolean;
teamChatInput: string;
teamChatTasksCollapsed: boolean;
```
In `ui/src/ui/app-settings.ts`, add `teamChatOpen?: boolean` to `SettingsHost` type, and add defensive cleanup in `applyTabSelection()`:
```typescript
} else if (host.teamChatOpen) {
host.teamChatOpen = false;
}
```
### Step 4: Build & Restart
```bash
cd ~/openclaw
pnpm build # Backend (gateway + plugin SDK)
pnpm ui:build # Control UI
openclaw gateway restart
```
Hard-refresh the browser (Ctrl+Shift+R) to load the new UI assets.
## Usage
### Creating a Project
Tell the coordinator agent what you want to build. It will:
1. Create the project with appropriate phases
2. Break down work into tasks
3. Assign tasks to agents based on capabilities
4. Dispatch ready tasks
**Example prompt:**
> "Create a team project to redesign our company website. @researcher should analyze competitors, @writer should draft copy, and @coder should build it in React. Priority: launch in 2 weeks."
### The Coordinator's Workflow
The coordinator uses CLI tools to manage the project board:
```bash
# Create a project
node {{SKILL_DIR}}/scripts/project-store.js create-project \
--name "Website Redesign" \
--description "Full redesign of company website" \
--coordinator main \
--agents "researcher,writer,coder"
# Add phases (ordered)
node {{SKILL_DIR}}/scripts/project-store.js add-phase \
--project PROJECT_ID --name "Research" --description "Competitive analysis"
# Add tasks with assignments and dependencies
node {{SKILL_DIR}}/scripts/project-store.js add-task \
--project PROJECT_ID --phase PHASE_ID \
--title "Analyze top 5 competitors" \
--description "Research competitor websites..." \
--assignee researcher --priority high
node {{SKILL_DIR}}/scripts/project-store.js add-task \
--project PROJECT_ID --phase PHASE_ID \
--title "Write homepage hero copy" \
--assignee writer --priority high \
--dependsOn "task_abc123"
```
### Dispatching Tasks
The orchestrator identifies ready tasks (dependencies met, not yet dispatched):
```bash
# See what's ready to dispatch
node {{SKILL_DIR}}/scripts/orchestrator.js plan PROJECT_ID
```
Then dispatch via OpenClaw's native `sessions_spawn`:
```
sessions_spawn(
agentId: "researcher",
task: "Research the top 5 competitors in the AI SaaS space...",
label: "task_abc123"
)
```
### Agent Communication
Agents can communicate using @-mentions:
- **@agentId** โ Direct message to an agent (routed via `sessions_send`)
- **@all** / **@team** โ Broadcast to all project agents
- **#task_id** โ Reference a task
- **TASK_COMPLETE: #task_id** โ Signal task completion
- **TASK_BLOCKED: #task_id** โ Signal a blocker
### Tracking Progress
```bash
# View projecRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context โ no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes โ information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development โ guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.