# Send Task Orchestra to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "task-orchestra",
    "name": "Task Orchestra",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/tobisamaa/task-orchestra",
    "canonicalUrl": "https://clawhub.ai/tobisamaa/task-orchestra",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/task-orchestra",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=task-orchestra",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "task-orchestra",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-04T01:21:13.106Z",
      "expiresAt": "2026-05-11T01:21:13.106Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=task-orchestra",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=task-orchestra",
        "contentDisposition": "attachment; filename=\"task-orchestra-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "task-orchestra"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/task-orchestra"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/task-orchestra",
    "downloadUrl": "https://openagent3.xyz/downloads/task-orchestra",
    "agentUrl": "https://openagent3.xyz/skills/task-orchestra/agent",
    "manifestUrl": "https://openagent3.xyz/skills/task-orchestra/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/task-orchestra/agent.md"
  }
}
```
## Documentation

### Task Orchestra

Coordinate multiple agents and tasks for complex workflows.

### When to Use

Multi-step operations requiring coordination
Parallel execution of independent tasks
Complex workflows with dependencies
Orchestrating subagents for large projects

### 1. Task Coordination

Break down complex tasks into manageable steps
Manage dependencies between tasks
Coordinate parallel execution
Handle task sequencing and scheduling

### 2. Agent Orchestration

Spawn and manage multiple subagents
Route tasks to appropriate agents
Monitor progress and handle failures
Aggregate results from multiple sources

### 3. Workflow Management

Define workflow patterns and templates
Implement error handling and recovery
Manage state and progress tracking
Coordinate handoffs between agents

### 4. Dependency Resolution

Analyze task dependencies
Create execution order
Handle conditional execution
Manage resource conflicts

### 1. Sequential Execution

Task A → Task B → Task C

### 2. Parallel Execution

Task A, Task B, Task C → Aggregate

### 3. Pipeline Processing

Input → Task A → Task B → Task C → Output

### 4. Supervisor Pattern

Coordinator → Multiple Subagents → Results

### 5. Event-Driven Processing

Event → Trigger → Response → Next Event

### Quick Actions

orchestrate [workflow] - Execute complex workflow
parallel [tasks] - Run tasks in parallel
pipeline [steps] - Chain tasks in sequence
supervise [agents] - Manage multiple agents
dependencies [tasks] - Analyze and resolve dependencies

### Usage Examples

"Orchestrate a complete research project with multiple agents"
"Run these tasks in parallel and combine results"
"Create a pipeline for content creation from research to publication"
"Supervise a team of agents working on different aspects"
"Analyze dependencies and create execution order"

### Research Project

1. Research Topic → Research Agent
2. Data Collection → Data Agent
3. Analysis → Analysis Agent
4. Report Generation → Writing Agent
5. Review → QA Agent

### Content Creation

1. Topic Research → Research Agent
2. Outline Creation → Writing Agent
3. Draft Writing → Writing Agent
4. Editing → Editing Agent
5. Publication → Publishing Agent

### Software Development

1. Requirements → Analysis Agent
2. Design → Design Agent
3. Implementation → Coding Agent
4. Testing → QA Agent
5. Deployment → Deployment Agent

### Spawning Agents

sessions_spawn({ task: "specific task", label: "agent-name", mode: "run" })

### Monitoring Progress

subagents list

### Handling Failures

subagents kill [agent-id]
subagents steer [agent-id] "new instructions"

### Types of Dependencies

Data Dependencies: Task B needs output from Task A
Resource Dependencies: Tasks sharing same resources
Order Dependencies: Tasks must run in specific order
Conditional Dependencies: Task runs only if condition met

### Resolution Process

1. Identify all dependencies
2. Create dependency graph
3. Find topological sort
4. Execute in dependency order
5. Handle conflicts and cycles

### Common Failure Scenarios

Agent Failure: Subagent crashes or times out
Dependency Failure: Required task fails
Resource Conflict: Multiple agents need same resource
Network Issues: API calls fail or timeout

### Recovery Strategies

Retry: Attempt failed task again
Alternative: Use different approach or agent
Skip: Continue without failed task
Rollback: Undo previous steps

### Progress Tracking

Track completed tasks
Monitor current execution
Record task results
Maintain workflow state

### Checkpointing

Save progress at key points
Enable restart from checkpoints
Maintain consistency across failures

### Parent → Child

/sessions_send [agent-id] "instructions"

### Child → Parent

Auto-announce results
Reply with findings
Report errors and status

### Agent → Agent

Share data through files
Coordinate via shared state
Trigger other agents

### Parallel Execution

Identify independent tasks
Run in parallel when possible
Aggregate results efficiently

### Resource Management

Monitor agent resource usage
Balance load across agents
Avoid resource conflicts

### Efficiency Metrics

Task completion time
Resource utilization
Error rates
Success rates

### Agent Limits

Max 10 concurrent subagents
Max 2 levels of nesting
10-minute timeout per agent
Automatic cleanup

### Data Integrity

Validate task inputs/outputs
Maintain consistency
Handle partial failures
Ensure atomic operations

### 1. Hierarchical Orchestration

Main Coordinator → Team Coordinators → Individual Agents

### 2. Dynamic Work Allocation

Assign tasks based on agent capabilities
Reassign if agent fails
Balance load dynamically

### 3. Event-Driven Workflows

Event → Trigger → Agent → Result → Next Event

### 4. Adaptive Planning

Plan → Execute → Monitor → Adjust → Repeat

### Self-Evolution

Use for complex self-improvement tasks
Coordinate multiple evolution agents
Manage long-term capability building

### Analysis Skills

Orchestrate research projects
Coordinate data analysis
Manage multi-step investigations

### Content Creation

Coordinate content production pipelines
Manage multi-agent content creation
Orchestrate publication workflows

### Common Commands

# List running agents
subagents list

# Kill failed agent
subagents kill [id]

# Send instructions
sessions_send [agent-id] "message"

# Spawn new agent
sessions_spawn({ task: "task", label: "name", mode: "run" })

### Workflow Examples

# Research project
orchestrate "research-project" with agents: research, analysis, writing

# Content pipeline
pipeline "content-creation" with steps: research, outline, draft, edit, publish

# Software development
supervise "dev-team" with agents: analysis, design, coding, testing, deployment

### Best Practices

Start Simple: Begin with sequential execution
Add Parallelism: Identify independent tasks
Handle Failures: Implement robust error handling
Monitor Progress: Track execution and results
Optimize Performance: Balance load and resources

### Success Metrics

Task completion rate
Execution time efficiency
Resource utilization
Error recovery effectiveness
Overall workflow success

Remember: Good orchestration makes complex tasks manageable and reliable.
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: tobisamaa
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-04T01:21:13.106Z
- Expires at: 2026-05-11T01:21:13.106Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/task-orchestra)
- [Send to Agent page](https://openagent3.xyz/skills/task-orchestra/agent)
- [JSON manifest](https://openagent3.xyz/skills/task-orchestra/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/task-orchestra/agent.md)
- [Download page](https://openagent3.xyz/downloads/task-orchestra)