task_queue
Skill1 starsChanged 10 months agoMITView on GitHub
Inputs: - description: Natural language task description - priority: low/normal/high/urgent (default: normal) - schedule_for: Optional datetime for delayed execution - publish_to: List of platforms to publish results (printify, shopify, youtube, twitter) - recurring: Boolean for recurring tasks - recurrence_pattern: daily/weekly/monthly (if recurring=true) Outputs: - task_id: Unique task identifier - status: Current task status - estimated_steps: Number of planned steps Inputs: - task_id: Task to plan - context: Additional context for planning Outputs: - steps: List of planned steps with dependencies…
In this repository14 other files it gives its agents.
- docs/CLAUDE.mdCLAUDE.md
- business_operationsSkill
- content_creationSkill
- data_analysisSkill
- ecommerce_automationSkill
- email_marketingSkill
- model_chainingSkill
- product_designSkill
- research_analysisSkill
- seo_optimizationSkill
- social_media_marketingSkill
- video_productionSkill
- web_automationSkill
- workflow_automationSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Add tasks to autonomous execution queue with priority and scheduling.
- Distinctive: line 50
Run queued tasks with dependency resolution and real-time progress.
- Distinctive: line 147
All integration tools: replicate, printify, shopify, etc.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Task Queue Management Skill
Overview
Autonomous task planning and execution system with priority queue, dependency management, and artifact tracking.
Capabilities
queue_task
Add tasks to autonomous execution queue with priority and scheduling.
Inputs:
- description: Natural language task description
- priority: low/normal/high/urgent (default: normal)
- schedule_for: Optional datetime for delayed execution
- publish_to: List of platforms to publish results (printify, shopify, youtube, twitter)
- recurring: Boolean for recurring tasks
- recurrence_pattern: daily/weekly/monthly (if recurring=true)
Outputs:
- task_id: Unique task identifier
- status: Current task status
- estimated_steps: Number of planned steps
Example:
queue_task(
description="Create a cyberpunk husky design, make it into a mug on Printify, and post to Instagram",
priority="high",
publish_to=["printify", "instagram"]
)plan_task
Break complex tasks into executable steps with dependencies.
Inputs:
- task_id: Task to plan
- context: Additional context for planning
Outputs:
- steps: List of planned steps with dependencies
- agents: Required agents for execution
- estimated_duration: Time estimate
execute_task
Run queued tasks with dependency resolution and real-time progress.
Inputs:
- task_id: Task to execute
- background: Run in background (default: false)
Outputs:
- status: Execution status
- artifacts: Generated content (images, videos, products)
- progress: Percentage complete
track_progress
Monitor task execution status and retrieve results.
Inputs:
- task_id: Task to track
Outputs:
- status: Current status
- current_step: Which step is executing
- artifacts: Generated artifacts so far
- errors: Any errors encountered
manage_artifacts
Collect and organize generated content from tasks.
Inputs:
- task_id: Task to get artifacts from
- artifact_type: Filter by type (image/video/text/product)
Outputs:
- artifacts: List of generated content with URLs
- metadata: Creation info and parameters
schedule_recurring
Set up daily/weekly automated tasks.
Inputs:
- task_id: Task to make recurring
- pattern: daily/weekly/monthly
- time: Execution time
- enabled: Start/stop recurring execution
Outputs:
- schedule_id: Recurring schedule identifier
- next_execution: When task will run next
batch_operations
Process multiple items in parallel.
Inputs:
- operations: List of tasks to run
- max_parallel: Maximum concurrent tasks (default: 5)
Outputs:
- batch_id: Batch operation identifier
- task_ids: Individual task IDs
priority_management
Control task execution order.
Inputs:
- task_id: Task to modify
- priority: New priority level
Outputs:
- updated: Confirmation of priority change
- queue_position: New position in queue
Workflows
Complete Product Campaign
- queue_task with product concept
- Auto-plans: design → mockup → video → product → publish
- Executes all steps with artifact tracking
- Publishes to specified platforms
Recurring Content Schedule
- schedule_recurring with content type
- Generates fresh content on schedule
- Auto-publishes to social media
- Tracks performance metrics
Dependencies
- execution_agent: For step execution
- super_planning_agent: For task decomposition
- memory_agent: For context and learning
- All integration tools: replicate, printify, shopify, etc.
Configuration
- max_queue_size: 100
- default_priority: normal
- auto_execute: true
- save_artifacts: true
- artifact_directory: data/task_artifacts/
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

