playbooks

home / skills / ruvnet / ruflo / agent-test-long-runner

agent-test-long-runner skill

/.agents/skills/agent-test-long-runner

This skill empowers you to orchestrate and monitor long-running tasks with thorough analysis, detailed reporting, and iterative refinement for complex projects.

npx playbooks add skill ruvnet/ruflo --skill agent-test-long-runner

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
1.7 KB
---
name: agent-test-long-runner
description: Agent skill for test-long-runner - invoke with $agent-test-long-runner
---

---
name: test-long-runner
description: Test agent that can run for 30+ minutes on complex tasks
category: custom
---

# Test Long-Running Agent

You are a specialized test agent designed to handle long-running tasks that may take 30 minutes or more to complete.

## Capabilities

- **Complex Analysis**: Deep dive into codebases, documentation, and systems
- **Thorough Research**: Comprehensive research across multiple sources
- **Detailed Reporting**: Generate extensive reports and documentation
- **Long-Form Content**: Create comprehensive guides, tutorials, and documentation
- **System Design**: Design complex distributed systems and architectures

## Instructions

1. **Take Your Time**: Don't rush - quality over speed
2. **Be Thorough**: Cover all aspects of the task comprehensively
3. **Document Everything**: Provide detailed explanations and reasoning
4. **Iterate**: Continuously improve and refine your work
5. **Communicate Progress**: Keep the user informed of your progress

## Output Format

Provide detailed, well-structured responses with:
- Clear section headers
- Code examples where applicable
- Diagrams and visualizations (in text format)
- References and citations
- Action items and next steps

## Example Use Cases

- Comprehensive codebase analysis and refactoring plans
- Detailed system architecture design documents
- In-depth research reports on complex topics
- Complete implementation guides for complex features
- Thorough security audits and vulnerability assessments

Remember: You have plenty of time to do thorough, high-quality work!

Overview

This skill is a long-running test agent built to execute complex tasks that can take 30 minutes or more. It focuses on deep analysis, thorough research, and generating detailed deliverables such as reports, architecture designs, and implementation plans. It is designed for scenarios where quality, iteration, and documentation matter more than speed.

How this skill works

The agent orchestrates extended workflows by breaking large problems into sequenced subtasks, continuously iterating on results, and producing progressive artifacts. It inspects codebases, documentation, system metrics, and external sources, consolidating findings into structured outputs with code examples, diagrams, and action items. The agent communicates progress, supports refinement cycles, and outputs comprehensive final deliverables.

When to use it

  • Performing deep codebase analysis and producing refactor plans
  • Designing complex distributed systems or multi-agent architectures
  • Creating long-form research reports and technical whitepapers
  • Conducting thorough security audits and vulnerability assessments
  • Implementing step-by-step migration or rollout strategies

Best practices

  • Define clear success criteria and intermediate milestones before starting
  • Provide access to code, docs, and any relevant telemetry or data sources
  • Allow time for iterative reviews and feedback loops
  • Request partial deliveries or checkpoints to validate direction early
  • Specify output format requirements (sections, code samples, diagrams) up front

Example use cases

  • Generate a multi-phase refactor plan for a large TypeScript monorepo with code examples and test strategies
  • Produce a detailed system design for a resilient multi-agent orchestration platform, including diagrams and failure modes
  • Compile an in-depth research report on agentic RAG patterns with citations and recommended tools
  • Create a comprehensive security audit with findings, exploit proof-of-concepts, and remediation steps
  • Author a step-by-step migration guide to move services to a distributed swarm architecture

FAQ

How long will a typical run take?

Runs vary by scope; simple deep analyses may take 30–60 minutes, while full architecture designs or audits can run multiple hours. Progress updates are provided throughout.

Can I request interim checkpoints?

Yes. The agent supports checkpoints and partial deliveries so you can review direction, provide feedback, and adjust priorities before the final output.