burst-supervisor

Dispatch work items to polecat workers across recoverable bursts.

3|4|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/nicsuzor/academicOps --skill burst-supervisor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: burst-supervisor
Source: https://github.com/nicsuzor/academicOps/tree/main/aops-core/skills/burst-supervisor
Command: npx skills add https://github.com/nicsuzor/academicOps --skill burst-supervisor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill manages long-running, iterative workflows by dispatching work items to workers in batches, ensuring that progress is saved and can be resumed even after interruptions.

Core Features & Use Cases

  • Stateful Supervision: Maintains and recovers state across multiple invocations, crucial for long-running tasks.
  • Batch Dispatch: Distributes work items to 'polecat' workers in manageable bursts.
  • Automated Evaluation: Semantically judges worker output against defined criteria, deciding to accept, revise, or fail tasks.
  • Use Case: Auditing a large set of API specifications. The supervisor dispatches each spec to a worker for review, evaluates the output, and either accepts it, sends it back for revision with specific feedback, or escalates it if it's fundamentally flawed or retries are exhausted.

Quick Start

Initialize a new supervisor for a spec audit workflow by running: /burst-supervisor init spec-audit

Frequently Asked Questions about burst-supervisor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage long-running batch processing workflows with state recovery?

Long-running iterative workflows are managed by dispatching work items to polecat workers in batches and maintaining recoverable state, ensuring progress is saved and resumable after interruptions. The supervisor evaluates output semantically to accept, revise, or fail tasks.

How do I automate document review and data extraction across multiple bursts?

Automated document review and data extraction are handled by dispatching items to workers in manageable bursts, semantically evaluating their output against defined criteria, and routing results for acceptance, revision, or failure based on the evaluation.

What is iterative workflow supervision and when do I need it for automation tasks?

Iterative workflow supervision is the process of dispatching batch processing tasks to workers and evaluating their output across multiple bursts. It is needed for long-running automation tasks requiring state management, automated evaluation, and state recovery after interruptions.

Can I use a supervisor to audit a large set of API specifications automatically?

Yes, you can audit a large set of API specifications by dispatching each spec to a worker for review, evaluating the output against defined criteria, and then accepting, sending back for revision, or escalating fundamentally flawed tasks when retries are exhausted.

How do I start an iterative workflow supervisor for a spec audit?

To start an iterative workflow supervisor for a spec audit, initialize a new supervisor instance using the init command with your workflow name, which sets up the environment for dispatching and evaluating work items in bursts.

What happens when a worker's output fails the semantic evaluation in a batch workflow?

When a worker's output fails semantic evaluation against defined criteria, the supervisor sends the task back for revision with specific feedback, or escalates it if the output is fundamentally flawed or retries are exhausted.