p9

Replace blocking CI waits with an event-driven control loop managing watchers and task-queue draining.

3|2|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/broomva/skills --skill p9-broomva
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: p9
Source: https://github.com/broomva/skills/tree/main/skills/orchestration/p9
Command: npx skills add https://github.com/broomva/skills --skill p9-broomva

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill eliminates the productivity drain caused by waiting for CI checks, deployments, or long-running builds to finish. Instead of watching a spinner or manually polling, it automates the wait and redirects your agent to perform other high-priority tasks.

Core Features & Use Cases

  • Productive Wait-Queue: Automatically pulls work from your task list, memory, or knowledge graph while waiting for external processes.
  • Self-Healing CI: Classifies common CI failures (lint, format, codegen) and attempts automated fixes, reducing the need for human intervention.
  • Parallel Safety: Manages concurrent agent sessions using unique session IDs to ensure state isolation and prevent race conditions.

Quick Start

Invoke the p9 skill to watch your current pull request and automatically handle CI checks and potential self-healing while you focus on other tasks.

Frequently Asked Questions about p9

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

FAQPage Schema
How do I stop blocking CI waits from interrupting my workflow?

To stop blocking CI waits, you can use an event-driven control loop that automates pull request monitoring and redirects your agent to perform other queued tasks while checks run in the background.

What is the best way to automate failure recovery for long-running deployments?

Automated failure recovery for long-running deployments is best handled by classifying common CI failures like lint or format errors and applying automated fixes without manual intervention.

Can I run concurrent agent sessions without causing race conditions?

Yes, you can run concurrent agent sessions without race conditions by managing state isolation through unique session IDs that ensure parallel safety during background task execution.

How does an event-driven control loop manage background watchers?

An event-driven control loop manages background watchers by replacing manual polling with an automated task-queue draining mechanism, ensuring state persistence while monitoring external processes.

Do I need a specific task list to drain background work during CI checks?

No, you do not need a specific task list format; the system automatically pulls work from your existing task list, memory, or knowledge graph to maintain productivity during CI waits.