Observability — Observability install Observability, Personal-AI, community, Observability install, ide skills, real-time monitoring tools, PAI multi-agent monitoring, WebSocket streaming for AI agents, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for AI Agents needing real-time monitoring and performance tracking with WebSocket streaming. Observability is a skill that enables real-time monitoring of PAI multi-agent activity, providing insights into agent performance and behavior through WebSocket streaming.

Features

Real-time monitoring of PAI multi-agent activity with WebSocket streaming
Dashboard UI accessible at http://localhost:5172
Server API available at http://localhost:5172 for programmatic access
Manage.sh script for easy startup, shutdown, and restart of the server and dashboard
Status checking capability to monitor the skill's health and performance

# Core Topics

blackpwnguin blackpwnguin
[0]
[0]
Updated: 3/8/2026

Agent Capability Analysis

The Observability skill by blackpwnguin is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for Observability install, real-time monitoring tools, PAI multi-agent monitoring.

Ideal Agent Persona

Perfect for AI Agents needing real-time monitoring and performance tracking with WebSocket streaming.

Core Value

Empowers agents to track performance in real-time using WebSocket streaming, providing a dashboard UI and server API for easy access and monitoring of PAI multi-agent activity.

Capabilities Granted for Observability

Monitoring agent performance in real-time
Debugging PAI multi-agent interactions
Analyzing agent activity with WebSocket streaming

! Prerequisites & Limits

  • Requires local server setup
  • Limited to PAI multi-agent activity monitoring
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

Observability

Install Observability, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Agent Observability Dashboard

Real-time monitoring of PAI multi-agent activity with WebSocket streaming.

Quick Start

bash
1# Start server and dashboard 2~/.claude/skills/observability/manage.sh start 3 4# Stop everything 5~/.claude/skills/observability/manage.sh stop 6 7# Restart both 8~/.claude/skills/observability/manage.sh restart 9 10# Check status 11~/.claude/skills/observability/manage.sh status

Access Points

What It Monitors

Real-Time Tracking

  • Agent session starts/ends
  • Tool calls across all agents
  • Hook event execution
  • Session timelines and traces
  • WebSocket live updates

Data Sources

  • Primary: ~/.claude/history/raw-outputs/YYYY-MM/YYYY-MM-DD_all-events.jsonl
  • Format: JSONL with structured event data
  • Hooks: Events logged automatically by PAI hook system

Architecture

Stack:

  • Server: Bun + Express + TypeScript
  • Client: Vite + Vue + TypeScript
  • Storage: In-memory streaming (no database)
  • Protocol: WebSocket for real-time updates

Key Features:

  • Watch filesystem with automatic reload
  • Tail-follow for today's event file
  • Cache events in-memory
  • Broadcast WebSocket to all clients
  • No persistence (fresh start each launch)

When to Activate This Skill

  • "Start observability"
  • "Stop the dashboard"
  • "Restart observability"
  • "Monitor agents"
  • "Show agent activity"
  • "Observability status"
  • "Debug agent workflow"

Examples

Example 1: Start monitoring agents

User: "start observability"
→ Launches server on port 4000
→ Starts dashboard on port 5172
→ Opens browser to live agent activity view

Example 2: Debug a stuck workflow

User: "something's weird with my agents, show me what's happening"
→ Opens observability dashboard
→ Shows real-time tool calls across all agents
→ Reveals which agent is blocked or looping

Example 3: Check dashboard status

User: "is observability running?"
→ Runs manage.sh status
→ Reports server and client running state
→ Shows access URLs if active

Development

Server

bash
1cd ~/.claude/skills/observability/apps/server 2bun install 3bun run dev

Client

bash
1cd ~/.claude/skills/observability/apps/client 2bun install 3bun run dev

Troubleshooting

Dashboard not loading

  • Check server is running: curl http://localhost:4000/health
  • Check client is running: curl http://localhost:5172
  • Restart: ./manage.sh restart

No events showing

  • Verify events file exists: ~/.claude/history/raw-outputs/YYYY-MM/YYYY-MM-DD_all-events.jsonl
  • Check hooks are configured in ~/.claude/settings.json
  • Try triggering an event (use any tool or agent)

Port conflicts

  • Server uses: 4000
  • Client uses: 5172
  • Check nothing else is using these ports

Files

~/.claude/skills/observability/
├── SKILL.md                          # This file
├── manage.sh                         # Control script
├── apps/
│   ├── server/                       # Backend (Bun + Express)
│   │   ├── src/index.ts
│   │   └── package.json
│   └── client/                       # Frontend (Vite + Vue)
│       ├── src/
│       ├── package.json
│       └── vite.config.ts
└── scripts/                          # Utility scripts

Key Principles

  1. Real-time - Events stream as they happen
  2. Ephemeral - No persistence, in-memory only
  3. Simple - No database, no configuration
  4. Transparent - Full visibility into agent activity
  5. Unobtrusive - Doesn't interfere with PAI operation

Hook Integration

For the observability dashboard to receive events, configure your PAI hooks to log to: ~/.claude/history/raw-outputs/YYYY-MM/YYYY-MM-DD_all-events.jsonl

The capture-all-events.ts hook in ~/.claude/hooks/ handles this automatically.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is Observability?

Perfect for AI Agents needing real-time monitoring and performance tracking with WebSocket streaming. Observability is a skill that enables real-time monitoring of PAI multi-agent activity, providing insights into agent performance and behavior through WebSocket streaming.

How do I install Observability?

Run the command: npx killer-skills add blackpwnguin/Personal-AI. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for Observability?

Key use cases include: Monitoring agent performance in real-time, Debugging PAI multi-agent interactions, Analyzing agent activity with WebSocket streaming.

Which IDEs are compatible with Observability?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for Observability?

Requires local server setup. Limited to PAI multi-agent activity monitoring.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add blackpwnguin/Personal-AI. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use Observability immediately in the current project.

Related Skills

Looking for an alternative to Observability or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI