Deliver real-time stock quotes and market data with PubNub

Deliver real-time sports scores, play-by-play, and scoreboards with PubNub

Build real-time betting and casino game platforms with PubNub

Build real-time auction platforms with PubNub bidding and countdowns

Drafts, edits, and adapts content to match Guy Podjarny's tone of voice — founder of Tessl and Snyk, co-host of the AI Native Dev podcast. Use when writing Tessl blog posts, Snyk-related communications, AI Native Dev content, or when the user requests Guy's voice, style, or tone for blog posts, social media, announcements, or long-form content.

Review text for blatant signs that it was LLM generated

Mandatory review of any UI which looks for any blatant signs of it being "vibe-coded"

test

Scale PubNub applications for high-volume real-time events

Build chat applications with PubNub Chat SDK

Secure PubNub applications with Access Manager, encryption, and TLS

Create, configure, and deploy PubNub Functions 2.0 event handlers, triggers, and serverless endpoints. Use when building real-time message transformations, PubNub modules, webhook integrations, or edge data processing.

Implement real-time presence tracking with PubNub

Build real-time applications with PubNub pub/sub messaging

maceytest

Framework for AI agent evaluation in containerized environments. Use when: (1) Running agent evaluations with `harbor run` against benchmarks (SWE-Bench, Terminal-Bench, Aider Polyglot, etc.), (2) Creating custom benchmark tasks with Dockerfile, instruction.md, solution, and tests, (3) Building adapters to convert existing benchmarks to Harbor format, (4) Implementing custom agents extending BaseAgent or BaseInstalledAgent, (5) Scaling evaluations to cloud providers (Daytona, Modal, E2B), (6) Exporting traces for RL/SFT training, (7) Debugging Harbor runs or inspecting package internals.

A playbook for agents when users are clearly frustrated and losing patience.

tesing creation of new skills

Use when users express frustration about being misunderstood or when agents struggle with context

When you need to test or debug API endpoints systematically