productivity▌

Context is the complete state available to a language model at inference time. It includes everything the model can attend to when generating responses: system instructions, tool definitions, retrieved documents, message history, and tool outputs. Understanding context fundamentals is prerequisite to effective context engineering.

Combined simplification and review pipeline. This skill orchestrates two sub-skills in sequence:

Generate diverse, realistic test inputs that cover the failure space of an LLM pipeline.

Create Hummingbot-branded presentation slides in PDF format from markdown content. Features two-column layouts and Mermaid diagram rendering for technical architecture and flowcharts.

This skill helps you create and improve IP geolocation feeds in CSV format by:

Guides preparing and executing a Product Hunt launch. Product Hunt is a community-driven product discovery platform; only ~10% of submissions get featured on the homepage. Best for SaaS, developer tools, AI/ML products, and productivity software. Physical products and service businesses have limited success.

Status: Production Ready Last Updated: 2026-02-03 Dependencies: Chrome MCP tools (optional), debugger agent, code-reviewer agent

Design a binary Pass/Fail LLM-as-Judge evaluator for one specific failure mode. Each judge checks exactly one thing.

SwiftData schema migrations move your data safely when models change. Core principle SwiftData's willMigrate sees only OLD models, didMigrate sees only NEW models—you can never access both simultaneously. This limitation shapes all migration strategies.

Write changelogs and release notes that users read and care about via inference.sh CLI.