AI Engineering

IP Portfolio manages intellectual property portfolios by analyzing status, mapping patents, trademarks, and copyrights, and producing renewal, licensing, and protection strategy reports. Use it for portfolio reviews, renewal schedules, and IP strategy planning.

A multi-agent system that orchestrates the full newsletter creation pipeline: curation, copywriting, A/B testing, editing, and quality review. Use for automated newsletter generation with a team of AI agents.

Patent Valuation provides frameworks for estimating patent value using cost, market, and income methods. Use it for IP valuation, royalty calculations, and patent strength assessment; infringement analysis and litigation work are out of scope.

Covers 12 quest archetypes, the 3-layer quest structure (surface, mechanical, narrative), reward psychology (DRIP model), and difficulty curve design for game quests. Ideal for AI-assisted quest design and game narrative planning.

Book to Skill Converter turns PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, and MOBI/AZW files into structured agent skills by extracting frameworks, mental models, principles, techniques, and anti-patterns. Use it to study a document with Copilot CLI, Amp, or Claude Code, apply an author's frameworks while working, or build a reusable knowledge base from a file.

Skill Creator creates new skills, modifies and improves existing skills, and measures skill performance. Use it when you want to create a skill from scratch, edit or optimize an existing skill, run evals, benchmark variance, or improve descriptions for triggering accuracy.

Skillpack Creator turns a completed task into a reusable local SkillPack with manifest, skills, prompts, scripts, and an optional zip. Use it when you want to convert a one-off research, coding, analysis, or content workflow into a distributable pack.

Agent Context Audit audits a repository's agent context—CLAUDE.md files, codebase docs, skills, and tool/MCP designs—against Anthropic's Claude 5 context-engineering guidance to find overconstraint, conflicts, redundancy, stale facts, and missing unknown knowns. It produces a scored findings report with concrete rewrites and applies approved fixes, used when someone says 'audit my CLAUDE.md' or

Codebase Harness Setup prepares a codebase for agent-driven development by making it legible, executable, and verifiable through structured docs, a reproducible dev stack, and a verify-before-ship loop. Use when onboarding a new or unfamiliar codebase to agent-driven development.

GPT Image 2 PPT generates slide images with OpenAI's gpt-image-2 from a markdown outline and a style or a .pptx template, then packages them into a 16:9 PowerPoint file. Use it for presentations, pitch decks, and courseware.

New Loop spins up a new loop (domain) in a file-based knowledge base, bootstraps the substrate if missing, scaffolds the loop README, and does one real test run recorded in the Timeline and LOG.md. Use when setting up a recurring job or workstream the agent should own.

Open Agent Teams delegates tasks to any CLI agent (Claude, Codex, Aider, etc.) running in a detached tmux session, using file sentinels for race-safe completion signaling and multi-turn iteration. Use it when delegating work to a non-Claude CLI agent or running executor work in an observable background terminal.