How to create Crestron Home Extension drivers which provide custom user interfaces and device control. This uses the Entity Model (v2) Crestron Device Driver SDK. Also includes references and domain knowledge for creating and working with these drivers. Use this whenever the user is building or editing a Crestron Home extension driver, its UiDefinition.xml, tile/room-page UI, or Entity Model v2 properties/commands — even if they don't say the word extension.
Evidence-gated SDLC for Claude Code, installed as configuration (no app code, no Docker): install CLAUDE.md + .claude/ (rules, the profile's agents/skills, hooks, artifact templates) + optional .mcp.json, then run /sdlc to drive spec → review → build → test → security → ship through profile-aware quality gates with an evidence-hashed gate ledger, working memory, and a self-improving learnings loop.
Classical engineering TRIZ: engineering and physical contradictions with the 40 Inventive Principles, Function Analysis, Trimming, the 76 Standard Solutions, Ideality, Resource Analysis, the System Operator, root-cause and patent analysis.
Development framework for herdr: structured skills and workflows with configurable profiles, model/effort targets, TDD, and explicit work and review routes.
Describe the outcome. Conquistador invokes the smallest relevant capability set and returns finished, channel-native work with one human review boundary.
Edit Overleaf projects live alongside human collaborators. Bundles the overleaf-mcp-rt MCP server (self-hosted Overleaf and overleaf.com) with skills for setup, safe co-editing, LaTeX workflow and review comments. Use when asked to read, write, review or compile anything on Overleaf.
Six skills (architect, review-swarm, ask-the-council, prompt-generator, up-to-date, ponytail), the build-loop workflow that builds TODO rows unattended, and the tracker script that renders any workflow run.
How Claude talks and writes — a reply style for chat with a per-prompt reminder hook, a rule set for docs, doc comments, commits, MR text and error messages, and a plain-language restate command
TRIZ for organizational, service and people-centric problems: Function Analysis in plain language for non-engineers, Perception Mapping of stakeholder beliefs, and solution ideas across super-system and sub-system levels.
Multi-agent trading analysis pipeline — technical, news, fundamentals, macro, adversarial bull/bear debate, and a final BUY/SELL/HOLD decision. Powered by yfinance, no external LLM API cost.
ML literature research for agents: top-tier venue search, arXiv / Hugging Face / Semantic Scholar, full-text verification, credibility scoring, and gdoc-ready notes.