Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
nullhub-admin
Teach managed nullclaw agents to discover NullHub routes first and then use nullhub api for instance, provider, component, and NullBoiler workflow tasks.
pm-git-file-tracking
Protocol for tracking files immediately after agent creation
session-manager-driver
Drive the trusty-mpm session manager (binary `tm`) to spawn, observe, command, and decommission durable tmux-backed Claude Code sessions in isolated workspaces. Wraps the `tm session` CLI / REST API and provides the spawn → observe → answer → stop/resume/decommission loop. Critically, the DRIVER interprets the raw tmux pane using its own inference — it does NOT depend on the daemon's optional LLM (no OpenRouter key required).
trusty-services
Install and configure trusty-memory and trusty-search for persistent AI memory and semantic code search
agent-role-design
Defining what each agent does, knows, and owns in a multi-agent system.
chain-of-thought-design
Designing reasoning chains that produce better outputs.
comparative-evaluation
A/B testing, side-by-side comparison, and preference ranking for AI outputs.
context-window-design
Designing around token limits, memory, and conversation persistence.
conversation-patterns
Turn-taking, repair sequences, grounding, and dialogue structure for human-AI interaction.