All skills

A lookup skill covering the Agentica multi-agent framework's pattern classes, core infrastructure, and primitives.

A meta-skill that discovers, downloads, configures, and routes every skill in the aelf blockchain ecosystem.

Reads `site-analysis.json`, groups pages by business purpose, and records explicit user approval of the page groups.

An iterative, human-in-the-loop planning skill: one question at a time, 2-3 trade-off-scored approaches, and section-by-section approval before any code is written.

A multi-agent execution rulebook: decompose plans into tasks, isolate each task on its own branch, enforce two-stage review, and gate merges behind human checkpoints.

Uses the cozempic CLI to prune your current Claude Code session and auto-open a new terminal that resumes it.

Turns any organizational or technical change into a structured plan covering communication, training, adoption and resistance.

Usage rules for calling trace-mcp tools inside bb to search indexed code and recall project decisions with minimal context.