Dev & Coding

A hybrid workflow skill for writing, completing, integrating, and improving SKILL.md files and agent definitions with enforced conventions and a lint step.

An orchestrator that diagnoses a Claude Code skill or bundle-plugin and improves its triggering description, token cost, workflow chain and security findings step by step.

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

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.