Create or revise runnable Deer Workflow orchestration modules from a user's task description. Use this skill whenever the user asks to turn a repeatable multi-step task into a Workflow, generate a deer-workflow script, coordinate several Agent Loops with parallel or pipeline, or repair a Workflow that assumes APIs are…
Write and run dynamic workflows: short JavaScript scripts in Claude Code's workflow dialect, run with the odw CLI outside the host agent's context, fanning subtasks out to coding-agent CLIs (Codex, Claude Code, Gemini, Qwen, Kimi, or your own) in a background process and handing back only the final result. Use this…
A way to write JavaScript workflows that send parts of a large task to separate coding-agent command-line programs and return only the final result. It supports multiple agents, stages, loops, and checks within one workflow.
Execute explicitly authorized Ultracode / Ultra Mode requests: optimize for exhaustive, correct answers within the user's stated scope by using any available independent-work mechanism (ODW workflows, subagents, dispatched workers, or tool-worker fan-out), with serial multi-pass fallback only when no such mechanism…
A skill for creating, editing, or reviewing Claude Code skills, especially skills that enforce disciplined agent behavior. Its instructions are written in Chinese.
A skill for measuring how well another skill works, including whether its description triggers it for the right requests. It uses evaluation results to guide revisions.
A skill that defines rules for keeping development work isolated in Git worktrees. A worktree is a separate working directory connected to the same Git repository, useful for keeping parallel changes apart.
Build a Godot 4 / GDScript game feature with a coordinated agent team — a Manager (you), a Creative Director, a Logic Developer, an Animation Developer, and a Tester — that iteratively and autonomously design, build, juice, and verify the feature against the project's design contract to a strict, un-skippable quality…