Skill Claude CodeCodex
Helps in drafting more meaningful commit messages based on changes. Use when creating commit messages or users ask to "(draft|create|make) a commit message.".
Skill Claude CodeCodex
Helps in drafting more meaningful commit messages based on changes. Use when creating commit messages or users ask to "(draft|create|make) a commit message.".
Skill Claude CodeCodex
Produce PR chains (trains or stacks) and deployment runbooks as session deliverables. Use when the user requests PR outputs or asks to merge an existing chain. Covers linear branches, CI/CD readiness, and separately authorized fast-forward merges with pipeline monitoring.
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision/design tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Skill Codex
Manage reusable agent skills with the installed skill-manager CLI. Invoke only when the user explicitly asks to "manage skills" or clearly asks for help managing their agent skills, or when the user invokes $managing-skills. Do not invoke for requests that merely mention a skill or independently ask to install…
Skill Claude CodeCodex
Perform code reviews following my engineering practices for work-order-driven development. Use when reviewing a work order (i.e. job) implementation.
Skill Claude CodeCodex
Perform code reviews following my engineering practices. Use when reviewing changes in a branch.
Skill Claude CodeCodex
Runs the agent as an overseer of work in subagents for the entirety of the session going forward instead of carrying out the work directly, with optional explicit Jev model and effort routing. Use when the user specifies that "you are the maestro", "act as the maestro", "as the maestro" or the user otherwise implies…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: