Skill design and optimization toolkit for AI agents. Includes grok-skill-creator (Grok Build) and mimo-skill-creator (MiMo Code) — create, test, benchmark, and optimize agent skills with evaluation pipelines.
Skill Claude CodeCodex
Create, test, and optimize Grok skills. Use when creating a skill from scratch, editing one, testing if a skill works, optimizing skill triggering, benchmarking performance, or packaging a .skill file. Triggers: "create skill", "new skill", "edit skill", "test skill", "skill not triggering", "optimize description"…
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Skill Claude CodeCodex
Create, test, and optimize Kimi Code skills. Use when creating a skill, editing one, testing if a skill works, optimizing triggering, or packaging a .skill file. Triggers: "create skill", "new skill", "edit skill", "test skill", "skill not triggering", "optimize description", "package skill", "SKILL.md", "whenToUse"…
Skill Claude CodeCodex
Create, test, and optimize skills for MiMo Code. Use when creating a skill, editing one, testing if a skill works, optimizing skill triggering, or packaging a .skill file. Triggers: "create skill", "new skill", "edit skill", "test skill", "skill not triggering", "optimize description", "package skill", "verify skill"…