Skill Claude CodeCodex
Creates or updates Margin Eval agent definitions for new CLI coding agents. Use this skill when Codex needs to add support for a new agent, scaffold a directory under configs/agent-definitions/, define schemas and hooks, add example agent configs, or review an existing definition for missing auth, unified-mode…
Skill Claude CodeCodex
Converts test suites from external eval frameworks into the Margin Eval suite format. Use this skill whenever the user wants to import, convert, translate, or migrate an eval dataset or test suite into Margin Eval format, or when they mention converting tasks from other benchmarking frameworks into Margin's structure.
Skill Claude CodeCodex
Creates new Margin Eval test suites from scratch. Use this skill whenever the user wants to author, build, or scaffold a new eval test suite, define test cases for evaluating coding agents, or create tasks with Dockerfiles, prompts, and grading scripts for the Margin Eval framework.