Skill Claude CodeCodex
A one-time text dashboard showing measured benchmark results for Ponytail on five everyday coding tasks and three AI models. A benchmark is a repeatable test used to compare results.
8 tagged lazy, measured the same way as everything else here.
Browse within: deepseek-harness 6dsh 6dsh-plugin 6
Skill Claude CodeCodex
A one-time text dashboard showing measured benchmark results for Ponytail on five everyday coding tasks and three AI models. A benchmark is a repeatable test used to compare results.
Skill Claude CodeCodex
A quick reference card for the Ponytail set of commands, which focuses on using the simplest workable implementation. It explains the available modes and related commands in Chinese and English.
Skill Claude CodeCodex
A coding-work style that seeks the smallest working solution and avoids unnecessary abstractions, dependencies, and scaffolding. It applies to writing, fixing, refactoring, reviewing, and designing code.