16 tagged ai quality, measured the same way as everything else here.
Browse within: agent-ops 14
Skill Claude CodeCodex
Use when about to return a non-measurable output — writing, proposals, plans, explanations, designs, drafts, or any artifact whose quality is judged rather than tested. Also use when the user says "second pass this", "grade this", "is this good enough?", "self-judge", "iterate on this". Do NOT use for measurable…
Skill Claude CodeCodex
A tool for creating or reorganizing CLAUDE.md and AGENTS.md files, which give coding agents project instructions.
Skill Claude CodeCodex
A planning skill that explores a complex development task from several angles, combines the findings, and improves the plan through review. It is intended for difficult architecture choices or plans that are too shallow.
Skill Claude CodeCodex
An orchestration skill that takes a plain-language development request through design, implementation, checking, and fixes. Orchestration means coordinating several work stages or agents into one process.
Skill Claude CodeCodex
Run Matt Shumer's Gauntlet Loop methodology to raise the quality of an artifact through cycles of building, independent critique, comparison against real references, and improvement. Use when the user asks for the Gauntlet Loop, a builder-critic process, adversarial critique, iterative refinement, or the creation of…