独立测试基准状态和候选状态，与提供的比较计划对照，不修复任何状态。
该技能用于独立测试两个状态（基准状态和候选状态）之间的差异，严格按照给定的比较计划执行，不修改或修复任何一方。它通过创建一个全新、独立的子进程（该子进程未参与候选状态的实现）来执行“orch-review”核心任务，从而确保评估的客观性。 该技能接收请求上下文、设计/评估计划、不可变的基准和候选状态标识、复现说明以及相关的实现交接文档。它调用“orch-review”执行所需的比较，收集原始证据，并报告新旧观察结果、候选状态接受结果、回归问题、预期功能缺失以及缺失或不适用检查。 该技能可以构建独立的评估工具以满足计划需求，但必须确保候选状态和基准状态保持不变，不做任何修复。最终输出包含状态/工具标识、条件、复现步骤、结果和限制的完整证据交接文档。即使执行失败或跳过，也会如实记录，评估者不决定是否采纳。此技能适用于需要客观、可比性测试的 AI 代理工作流程，尤其适合于 Claude Code、Cursor、Codex 等平台。
npx skills add https://github.com/DanMcInerney/orchflows/tree/main/example-workflows/design-loop/skills/test-increment使用共享交接合同。输入内容包括请求上下文、设计/评估计划、不可变的基准状态和候选状态标识、复现说明以及相关的实现交接文档。使用一个全新的、未参与候选状态实现的子进程。
调用核心 orch-review 执行指定的“test-increment”任务，提供两个实际状态、预期结果、评估计划、已解决的审查指南，以及在执行有副作用时的独立验证位置。要求它执行所需的比较，保留原始证据，并报告旧/新观察结果、候选状态接受结果、回归问题、预期功能缺失以及缺失或不适用检查。它可以构建评估计划所需的独立评估工具；但必须保持候选状态和基准状态不变，不做任何修复。
返回包含精确状态/工具标识、条件、复现步骤、结果和限制的证据交接文档。跳过或失败的运行将被如实记录；评估者不决定是否采纳。
This repo contains 5 individual skills — each has its own dedicated page.
Delegate one independent review of supplied evidence into a globally ranked, cited assessment.
Delegate bounded source collection and return locally ranked inspectable evidence, or a worker handle for composition.
Review selected native agent history to improve the local environment, custom workflows, or Orchflows itself.
Create short videos for any genre or placement, then independently review the actual exports.
Research bounded public source scopes, then return one independent ranked assessment.
ElevenLabs text-to-speech with mac-style say UX.
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.
Capture and automate macOS UI with the Peekaboo CLI.
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".