Testing

Create new skills, modify and improve existing skills, and measure skill performance.

TDD and testing skills for iOS/macOS apps.

Playwright 驱动的浏览器控制（导航、点击、填表、按键、滚动、等待、标签页和截图）

Test the configured text-generation model with a supplied prompt.

ArkClaw知识库问答技能, 从火山引擎ArkClaw公开知识库检索有关ArkClaw企业版相关文档, 用于解决ArkClaw企业版使用相关问题, 指令触发方式`/qa <问题描述>`

Developer role in AID methodology.

Create new skills, modify and improve existing skills, and measure skill performance.

Remove redundant unit test code in a scoped area without dropping use cases or coverage, proven by a per-line coverage diff before and after, and finish with…

对 AutoResearch 目录或 ZIP 做只读质检；审优化面、Baseline 和 Reference 提升，检查 21 项、独立 sandbox、轨迹与可选 Codex sessions 的泄漏/作弊/infra 问题、评分资源及四项题包哈希绑定。输出跑分与可执行退回说明；不用于求解任务。

OWASP-grounded code security reviews and offensive audits with exploit proof.

Run a coverage-accountable, unusually strict review of Exograph for correctness, structural simplicity, deep modules, lifecycle safety, performance, tests…

Film a real web app, logged in or public, SPA or multi-page, as clean re-recordable product footage.

Use when the user wants Codex to build, refine, test, validate, or list CLI-Anything harnesses for GUI applications or source repositories.

Autonomous engineering loop and multi-harness worker orchestrator for ANY codebase, language, or build system.

XP pair work for ONE yurtle-kanban issue.

Cross-browser testing with bidiwave using the W3C WebDriver BiDi protocol.

Create new skills, modify and improve existing skills, and measure skill performance.

Record a pytest suite that has grown too slow as a GitHub issue, then stop.

Follow a Testery test run with a live ANSI dashboard (progress bar, counts, ETA, currently-running tests) and report a final pass/fail summary with emojis.

按原v0.3.10完整标准审阅AutoResearch题包，包括NOP、三门控、21项、Harbor六项、轨迹行为/分数、资源时长与四项指纹；保留原始结果，再逐原因应用指定旧题豁免，不用于求解或自动运行题包。

Select a dependency-ready feature slice, audit BDD coverage, and prepare issue-backed work packets.

Create new skills, modify and improve existing skills, and measure skill performance.

Rewrites red-team test prompts by replacing up to three selected terms with indexed placeholders and rendering those terms as deterministic A-Z 5x7 binary…

Synthesise the current conversation into a spec, publish it where the project's issue tracker points, and name the next command: journey when the stories add…