メニュー
Create, edit, or run SpecLoop scenario files under `.specloop/scenarios/`, including local localhost checks, remote landing/blog screenshot flows, and manual browser QA runbooks.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Run the SpecLoop QA loop: load specs and business rules, enforce read-only safety, explore critical flows, write structured findings, triage accepted reports, and suggest regression tests.
Run a repeatable, agent-driven workflow enforcing the 7 mandatory phases (Idea, Plan, Implement, Test, Gate, Ship, Reflect) to keep projects improving while maintaining SpecLoop quality standards.
Run a backend validation loop that generates Postman collections, executes RESTful tests, and validates API compliance using OpenAPI/Swagger specs or code routes.
Run an agentic testing loop for Mobile applications (SwiftUI, iOS, Android) that navigates the UI, analyzes accessibility, takes screenshots, and verifies visual specs.
| name | specloop-scenario |
| description | Create, edit, or run SpecLoop scenario files under `.specloop/scenarios/`, including local localhost checks, remote landing/blog screenshot flows, and manual browser QA runbooks. |
Use this skill when the user asks to create a QA scenario, add a browser flow, or run a specific .specloop/scenarios/*.md file.
specloop.yaml for target URL and output folders..specloop/screenshots/.After specloop scaffold scripts:
node --experimental-strip-types scripts/specloop-new-scenario.ts --name "pricing smoke" --url "http://localhost:3000"
Keep scenarios small: one persona, one target, one expected outcome, and explicit evidence paths.