Set up unit testing with /tests or /tests unit, or explicitly set up browser and end-to-end testing with /tests browser. Reuse or install a suitable test runner, add one example or smoke test, document commands, and verify. Use check for one-time live verification.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Context reuse: Reuse any required file already loaded in project instructions or the current session. Read it again only if absent, changed, or exact current bytes or line references are needed.
First action: Before project inspection, preflight, or any other tool call,
publish running to blueprint/.state/run.json using the dashboard activity
contract in AGENTS.md. Use tests as the command for either setup mode.
/tests or /tests unit: set up stack-native unit testing. Read and follow
reference/unit.md only./tests browser: set up a repeatable browser harness. Read and follow
reference/browser.md only./tests Playwright remains a unit request with a runner
preference to clarify, not permission to install browser automation.Load only the selected reference. Do not read both references preemptively. Treat any remaining runner or stack arguments as preferences to verify against project files, never as permission to expand the selected setup.
Follow the selected reference's inspection, approval, verification, and report steps. Unit setup may add tests to an existing Verify command; browser setup must not add its slower gate to Verify or CI without a separate request or an existing project requirement. Neither mode creates CI just by being invoked. Do not commit, merge, push, publish, or begin product feature work.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Adopt Blueprint into an existing brownfield codebase by surveying shipped behavior and generating plans, standards, commands, adapter choices, and visibility setup. Use for /adopt or requests to bootstrap Blueprint into an established app. Use onboard for a fresh scaffold.
中文简介正在准备中。当前显示原文说明。
Audit current changes, a path, or the full project for quality, security, performance, or test problems and record durable findings. Independent mode prepares or completes a fresh-reviewer checkpoint handoff. Use for /audit, independent review, security review, code quality review, dead code, duplication, or standards drift.
中文简介正在准备中。当前显示原文说明。
Run one explicit bounded Blueprint spec and implementation pass through configured quality gates, then stop before completion or external actions. Use only when the user directly invokes /autopilot, $autopilot, or asks for Autopilot.
中文简介正在准备中。当前显示原文说明。
Brief an upcoming build-plan feature without writing files. Explain scope, dependencies, affected areas, size, and likely splits for the next item or a named item. Use for /brief, feature previews, what comes next, or build-order decisions before /feature.
中文简介正在准备中。当前显示原文说明。
Check the running app, CLI, or server against the active spec's done-when criteria and capture observable pass or fail evidence without editing source. Use /check to verify real feature behavior, or /check guide [latest|scope] for a read-only manual walkthrough: how to test manually, where to click, expected and incorrect results, or a human review path.
中文简介正在准备中。当前显示原文说明。
Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI, with an optional local pre-push hook. Use for /ci, GitHub Actions setup, pull-request checks, automatic checks, pre-push hooks, or aligning typecheck, test, and build verification.
中文简介正在准备中。当前显示原文说明。