菜单
Use when a user asks to run Expect or expect-cli, validate the frontend in a real browser, or surface Expect's native replay output for this repository.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Review pull requests for high-impact issues only. Use when the user asks to review a PR, especially requests like "do a review of PR <id>", "review PR <id>", or "PR review". Focus on security, repository conventions, reuse over reimplementation, structure consistency, and unnecessary complexity. Return only actionable comments worth changing.
Create or update any LLM-related prompt file in this repository using the required `<role>`, `<task>`, `<input>`, and `<output>` structure, with optional `<tools>` when tool policy is needed, and explicit model-aligned field contracts. Use for prompts stored in markdown, Python prompt templates, YAML/JSON config prompts, and any other runtime prompt definitions for large language models (LLMs).
Review LLM pipeline changes that add or modify retry logic, batching, multi-pass aggregation, fallback flows, or persisted diagnostics/artifacts. Use when an agent, orchestrator, writer, or API path changes how LLM calls are retried, split, combined, failed closed, or written to/read from run artifacts.
Review generated, imported, or cleaned-up Markdown artifacts for conversion damage before changes are applied. Use when Codex needs to inspect Markdown files for encoding corruption, broken tables, whitespace merges, repeated extraction fragments, malformed blockquotes, or similar document-conversion artifacts and propose exact fixes before editing.
Analyze GitHub pull request review threads against the current local branch. Use when the user asks to list unresolved PR comments, quote the exact review text, explain the code under review, determine whether the issue still exists, and state whether a fix or only a reply is needed.
基于 SOC 职业分类
| name | expect-browser-testing |
| description | Use when a user asks to run Expect or expect-cli, validate the frontend in a real browser, or surface Expect's native replay output for this repository. |
Use expect-cli for browser testing against the running Query Mechanism Urbind frontend. Prefer Expect's native replay flow instead of repo-local recording helpers.
Do not use this as a replacement for pytest, backend smoke scripts, or linting.
uv sync --group devpython -m uvicorn backend.api.main:app --host 127.0.0.1 --port 8000frontend/:
npm installnpm run devNEXT_PUBLIC_API_BASE_URL=http://127.0.0.1:8000http://127.0.0.1:3000http://127.0.0.1:8000EXPECT_BASE_URL=http://127.0.0.1:3000 npx -y expect-cli@latest -a codex -m "<instruction>" -t changesEXPECT_BASE_URL=http://127.0.0.1:3000 npx -y expect-cli@latest -a codex -m "<instruction>" -t branchOpen http://127.0.0.1:3000, load the latest saved Munich answer, verify the answer renders, click a citation chip so the quote popover opens, and open Chat About the Answer without UI or console errors.Open http://127.0.0.1:3000 in dev mode, generate an answer for Munich and Leipzig, switch to chat, ask a follow-up, and verify citation chips remain clickable.test the app-t changes during active development.EXPECT_BASE_URL; current expect-cli 0.0.10 help does not expose --base-url.expect-cli to frontend/package.json or CI by default.FSL-1.1-MIT, not plain MIT today. Do not vendor it into the repo without explicit approval.