菜单
Write an end-to-end (e2e) test for vix. Use when the user asks to add, create, or modify an e2e test that drives the real vix TUI and vixd daemon against the mock LLM server.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/get-vix/vix --skill write-e2e-test命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Author and edit vix workflows — declarative multi-step pipelines (agent/bash/tool/if/fan_out/fan_in nodes) stored in config/workflow.json or embedded inline in a job/hook. Use when the user asks to create, modify, or understand a workflow, or to fan work out across many items and join the results.
Create and manage lifecycle hooks that vixd fires automatically on agent-loop events (a tool about to run, a prompt submitted, a thread starting, a turn finishing). Use when the user wants to enforce a rule, block or rewrite a tool call, validate prompts, auto-format, notify, or react to what the agent does.
Create and manage scheduled jobs (cron tasks, reminders, heartbeat checks, polling watchers) that vixd runs automatically. Use when the user asks to schedule, automate, monitor, watch, or be reminded about something.
基于 SOC 职业分类
正在显示 SKILL.md
| name | write-e2e-test |
| description | Write an end-to-end (e2e) test for vix. Use when the user asks to add, create, or modify an e2e test that drives the real vix TUI and vixd daemon against the mock LLM server. |
Write or modify a vix end-to-end test. $ARGUMENTS
Before doing anything else, read e2e/README.md (at the repo root) in full. It is
the authoritative guide to how the e2e suite works — the separate Go module, the
mock LLM server, the Landlock sandbox, the tmux/freeze screenshot harness, and the
HTML report. Understand it before writing any test.
Then follow this process:
Read the README. Start with e2e/README.md. Note how tests are run
(make test-e2e), how they are structured, and the conventions they follow.
Study existing tests. Browse the existing test files under e2e/ to match
the established patterns (scenario setup, mock LLM scripting, assertions,
screenshots). Mirror the closest existing test rather than inventing a new
shape.
Implement the test. Add or modify the test following the conventions you just learned. Keep it focused on the behaviour being exercised; do not over-engineer or add unrelated scaffolding.
Verify. Run the suite (or the relevant subset) as documented in the README to confirm the test builds and behaves as expected. Report the outcome.
If anything in the README contradicts these steps, the README wins.
