Automated summary
Generates E2E test skeletons from BDD .feature scenarios, with framework detection and coverage gap analysis.
Strengths
- Classifies each acceptance criterion as e2e-suitable, integration-suitable or unit-suitable so you don't write needless E2E tests
- Auto-detects Playwright, Cypress or Vitest and mirrors the test patterns already used in the repository
- The --analyze mode surfaces BDD scenarios that lack E2E coverage, either repo-wide or for a single feature file
- Suggests a follow-up with /tdd to fill in the [TODO] markers of the generated skeleton
Limitations
- Flagged as an experimental feature that may change significantly in v4.0
- Only produces skeletons: implementing the tests and running them stays manual
- Assumes .feature scenarios already exist (e.g. from /derive bdd) and supports only three frameworks
Use it when you already have BDD scenarios and want to bootstrap an E2E suite in the framework your project already uses.
Avoid it for pure logic or component-to-component checks without a UI, which belong in unit or integration tests.
Security analysis
SafeThe skill only reads BDD feature files and writes E2E test skeletons. Bash access is restricted to 'npm test:*', which executes project test scripts rather than arbitrary shell commands. No destructive, exfiltration, obfuscation, or safety-disabling behavior is present.
No concerns found
How this analysis is madeExamples
/e2e specs/login.feature — generate the E2E test skeleton for these scenarios/e2e --analyze — scan all feature files and tell me which ones have no E2E coverage/e2e --analyze specs/checkout.feature — classify its acceptance criteria and show the E2E gapssource: ../../../../skills/e2e-assistant/SKILL.md source_version: 1.0.0 translation_version: 1.0.0 last_synced: 2026-04-10 status: current description: "[UDS] 從 BDD 場景生成 E2E 測試骨架，支援框架偵測與覆蓋差距分析" name: e2e allowed-tools: Read, Write, Grep, Glob, Bash(npm test:*) scope: partial argument-hint: "[feature file or --analyze | .feature 檔案或 --analyze]"
E2E 助手
語言: English | 繁體中文
[!WARNING] 實驗性功能 / Experimental Feature
此功能正在積極開發中，可能在 v4.0 中有重大變更。 This feature is under active development and may change significantly in v4.0.
從 BDD .feature 場景生成 E2E 測試骨架，支援框架偵測與覆蓋差距分析。
工作流程
/derive bdd → .feature 場景
↓
/e2e → 分析 AC 適用性 → 偵測框架 → 參考既有模式 → 生成骨架
↓
手動執行驗證
模式
1. 生成模式（預設）
分析 BDD 場景、分類 AC 適用性、偵測框架、生成 E2E 測試骨架。
2. 分析模式（--analyze）
掃描 BDD feature 與既有 E2E 測試之間的覆蓋差距。
AC 分類
| 類別 | 條件 | 範例 |
|------|------|------|
| e2e-suitable | 多步驟使用者流程或 UI 互動 | 登入 → 操作 → 驗證 |
| integration-suitable | 跨元件但無 UI | API 呼叫 → DB 寫入 |
| unit-suitable | 純邏輯或計算 | 排序、驗證、格式化 |
支援框架
| 框架 | 自動偵測 | 範本 |
|------|:--------:|------|
| Playwright | ✅ | @playwright/test |
| Cypress | ✅ | cy.* 指令 |
| Vitest | ✅ | describe/it + async |
使用方式
/e2e <feature-file> - 從 BDD 場景生成 E2E 骨架
/e2e <spec-file> - 委派 /derive e2e 處理 SDD 規格
/e2e --analyze - 掃描所有 feature 的 E2E 覆蓋差距
/e2e --analyze <feature-file> - 分析特定 feature 的 AC 適用性
下一步引導
/e2e 完成後，AI 助手應建議：
E2E 骨架已生成。建議下一步：
- 執行
/tdd填入[TODO]標記的測試實作 ⭐ 推薦 — 實作測試邏輯- 執行
/checkin品質關卡（若功能完成）- 執行
/e2e --analyze檢查整體 E2E 覆蓋狀況
參考
- 規格：SPEC-E2E-001
- 核心規範：testing-standards.md
- 工具程式：
cli/src/utils/e2e-analyzer.js、cli/src/utils/e2e-detector.js
AI 代理行為
完整的 AI 行為定義請參閱對應的命令文件：
/e2e
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/e2e-assistant-mrx3xxs0/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/e2e-assistant-mrx3xxs0' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/e2e-assistant-mrx3xxs0/download' --output '.skill-downloads/e2e-assistant-mrx3xxs0/SKILL.md.part' && mv '.skill-downloads/e2e-assistant-mrx3xxs0/SKILL.md.part' '.skill-downloads/e2e-assistant-mrx3xxs0/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read, Write, Grep, Glob, Bash(npm test:*)
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/e2e-assistant-mrx3xxs0/SKILL.md' && test -s '.skill-downloads/e2e-assistant-mrx3xxs0/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/e2e' && cp -R '.skill-downloads/e2e-assistant-mrx3xxs0' '.claude/skills/e2e'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/e2e-assistant-mrx3xxs0'openskills read 'e2e-assistant-mrx3xxs0'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/e2e-assistant-mrx3xxs0/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
ClickHouse Performance Comparison
Testing
Evaluate ClickHouse performance test results, check PR performance changes, compare with history, and assess whether a result is actionable.
Analyze CI Performance Reports
Testing
Analyze CI performance comparison reports for a ClickHouse PR. Cross-references master history to distinguish real regressions from flaky tests.
Santa Method
Testing
Multi-agent adversarial verification with two independent reviewers. Output is checked twice and iteratively fixed until both pass before shipping.