菜单
Set up end-to-end testing infrastructure for Assistant Skills plugins. Use when user wants to "add E2E tests", "test my plugin", "set up integration testing", "create plugin tests", or needs to validate their Claude Code plugin works correctly with real API calls.
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。
基于 SOC 职业分类
This skill should be used when the user wants to run Claude with risk-based permission enforcement, configure safe mode settings, create permission blocks for SAFEGUARDS.md files, or understand how to restrict CLI operations based on risk levels. Use when asked about "safe mode", "permission enforcement", "risk levels", "claude-safe", or "restricting dangerous commands".
Build and scaffold Assistant Skills plugin projects. This skill should be used when: (1) create new Claude Code plugin project, (2) add skill to existing project, (3) scaffold CLI library for API, (4) wrap existing CLI tool, (5) validate project structure, (6) migrate existing project to new structure, (7) show reference patterns from production implementations (Jira, Confluence, Splunk).
Create production-ready demo platforms for Assistant Skills plugins. Use when you want to "create a demo", "scaffold demo infrastructure", "set up demo for plugin", "generate demo project", or need to create queue-managed demo environments like jira-demo, confluence-demo, or splunk-demo.
Audit and optimize skills for token efficiency and progressive disclosure compliance. Use when user wants to "analyze skill tokens", "audit skills", "optimize skill size", "check token efficiency", or "validate progressive disclosure".
Extract shared libraries from Assistant Skills projects and publish them as PyPI packages. Use when user wants to "publish shared library", "create PyPI package", "extract library to package", "migrate to pip install", or needs to convert vendored code into an installable package with CI/CD.
Create professional README landing pages for Assistant Skills projects with consistent branding. Use when creating or upgrading project READMEs, generating logos, or ensuring visual consistency across repositories.
| name | e2e-testing |
| description | Set up end-to-end testing infrastructure for Assistant Skills plugins. Use when user wants to "add E2E tests", "test my plugin", "set up integration testing", "create plugin tests", or needs to validate their Claude Code plugin works correctly with real API calls. |
Set up comprehensive end-to-end testing infrastructure for Assistant Skills plugins. Auto-generates test cases from your plugin structure and skills.
# Initialize E2E testing infrastructure
python skills/e2e-testing/scripts/setup_e2e.py /path/to/project
# Auto-generate test cases from plugin structure
python skills/e2e-testing/scripts/generate_test_cases.py /path/to/project
# Run tests
./scripts/run-e2e-tests.sh
# Update project documentation
python skills/e2e-testing/scripts/update_docs.py /path/to/project
| Script | Purpose |
|---|---|
setup_e2e.py | Initialize E2E testing infrastructure |
generate_test_cases.py | Auto-generate test cases from plugin |
run_tests.py | Execute tests with multiple output formats |
update_docs.py | Update project documentation |
| Method | Location | Setup |
|---|---|---|
| OAuth | ~/.claude.json | claude auth login |
| API Key | Environment | export ANTHROPIC_API_KEY="sk-ant-..." |
Local runs (--local) prefer OAuth credentials over API keys.
| Variable | Default | Description |
|---|---|---|
E2E_TEST_TIMEOUT | 120 | Timeout per test (seconds) |
E2E_TEST_MODEL | claude-sonnet-4-20250514 | Claude model |
E2E_MAX_TURNS | 5 | Max conversation turns |
| Format | Flag | Description |
|---|---|---|
| Console | (default) | Colored terminal output |
| JSON | --output results.json | Machine-readable results |
| JUnit | --junit results.xml | CI/CD integration |
| HTML | --html report.html | Visual report |
| Model | Cost per Test | 20 Tests |
|---|---|---|
| Haiku | ~$0.001 | ~$0.02 |
| Sonnet | ~$0.01 | ~$0.20 |
| Opus | ~$0.05 | ~$1.00 |
Edit tests/e2e/test_cases.yaml to add custom test cases:
suites:
custom:
tests:
- id: my_test
prompt: "Do something specific"
timeout: 180 # Override default
max_turns: 10 # Override default
expect:
output_contains: ["expected"]
Failed test responses logged to test-results/e2e/responses_latest.log.
tests/e2e/README.mddocs/test-prompt-best-practices.mddocs/troubleshooting.md