How do I install the E2e Outside In Test Generator skill?

Run npx skillmds@latest add rysweet/e2e-outside-in-test-generator-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is E2e Outside In Test Generator safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with E2e Outside In Test Generator?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is E2e Outside In Test Generator free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published E2e Outside In Test Generator?

rysweet (@rysweet) published this skill. Their other Agent Skills are listed on their SkillMD profile.

E2e Outside In Test Generator by rysweet

Name: E2e Outside In Test Generator
Author: rysweet

File contents

E2E Outside-In Test Generator

Purpose

Generate runnable end-to-end tests from the user's point of view. The bundled helper creates a starter outside-in plan or seed scenario; the agent then adapts that output to the repository's existing test framework and validates it with normal test commands.

Supported App Types

App type	Preferred output
Web	Playwright specs
CLI	Shell, bats, cargo/npm/dotnet test harnesses already present
TUI	Terminal interaction tests using existing repo conventions
API	HTTP/client tests in the repo's existing test framework
MCP	YAML scenario tests when the repo already uses them

Workflow

Detect the app type from package manifests, routes, binaries, docs, and existing tests, or run the helper.
Identify 3-8 critical user journeys and expected outcomes.
Generate tests in the repository's existing e2e/test location, or e2e/ if there is no convention.
Prefer real user entry points over mocked internals.
Run the relevant existing test command and fix failures caused by the new tests.
Report any product bugs found separately from test harness problems.

Output Requirements

Tests must be runnable by existing tooling.
Generated assertions must validate observable behavior, not implementation details.
Do not add a new test framework unless the repository has no suitable e2e path.
Do not silently skip journeys; document unsupported journeys and why.

Native Helper

# Inspect detected app type and journey plan
amplifier-bundle/skills/e2e-outside-in-test-generator/scripts/generate-e2e.sh plan

# Generate a starter scenario/spec
amplifier-bundle/skills/e2e-outside-in-test-generator/scripts/generate-e2e.sh generate --type web --output e2e
amplifier-bundle/skills/e2e-outside-in-test-generator/scripts/generate-e2e.sh generate --type cli --output e2e

The helper intentionally creates starter artifacts only. The agent must adapt the scenarios to real project commands, routes, and assertions before claiming completion.

---name: e2e-outside-in-test-generator-2description: Generates comprehensive end-to-end test scenarios using outside-in methodology. Supports Web (Playwright), CLI, TUI, API, and MCP/gadugi-style scenarios. Auto-detects app type or accepts explicit override.---# E2E Outside-In Test Generator## PurposeGenerate runnable end-to-end tests from the user's point of view. The bundled helper creates a starter outside-in plan or seed scenario; the agent then adapts that output to the repository's existing test framework and validates it with normal test commands.## Supported App Types| App type | Preferred output || --- | --- || Web | Playwright specs || CLI | Shell, bats, cargo/npm/dotnet test harnesses already present || TUI | Terminal interaction tests using existing repo conventions || API | HTTP/client tests in the repo's existing test framework || MCP | YAML scenario tests when the repo already uses them |## Workflow1. Detect the app type from package manifests, routes, binaries, docs, and existing tests, or run the helper.2. Identify 3-8 critical user journeys and expected outcomes.3. Generate tests in the repository's existing e2e/test location, or `e2e/` if there is no convention.4. Prefer real user entry points over mocked internals.5. Run the relevant existing test command and fix failures caused by the new tests.6. Report any product bugs found separately from test harness problems.## Output Requirements- Tests must be runnable by existing tooling.- Generated assertions must validate observable behavior, not implementation details.- Do not add a new test framework unless the repository has no suitable e2e path.- Do not silently skip journeys; document unsupported journeys and why.## Native Helper```bash# Inspect detected app type and journey planamplifier-bundle/skills/e2e-outside-in-test-generator/scripts/generate-e2e.sh plan# Generate a starter scenario/specamplifier-bundle/skills/e2e-outside-in-test-generator/scripts/generate-e2e.sh generate --type web --output e2eamplifier-bundle/skills/e2e-outside-in-test-generator/scripts/generate-e2e.sh generate --type cli --output e2e```The helper intentionally creates starter artifacts only. The agent must adapt the scenarios to real project commands, routes, and assertions before claiming completion.

Frequently asked questions

E2e Outside In Test Generator