The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from existing source test files (Playwright, Cypress, Selenium, etc.) and external documentation to perform migrations.
Ingestion points: Source test files (e.g., .spec.ts, .yml, .maestro/), repository configuration files, and external migration guides hosted at e2e.tester.army.
Capability inventory: The agent has the ability to execute shell commands (via npx), write new test files to the filesystem, and propose modifications to CI workflow files.
Boundary markers: The instructions do not specify explicit delimiters or "ignore previous instructions" warnings when processing the content of existing tests.
Sanitization: There is no mention of sanitizing or escaping the logic found in existing tests before translating them into the new suite.
[COMMAND_EXECUTION]: The skill utilizes several CLI tools to perform its tasks, including npx e2e init, npx e2e run, npx playwright test --list, and maestro test. It also includes a feedback mechanism that sends data externally via npx e2e feedback.
[EXTERNAL_DOWNLOADS]: The skill references and retrieves documentation from https://e2e.tester.army/docs/. These are vendor-owned resources associated with the skill author.
[DYNAMIC_EXECUTION]: The instructions include a fallback for importing legacy CommonJS modules by executing them in a child process using TypeScript runners like ts-node or tsx.

migrate-to-e2e