The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands to manage the migration workflow, including npx codeceptjs init, npx codeceptjs check, npx codeceptjs list, npx codeceptjs dry-run, and npx codeceptjs run.
[EXTERNAL_DOWNLOADS]: The migration process involves dependencies on several Node.js packages associated with the CodeceptJS ecosystem, such as codeceptjs, @codeceptjs/configure, @codeceptjs/helper, @codeceptjs/effects, and @testomatio/reporter.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it is designed to ingest and process untrusted Cypress configuration and test files.
Ingestion points: Files located in cypress/e2e/, cypress/support/, and cypress.config.* are read and analyzed by the agent.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from being influenced by malicious instructions that might be embedded within the Cypress source code.
Capability inventory: The agent has the ability to execute shell commands, write new test/helper files, and perform browser-side execution via page.evaluate and addInitScript.
Sanitization: No specific sanitization or validation of the input Cypress code is performed before it is processed or converted.
[REMOTE_CODE_EXECUTION]: The skill generates new JavaScript and TypeScript files (e.g., helpers and test specs) and uses browser-level execution methods like page.evaluate and addInitScript to interact with the application under test. These are standard features for end-to-end testing frameworks.

migrate-cypress-to-codeceptjs