The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references templates and configurations for fetching standard testing tools and dependencies from well-known repositories, including k6 (jslib.k6.io, dl.k6.io), Playwright, and Cucumber libraries via NPM and Maven Central.
[COMMAND_EXECUTION]: The instructions direct the agent to generate and execute shell commands for running test suites (e.g., mvn test, npm run test:bdd, k6 run). This is a core functional requirement for the automation engineer role.
[INDIRECT_PROMPT_INJECTION]: The skill has a defined attack surface because it ingests untrusted data from external sources such as Jira tickets, Confluence pages, and local project files (Backlog.md).
Ingestion points: Jira issues, Confluence test plans, and the project backlog (Backlog.md and related ticket files).
Boundary markers: Absent; the skill does not explicitly instruct the agent to use delimiters or warnings to ignore embedded instructions in the test cases it processes.
Capability inventory: The skill possesses extensive capabilities across its scripts, including shell command execution (mvn, npm, k6), file system writes (testing/e2e-{ticket}.md), and browser automation via MCP tools.
Sanitization: Absent; there are no specific instructions for escaping or validating external content before it is used to generate test logic.

e2e-tester