The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests external data including telemetry, query plans, and test logs. Ingestion points: Reads tool-generated reports and runtime evidence (SKILL.md, verification.md). Boundary markers: Mandates isolated environments, synthetic datasets, and explicit user authorization (harness.md). Capability inventory: Includes shell command execution and file writing to tmp/reports/ (SKILL.md). Sanitization: Employs mandatory question tool checkpoints for authorization and recommends redaction of output artifacts (harness.md).- [EXTERNAL_DOWNLOADS]: The skill references official documentation and installation paths for performance testing tools like k6, Locust, and Gatling. All sources listed in references/sources.md point to official project domains or well-known technology organizations.- [COMMAND_EXECUTION]: The skill facilitates the generation and execution of project-specific shell commands for performance measurement. The process is protected by a strict requirement for explicit user consent before any action is taken and an explicit prohibition against the use of elevated privileges such as sudo.

performance-test