The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data which serves as a potential vector for indirect prompt injection.
Ingestion points: The skill analyzes application source code, performance logs, and database query execution plans as outlined in SKILL.md and references/framework-patterns.md.
Boundary markers: There are no explicit instructions for the agent to use delimiters or sanitization routines when processing external data.
Capability inventory: The agent is tasked with generating reports, identifying bottlenecks, and suggesting code changes based on its analysis of the ingested data.
Sanitization: No sanitization steps are defined for the input data.
[DYNAMIC_EXECUTION]: The skill involves the generation of executable scripts for performance testing.
Evidence: The skill provides templates for generating k6 JavaScript tests and Artillery configuration files in references/load-testing.md.
[COMMAND_EXECUTION]: The skill instructs the agent to utilize various performance analysis and monitoring tools.
Evidence: Mentions usage of npx webpack-bundle-analyzer, k6, Artillery, JMeter, and Locust for performance profiling and load testing.

performance