The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides informational grep command examples designed to assist developers in auditing their codebases for specific Ktor construction and logging patterns.
[SAFE]: The architectural pattern demonstrated uses expect/actual declarations to abstract platform-specific HTTP engines, which is the recommended approach for Kotlin Multiplatform development.
[SAFE]: The example code includes a configuration to allow HTTPS to HTTP downgrades during redirects (allowHttpsDowngrade = true). While this is a security-sensitive setting, it is presented as part of a technical architectural template for specific KMP networking requirements.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to audit project code by running grep and interpreting the results.
Ingestion points: The agent reads and analyzes output from grep commands targeting *.kt files within the workspace.
Boundary markers: No explicit delimiters are used for the code snippets ingested during the audit process.
Capability inventory: The skill uses local shell command execution (grep) and internal code analysis capabilities.
Sanitization: No sanitization is performed on the ingested code before analysis.

ktor-kmp-client-architecture