The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the creation and execution of shell scripts (init.sh, smoke-test.sh) for automating environment setup tasks, including dependency installation, build processes, and service orchestration.
[PRIVILEGE_ESCALATION]: The skill provides instructions to modify file permissions using chmod +x on shell scripts created during the environment bootstrap process.
[DYNAMIC_EXECUTION]: The skill implements a pattern of generating executable shell scripts from embedded templates and subsequently executing them to perform environment-level operations.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill reads external configuration files including package.json, docker-compose.yml, .env.example, and test files like tests/smoke.test.ts to determine the setup logic.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present when processing these files.
Capability inventory: The skill possesses the ability to execute shell commands, write to the file system, and perform network requests to localhost via curl.
Sanitization: There is no evidence of sanitization or content validation for the ingested files before they are used to drive agent actions.

environment-bootstrap