The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes system commands including pc (Pipecat CLI), docker, and uv. It utilizes shell piping (yes |) to automate interactive prompts during the Docker build and agent deployment processes.
[CREDENTIALS_UNSAFE]: The skill accesses local .env files to upload secrets to the vendor's cloud service via the pc cloud secrets set command. It also handles the authentication flow by capturing and parsing login URLs and six-digit codes from the CLI's background output.
[EXTERNAL_DOWNLOADS]: The skill directs the user to install the vendor's CLI tool (pipecat-ai-cli) using the uv package manager if the tool is not already present on the system.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external configuration data from pcc-deploy.toml and .env files which are interpolated into shell commands.
Ingestion points: Reads and parses pcc-deploy.toml and .env files from the local filesystem (SKILL.md).
Boundary markers: None; the skill does not use specific delimiters or instructions to ignore embedded commands in the config files.
Capability inventory: Full subprocess execution capabilities for pc, docker, and uv (SKILL.md).
Sanitization: None; values from the configuration files are passed directly to the CLI tools.

deploy