The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the official @operately/operately-cli package from the NPM registry. This is a standard and expected distribution method for the tool.
[COMMAND_EXECUTION]: The skill relies on executing the operately CLI to perform project management and collaboration tasks as detailed in SKILL.md and the reference documentation.
[PROMPT_INJECTION]: The skill contains a surface area for indirect prompt injection.
Ingestion points: The agent retrieves and processes markdown data (documents, descriptions, and check-ins) from the Operately platform using commands like operately documents get or operately projects get (found in SKILL.md and resource-hubs.md).
Boundary markers: There are no explicit instructions or delimiters mentioned to help the agent distinguish between platform data and system instructions.
Capability inventory: The agent can execute shell commands through the CLI, modify data on the platform, and write output to the local file system (described in SKILL.md).
Sanitization: No validation or sanitization of content retrieved from the platform is documented before the agent interpolates it into its context.

operately-cli