The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute packages from the npm registry, specifically @przeprogramowani/10x-cli and skills@1.5.26. It also retrieves documentation from the vendor's GitHub repository at github.com/przeprogramowani/10x-cli. These actions align with the skill's purpose as a vendor-authored guide.
[COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands through the 10x_cli runner, including authentication, content synchronization, listing course modules, and running diagnostic checks. It also utilizes standard shell utilities like test and npm view to verify the local environment and package metadata.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external files and tool outputs, creating a vulnerability surface where third-party content could influence agent behavior.
Ingestion points: Reads local files such as context/foundation/shape-notes.md and parses JSON output from 10x_cli doctor --json.
Boundary markers: While the skill provides a structured workflow (init, shape, PRD), it does not employ explicit delimiters or system-level warnings to isolate untrusted data being read into the prompt.
Capability inventory: The agent is empowered to execute shell commands via the 10x_cli tool and perform file operations (read/write) within the project structure.
Sanitization: The instructions explicitly direct the agent to redact credentials and sensitive information from diagnostic data before processing or sharing it.

10x-cli-guide