The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends the installation of external tools and packages from the belt-sh and inference-sh organizations via npx skills add. It also references a remote installation guide at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
[COMMAND_EXECUTION]: The skill provides numerous examples for executing the belt CLI tool to log in, search for LLM applications, and run inference tasks with various models like Claude, Gemini, and Kimi.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill retrieves responses from external Large Language Models through the belt app run command, which are then brought into the agent's context.
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the model outputs.
Capability inventory: The skill uses the Bash tool to interact with the belt CLI for model inference.
Sanitization: No specific sanitization or filtering mechanisms for the external model responses are defined in the instructions.
[NO_CODE]: The skill consists exclusively of a SKILL.md file containing documentation and command examples; it does not distribute any standalone scripts or executable binary files.

llm-models