The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill interacts with the Cerebras API to generate code, representing an external service dependency for core functionality.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-defined 'contract prompts' to generate source code, which creates a vulnerability surface for indirect prompt injection.
Ingestion points: Workflow Step 2 in SKILL.md where the prompt is passed to the generation tool.
Boundary markers: None identified; the skill does not specify delimiters or instructions to ignore embedded commands in the contract.
Capability inventory: The skill writes arbitrary files to the local disk via the mcp__speed-run__generate_and_write_files tool.
Sanitization: No sanitization, validation, or review step for the generated code is described before it is written to disk.
[DYNAMIC_EXECUTION]: The skill's primary purpose is the runtime generation and writing of executable code (e.g., FastAPI applications) based on high-level natural language specifications.
[COMMAND_EXECUTION]: The skill uses a tool to perform file system write operations (output_dir) based on output received from an external hosted LLM.

turbo