The Agent Skills Directory

[SAFE]: The skill is composed exclusively of Markdown documentation and reference materials designed to guide an AI in structured prompt construction for video generation.
[NO_CODE]: No executable scripts (Python, JavaScript, Shell) are present in the skill directory. All functionality is delivered through natural language instructions.
[COMMAND_EXECUTION]: The skill does not invoke or suggest the execution of arbitrary shell commands. It references a set of pre-defined Higgsfield MCP tools for media generation and management, which are scoped within the platform's allowed tools.
[DATA_EXFILTRATION]: There are no indicators of data exfiltration. The skill does not perform network requests to untrusted domains and does not access sensitive local file paths (e.g., SSH keys, AWS configs).
[CREDENTIALS_UNSAFE]: No hardcoded API keys, secrets, or tokens were detected across any of the analyzed files.
[PROMPT_INJECTION]: The instructions follow standard operational guidelines for prompt crafting and do not contain directives aimed at bypassing safety filters or overriding core agent behaviors.
[EXTERNAL_DOWNLOADS]: The skill does not perform any remote package installations or script downloads. All reference materials are local to the skill's structure.

higgsfield-cinematic