The Agent Skills Directory

[SAFE]: The skill provides a set of markdown-based templates and procedural guidelines for project management. It does not include any executable scripts, binaries, or logic that interacts with the underlying operating system.\n- [PROMPT_INJECTION]: Analysis of the workflow instructions reveals no patterns associated with prompt injection, such as attempts to bypass safety filters, extract system prompts, or override agent instructions. The skill maintains a professional and task-oriented tone.\n- [DATA_EXFILTRATION]: No sensitive file paths, environment variables, or hardcoded credentials were detected. The skill does not contain any network communication logic or commands that could be used for data exfiltration.\n- [EXTERNAL_DOWNLOADS]: There are no references to external scripts, packages, or remote repositories. The skill operates entirely on user-provided feature descriptions and internal logic.\n- [COMMAND_EXECUTION]: The skill does not use subprocesses, shell commands, or other mechanisms to execute arbitrary system commands. Mentions of task management tools are limited to descriptive examples of workflow integration.

speckit-workflow