The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown files (SKILL.md and dynamic-questioning.md) providing behavioral instructions. No executable code or scripts are included in the package.\n- [PROMPT_INJECTION]: The skill employs strong directive language such as 'MANDATORY' and 'SOCRATIC GATE' to enforce a specific communication workflow. These instructions are intended to improve task clarity and do not target safety filters, system prompt extraction, or model jailbreaking.\n- [COMMAND_EXECUTION]: The requested tools ('Read', 'Glob', 'Grep') are limited to read-only file system operations. While the text mentions 'Auto-install' in an error handling context, the skill does not request or provide the means (like a shell or package manager tool) to execute such commands.

brainstorming