The Agent Skills Directory

[SAFE]: The skill is composed of purely instructional markdown content and static reference templates. There is no executable code included in the skill package.
[COMMAND_EXECUTION]: The core instructions in SKILL.md explicitly mandate that the agent must not attempt to run timers, shell commands, or system notifications, ensuring that no unauthorized system actions are performed.
[EXTERNAL_DOWNLOADS]: The skill does not define any dependencies for Python or Node.js, nor does it attempt to fetch or execute remote scripts via network utilities.
[DATA_EXFILTRATION]: No network-enabled operations or access to sensitive local environment files (e.g., SSH keys, AWS credentials) were found.
[PROMPT_INJECTION]: The instructions focus on persona-driven support and do not contain patterns intended to bypass AI safety guardrails or leak system prompts.

adhd-support