The Agent Skills Directory

[SAFE]: The skill provides educational content and productivity strategies without any malicious behavior. It emphasizes privacy by explicitly stating that no data leaves the user's machine and no network requests are made.
[NO_CODE]: The skill consists entirely of Markdown documentation, configuration files, and instructions. It does not include any executable scripts, binaries, or external dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill implements a persistent memory system by reading from and writing to ~/productivity/memory.md. While this creates an ingestion point for user-controlled data, the risk is negligible as the skill lacks high-privilege capabilities such as network access or arbitrary command execution.
Ingestion points: Reads user preferences from ~/productivity/memory.md (referenced in SKILL.md and memory-template.md).
Boundary markers: The instructions guide the agent to learn only from explicit statements, but no specific technical delimiters for the file content are defined.
Capability inventory: The skill is limited to providing text-based advice and performing basic file operations in a dedicated user directory. No network or system-level capabilities are identified.
Sanitization: No explicit sanitization or validation of the memory file content is performed.

Productivity