The Agent Skills Directory

[SAFE]: The skill consists of purely instructional markdown content based on the book "The Almanack of Naval Ravikant". It provides advice on how to build a reading habit, prioritized learning, and effective interpretation of texts.\n- [NO_CODE]: No scripts (Python, JavaScript), executables, or shell commands are included in the skill package. All logic is contained within natural language instructions.\n- [DATA_EXFILTRATION]: The skill does not perform any network operations (e.g., curl, wget) and does not access sensitive system paths or credentials.\n- [OBFUSCATION]: Analysis of the markdown text and metadata did not reveal any hidden content, zero-width characters, or encoded strings.\n- [PROMPT_INJECTION]: The instructions do not contain attempts to override agent safety protocols or bypass restrictions; the instructions are consistent with the stated purpose of habit formation.\n- [INDIRECT_PROMPT_INJECTION]: The skill does not ingest external or untrusted data, significantly limiting the surface area for indirect injection attacks.

reading-metaskill