The Agent Skills Directory

[SAFE]: The skill consists exclusively of instructional Markdown content (SKILL.md and README.md). It defines a cognitive methodology for the AI (Observation, Hypothesis, Evidence, Conclusion, Verification) and contains no scripts, binaries, or automated tasks.
[PROMPT_INJECTION]: While the skill uses authoritative language to enforce its reasoning loop (e.g., 'Violating the letter of the rules is violating the spirit of the rules'), these instructions are internal to the reasoning framework and do not attempt to bypass AI safety filters, extract system prompts, or override platform-level constraints.
[DATA_EXFILTRATION]: No network commands (such as curl or wget) or references to sensitive file paths (such as .env, SSH keys, or cloud credentials) were found. The skill does not possess the capability to move data to external servers.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts. The npx command mentioned in the README.md is a standard installation instruction for the user to add the skill to their environment and is not executed by the skill itself at runtime.

master-brain