The Agent Skills Directory

[SAFE]: The skill is composed entirely of Markdown documentation (SKILL.md, references/, examples/). There are no scripts (Python, JS, Shell) or binary executables included in the skill package.
[SAFE]: The skill uses a structured, multi-phase prompting approach to guide the AI's reasoning. It includes explicit 'Anti-Sycophancy' rules to ensure the AI provides objective, critical feedback rather than simply agreeing with the user.
[SAFE]: No hardcoded credentials, API keys, or sensitive environmental data were found in any of the files.
[SAFE]: No remote code execution patterns, external package installations, or obfuscated payloads were detected. The URLs provided in the documentation are strictly for context or internal file references.
[SAFE]: The skill does not request or use any specialized tools that would grant it elevated privileges on the host system. It operates within the standard conversational boundaries of the AI agent.

axiom