The Agent Skills Directory

[SAFE]: The skill is entirely composed of instructional Markdown files and does not contain any executable scripts, binaries, or code modules. It is identified as a methodology-only toolkit.
[SAFE]: No network operations such as curl, wget, or API calls were identified. The skill does not attempt to exfiltrate data or communicate with external servers.
[SAFE]: The skill does not access the local file system or sensitive configuration files. The sub-agents (decision-maker, problem-analyzer, and report-writer) include explicit 'What This Agent Should NOT Do' sections that forbid the writing of code, running of commands, or modification of files.
[SAFE]: No signs of prompt injection, obfuscation, or credential exposure were detected in the instructions or metadata. The content remains consistent with its stated purpose of applying philosophical principles to analytical workflows.

on-practice