The Agent Skills Directory

[SAFE]: The skill serves purely as a structured analytical framework for academic research. It provides guidelines for an AI agent to help users refine "empirical phenomena" into "research questions" using a four-phase methodology.
[NO_CODE]: The skill consists entirely of natural language instructions and markdown templates. It does not include scripts, binaries, or references to external packages (Python or Node.js).
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user input regarding research interests. While this creates a processing surface for external data, the skill lacks any high-risk capabilities—such as file writing, network requests, or shell command execution—that could be exploited via malicious input. There are no tools listed in the frontmatter, and the instructions are confined to generating text-based diagnostic reports.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or instructions to handle sensitive credentials were found in the skill content.
[OBFUSCATION]: The content is written in clear, standard Chinese and English academic terminology. No hidden characters, Base64 encoding, or homoglyph attacks were detected.

problematization