The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a series of included Python scripts to manage the paper analysis workflow, such as run_pipeline.py and write_obsidian_note.py. It includes logic to identify a suitable Python 3.10+ interpreter on the host system to ensure script execution.
[EXTERNAL_DOWNLOADS]: The skill fetches research paper content and metadata from well-known services including arXiv, Semantic Scholar, and OpenAlex. These operations are core to the skill's functionality and target reputable academic repositories.
[PROMPT_INJECTION]: The skill processes external PDF files, which introduces a surface for indirect prompt injection. Malicious instructions within a paper could theoretically attempt to subvert the agent's summarization logic. The skill mitigates this by employing a 'Style Gate' and a linting script (lint_note.py) to verify the structure and language of the generated output.

deeppapernote