The Agent Skills Directory

[SAFE]: The skill operates within a restricted set of file-manipulation tools (Read, Write, Edit, Grep, Glob) and provides specific, evidence-based instructions for academic writing. No malicious command execution or unauthorized file access patterns were detected.
[SAFE]: All external references and mentioned services such as Semantic Scholar, PubMed, Zenodo, Hugging Face, and arXiv are well-known, trusted academic services appropriate for the skill's stated purpose.
[SAFE]: The skill includes explicit anti-hallucination and verification instructions, such as 'Never fabricate citations, DOIs, arXiv IDs' and 'Surface the checklist in the response. Never apply AIO edits silently', which act as internal safeguards for both data integrity and user transparency.

academic-aio