The Agent Skills Directory

[SAFE]: The skill operates entirely offline and strictly processes local text and markdown files provided by the user. It does not perform any network requests, API calls, or remote data fetching.
[SAFE]: The provided Python scripts (repurpose_analyzer.py, draft_fidelity_check.py, and repurpose_rules.py) rely exclusively on standard libraries (argparse, json, re, sys, pathlib). They perform deterministic text analysis using regular expressions and string matching without dangerous functions like eval() or exec().
[SAFE]: The skill includes explicit guidance for the agent to ignore instructions embedded within source text files, which effectively mitigates potential indirect prompt injection attacks from processed content.
[SAFE]: File access is restricted to reading provided input files and an optional local JSON story bank. No unauthorized persistence mechanisms or privilege escalation attempts were identified.

linkedin-content-repurposer