The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to automate development workflows and content publishing.
It utilizes curl to interact with the GitHub Contents API for uploading blog posts to the author's repository (Gingiris-1031/growth-tools).
It executes local scripts such as citability-scorer.py and sync-i18n.py to process and validate blog content.
It uses common shell utilities like base64, source, and grep for environment configuration and data formatting.
[PROMPT_INJECTION]: The skill processes data from external sources and other agent skills, creating a surface for indirect prompt injection.
Ingestion points: The skill reads inputs from other agent skills (keyword data and competitor research) to guide article generation.
Boundary markers: The instructions do not specify explicit delimiters when processing the ingested keyword or competitor data.
Capability inventory: The skill possesses capabilities to read local configuration files, execute shell commands, and write to remote GitHub repositories.
Sanitization: No specific sanitization or validation logic is defined for the data ingested from competitor research or keyword tools.

gr-blog-post