The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several command-line tools to manage the Hugo site.
Executes hugo list all via a Python subprocess in scripts/seo_posts.py to identify published content.
Uses git status and git log to identify recently changed files for processing.
Runs local Python scripts including scripts/seo_posts.py, scripts/site-search, and article_status.py for mechanical checks and logging.
Performs a full site build to a temporary directory using hugo --gc --minify to verify that internal links resolve correctly.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data which could contain malicious instructions.
Ingestion points: Reads blog post content (index.md) and external prompt configuration files (seo-front-matter.md).
Boundary markers: Absent; the skill treats the content of these files as data to be processed or rules to be followed.
Capability inventory: File system writes (editing posts), command execution (Hugo builds).
Sanitization: None; the skill relies on the LLM's ability to distinguish between content and instructions.
[EXTERNAL_DOWNLOADS]: The skill instructions mention downloading tools if they are missing.
Recommends brew install hugo and brew install python for environment setup. These are references to official software via a well-known package manager.

write-seo