The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute the wewrite stats command and the fetch_stats.py script. These operations are required for the skill's primary function of data synchronization and analysis.
[EXTERNAL_DOWNLOADS]: The instructions recommend installing the wewrite CLI tool using uv tool install wewrite or by executing an install.sh script within the repository. These are standard procedures for installing functional command-line utilities.
[PROMPT_INJECTION]: The skill processes content fetched from the WeChat API (article metadata and engagement metrics). This creates a potential surface for indirect prompt injection if external data contains instructions intended to manipulate the agent.
Ingestion points: External data from the WeChat Official Accounts API via fetch_stats.py (SKILL.md).
Boundary markers: None identified; the instructions do not specify delimiters or warnings for the agent when processing external API data.
Capability inventory: The skill is granted Bash, Read, Write, and Edit permissions (SKILL.md).
Sanitization: The skill does not explicitly describe any sanitization or validation procedures for the ingested API content.

wewrite-stats