The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes data from external sources such as messaging channels and shared document platforms to gather context for documentation.
Ingestion points: Context is pulled from links, shared documents, and team communication channels via MCP servers or connectors.
Boundary markers: No explicit delimiters or instructions are used to ignore embedded prompts in the gathered context.
Capability inventory: The skill can create and modify files using create_file and str_replace and invoke sub-agents for testing.
Sanitization: No sanitization of external content is specified before processing.
[EXTERNAL_DOWNLOADS]: The skill is installed from the official Anthropic skills repository via the skills CLI.
[SAFE]: No malicious code, obfuscation, or unauthorized access to sensitive local files was detected. The use of file manipulation tools is strictly limited to drafting documentation as per the skill's stated purpose.

doc-coauthoring