The Agent Skills Directory

[SAFE]: The skill requests organizational and technical context, such as team dynamics and architecture, to assist in high-quality documentation drafting. These operations are conducted through authorized platform integrations and direct user input, which is consistent with the skill's primary purpose.
[SAFE]: The skill involves ingesting data from external sources like team messaging channels and shared documents. While this represents a surface for indirect prompt injection, the skill adheres to standard interaction models and does not include instructions designed to maliciously leverage or execute external data.
Ingestion points: Stage 1 and Stage 2 facilitate reading from messaging integrations and external document links (SKILL.md).
Boundary markers: The instructions do not explicitly mandate the use of delimiters for ingested external context.
Capability inventory: The skill utilizes create_file and str_replace for document editing and uses sub-agents for verification.
Sanitization: No explicit sanitization or filtering is applied to the ingested external content.

doc-coauthoring