The Agent Skills Directory

[SAFE]: The skill serves as a legitimate guide for Bluesky content strategy and AT Protocol API interaction. It uses standard placeholders for authentication and targets well-known official service domains.
[COMMAND_EXECUTION]: The skill provides documentation for executing curl commands to interact with the AT Protocol API. These are presented as instructional templates for the agent to perform search, profile retrieval, and post creation operations via the official bsky.social endpoint.
[INDIRECT_PROMPT_INJECTION]: The skill features a surface for processing external data through search queries and profile lookups.
Ingestion points: External data enters the agent context via the app.bsky.feed.searchPosts and app.bsky.actor.getProfile API calls based on user-supplied keywords or handles.
Boundary markers: The skill does not define specific delimiters or "ignore instructions" warnings for the content returned by these API calls.
Capability inventory: The skill includes network writing capabilities (com.atproto.repo.createRecord) to publish content to the network.
Sanitization: No specific sanitization or filtering logic is provided for external content before processing or re-posting, relying on standard agent guardrails.

bluesky