The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references and provides commands to install the belt-sh/cli and inference-sh/skills from external sources. These are standard platform components required for the skill to function as intended.- [COMMAND_EXECUTION]: The skill uses the belt command-line interface to execute various application tools, including x/post-create for social media interaction, infsh/html-to-image for asset creation, and infsh/agent-browser for web interaction. These commands are integral to the skill's documented workflow.- [PROMPT_INJECTION]: The skill design includes an attack surface for indirect prompt injection.- Ingestion points: The agent ingests data from external sources through the tavily/search-assistant and infsh/agent-browser tools.- Boundary markers: The provided instructions do not include specific boundary markers or 'ignore' instructions for content retrieved from external sources.- Capability inventory: The agent is equipped with the x/post-create tool, which allows it to write content to a public social media platform.- Sanitization: The skill does not prescribe specific sanitization or validation steps for content fetched from the web before it is used in outbound social media posts.

twitter-thread-creation