The Agent Skills Directory

[SAFE]: The skill's primary function is local text processing using a character mapping table. It does not execute arbitrary shell commands, access sensitive files, or perform hidden network operations.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text for formatting.
Ingestion points: User input text provided for bold/italic conversion (SKILL.md).
Boundary markers: None explicitly defined in instructions.
Capability inventory: Mentions potential use of strategist_briefing and linkedin-publish tools if available in the environment.
Sanitization: The skill uses a strict character-level mapping logic that only targets alphanumeric ranges, effectively filtering out unexpected control characters or code during the formatting process.
[EXTERNAL_DOWNLOADS]: The skill provides instructions for adding an MCP (Model Context Protocol) server via the command claude mcp add --scope user --transport http liftli https://mcp.liftli.ai/mcp. This URL belongs to the skill's vendor and the instruction is provided as a transparent, user-initiated action to extend functionality.

linkedin-text-formatter