The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches specialized sub-skills from the official vendor domain at pydantic.dev to handle specific observability tasks like querying and UI access.
[COMMAND_EXECUTION]: The skill uses uvx or npx to execute the logfire whoami command, which is necessary to verify the current authentication state and project context.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes local project documentation to determine the appropriate monitoring strategy.
Ingestion points: Reads project files including README.md, AGENTS.md, and CLAUDE.md in Step 2.
Boundary markers: None explicitly defined in this entry-point skill.
Capability inventory: The skill can execute CLI commands (uvx logfire) and fetch additional remote instructions.
Sanitization: No specific sanitization or filtering is mentioned for the documentation content being read.
[CREDENTIALS_UNSAFE]: The skill references the use of .logfire/logfire_credentials.json for managing authentication tokens. It includes explicit security warnings against displaying, logging, or committing these tokens, following standard secret management practices.

logfire-setup