The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs official observability packages such as opik and opik-ts using standard package managers like pip or npm. These packages and the referenced documentation are provided by the verified vendor comet-ml.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform configuration checks (e.g., opik healthcheck) and run code verification paths. It includes strict instructions to only execute safe, non-production commands and to stop immediately if verification cannot be performed autonomously and safely.
[INDIRECT_PROMPT_INJECTION]: The skill reads and instruments untrusted source code within the user's project to add observability.
Ingestion points: Project source and configuration files (e.g., pyproject.toml, package.json, and source code files) are accessed via Read, Grep, and Glob tools.
Boundary markers: The instructions do not define specific boundary markers to isolate untrusted file content from the agent's internal reasoning.
Capability inventory: The skill has the ability to Edit and Write to the filesystem and execute commands via Bash.
Sanitization: No explicit content filtering or sanitization is mentioned for the ingested file content.

opik-instrument