The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute gh (GitHub CLI) commands. This is used solely for read-only operations such as checking authentication status, listing repository tags, and comparing commit histories to identify recent code changes related to an alert.\n- [EXTERNAL_DOWNLOADS]: The skill instructions facilitate interaction with external monitoring platforms (e.g., Datadog, Grafana) via Model Context Protocol (MCP) servers and the GitHub API. These interactions are performed to retrieve operational data (metrics, logs, traces) and are targeted at well-known, trusted services.\n- [PROMPT_INJECTION]: The skill is designed to ingest and analyze data from external sources, which presents a surface for indirect prompt injection.\n
Ingestion points: Monitor configurations, logs, and commit messages are retrieved from external monitoring MCPs and the GitHub API.\n
Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions for the external data being processed.\n
Capability inventory: The agent has access to Bash, Read, Glob, and Grep tools, providing a broad capability set for investigation.\n
Sanitization: The skill does not explicitly sanitize log messages or commit data before presenting them to the LLM for analysis.

ops-investigate-alert