The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides a command to download and execute an installation script directly from the vendor's repository using the curl | sh pattern.
[EXTERNAL_DOWNLOADS]: The skill fetches several external resources from the vendor's infrastructure:
The official installation script from raw.githubusercontent.com/greptimeteam/greptimedb/.
Sister skills (SKILL.md files) from docs.greptime.com/skills/.
A Python package greptimedb-mcp-server recommended for installation via pip.
A documentation repository via npx skills add targeting github.com/GreptimeTeam/docs/.
[COMMAND_EXECUTION]: The skill includes shell commands for database deployment and operations:
Containerized deployment using docker run.
Shell script execution for initial installation.
Local binary execution of the greptime database service.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external data (logs, traces, and metrics), creating an attack surface for indirect prompt injection.
Ingestion points: Ingestion protocols including OTLP, Prometheus, Loki, and Elasticsearch ingest APIs (SKILL.md).
Boundary markers: None explicitly defined in this entry-point skill for the processed data.
Capability inventory: Shell command execution (Docker, curl, shell), local file system access (via volume mounts and data-home configuration), and network operations (SKILL.md).
Sanitization: Relies on internal database parsing and the specialized greptimedb-pipeline sister skill for data transformation.

greptimedb-quickstart