The Agent Skills Directory

[SAFE]: The skill follows established security best practices for administrative AI agents.
Guardrails for Destructive Operations: The SKILL.md file defines a strict "Destructive operations" tier. It requires the agent to calculate the blast radius, name the target explicitly, and wait for human approval before executing irreversible commands like deleting namespaces or terminating batches.
Private Key Security: In references/triage/certificates.md, the skill includes explicit warnings about private keys: "Never print, echo, cat, or log private-key contents," and "Restrict permissions (chmod 600), never commit it to source control."
Trusted Vendor Resources: All external references, such as GitHub repositories (github.com/temporalio/*), documentation links (docs.temporal.io), and Go modules (go.temporal.io/cloud-sdk), point to the official Temporal Technologies (the skill's author) infrastructure.
Standard Diagnostic Tools: The skill utilizes well-known network and security diagnostic utilities (openssl, nc, dig, nslookup, nslookup) for their intended purposes.
Safe Environment Variables: The skill instructs the agent to use standard environment variables for authentication (TEMPORAL_API_KEY, TEMPORAL_CLOUD_API_KEY) and provides clear distinctions between variables intended for different tools (tcld vs. temporal CLI).

temporal-ops