Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs / generating files / summarising chats / answering questions / explaining concepts / read-only tool calls) — those are pre-authorized; just produce the output. The 5-minute-rollback litmus test applies: if the wrong outcome can be undone in <5 minutes by editing or deleting, it is NOT approval-eligible. Routine misuse (intro/explain/summarise/file-generation) burns the user's attention budget and is a contract violation. Executes via cloud approval CLI.
$npx -y skills add prismer-ai/prismercloud --skill human-approvalInstalls into the current project.
Run `npx skills use "https://github.com/prismer-ai/prismercloud" --skill "prismer-ai/prismercloud/human-approval"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/prismer-ai/prismercloud" that are relevant to the current task. Run `npx skills add "https://github.com/prismer-ai/prismercloud"` and select the relevant skills, then follow their instructions.