Manages long-lived agent workloads with runtime lifecycle, observability, safety controls, metrics tracking, incident response, and integrations for PM2, systemd, containers, CI/CD.
From everything-claude-codenpx claudepluginhub sandaruwanweerawardhana/claude-codeThis skill uses the workspace's default tool permissions.
Drafts personalized cold emails, warm intros, follow-ups, updates, and comms for investor outreach to angels, VCs, and accelerators during fundraising.
Implements iterative retrieval pattern with dispatch-evaluate-refine loop to progressively gather relevant codebase context for subagents in multi-agent workflows.
Creates consistent pitch decks, one-pagers, investor memos, financial models, accelerator apps, and fundraising materials from a single source of truth.
Use this skill for cloud-hosted or continuously running agent systems that need operational controls beyond single CLI sessions.
When failure spikes:
This skill pairs with: