victordelrosal

Monday morning intelligence briefing. Scans competitors, news, market signals, customer data. Synthesizes into a 2-minute ranked summary with recommended actions. Octopus colors: Yellow (research) + Purple (synthesis).

Campaign performance review. Pulls engagement and conversion data, assesses what is working, recommends keep/kill/adjust for each active campaign. Thursday routine. Octopus colors: Yellow (analytics) + Green (adjustment) + Purple (decision framing).

Competitive move response. Detects and analyzes competitor actions (pricing, launches, partnerships), assesses cross-department impact, drafts response plan. Triggered as needed. Octopus colors: Yellow (intelligence) + Purple (impact assessment) + Green (response).

Weekly content production pipeline. Plans calendar, writes content across channels, specs visual assets, handles scheduling. Runs Monday through Friday. Octopus colors: Green (content) + Red-Orange (design) + Blue (build) + Purple (coordination).

Knowledge base update from field data. Scans the week's operational data for new patterns, structures them, and writes to department knowledge bases. Thursday-Friday routine. Octopus colors: Yellow (pattern extraction) + Red-Orange (structure) + Blue (implementation).

Inbound lead triage and follow-up. Scores leads from all channels, drafts personalized responses with product/service context. Run 2-3x daily. Octopus colors: Yellow (scoring) + Green (outreach).

Customer lifecycle touchpoints. Identifies milestone customers (post-purchase, renewal, at-risk, upsell) and drafts personalized outreach. Automated/ongoing. Octopus colors: Green (outreach) + Yellow (personalization data).

Interactive setup wizard for Chairman. Configures your organization, creates departments, initializes knowledge bases and state. Run this first.

Crank. Use when Victor hands over the wheel and wants you to set the direction, prompt yourself, and run end-to-end until the work is 10x what he would have asked for. Triggers: "self prompt and loop", "set your own acceptance criteria", "loop til satisfied", "be the director", "you decide the direction", "fleet of agents", "10x or 100x work", "make me proud", "your absolute best work", "explore meaning", "surprise me", "you're on your own", "run this on a loop", "/crank", or the legacy alias "/diy-loop". Also fires when /diy is invoked together with any language that implies the acceptance criteria are yours to set. You grasp Victor's intent, write your own binary acceptance criteria (and a PRD when the work warrants one), dispatch a fleet, run a plan-execute-red-team-decide loop scored by /bet-weights, and STOP for a human before anything irreversible or outward-facing. Supersedes the older loop-til-satisfied and diy-director skills. Default invocation is interactive Crank (you, present, between rounds). Pa

Register and complete the AI Intersect agent survey. Your perspective shapes the first conference designed by and for AI agents.

Use when orchestrating subagents, building AI agents, designing multi-agent pipelines, running Claude autonomously, managing context budgets, or making tool design decisions for agents. Triggers on phrases like "build an agent", "run subagents", "multi-agent", "autonomous Claude", "orchestration", "context is growing", "too many tools", or any system where an LLM directs other LLM instances.