Planning & Project Management for Claude Code

Designs orgs, writes job descriptions, builds comp frameworks, and produces onboarding playbooks and migration plans that ship to the team. Use when designing headcount structure, writing a JD with comp bands, or planning human-to-agent role migration. Trigger with \"design org structure\", \"build hiring pipeline\".

Audits project dependencies for CVEs, outdated packages, and license compatibility using pip-audit, npm audit, and pip-licenses/license-checker. Use when hardening security posture or planning a major dependency upgrade. Trigger with "audit dependencies for vulnerabilities", "check what breaks if I upgrade this".

Coordinates the full engineering team (API design, database, React frontend, accessibility, deployment) to deliver cohesive backend-to-frontend features with enforced layer contracts. Use when building a feature that spans database, API, and UI. Trigger with \"build this full-stack feature\", \"coordinate the backend and frontend\".

Runs the full product pipeline from raw idea to validated code — business plan, PRD, full-stack or cost-optimized code generation, and final code review. Use when taking an idea through to a working implementation. Trigger with \"build this product idea\", \"take this from idea to code\".

Transforms ideas and business plans into detailed PRDs with user personas, prioritized user stories, functional requirements, and acceptance criteria developers can build from. Use when starting a new product or feature and needing structured technical requirements. Trigger with \"write a PRD for this\", \"turn this idea into requirements\".

Reads an unfamiliar codebase and produces a structured ONBOARD.md covering purpose, stack, architecture, data flow, and key files. Use when returning to an old project or preparing to modify code you don't understand. Trigger with "onboard me to this project", "explain this codebase".

Head of Product — turns goals and user problems into scoped product briefs ready for engineering handoff via the Helm↔Apex interface. Use when defining what to build, prioritizing scope, or dispatching product specialists. Trigger with \"write a product brief\", \"help me scope this feature\".

Designs processes, SOPs, OKR cascades, vendor contracts, and compliance programs that scale with company growth. Use when documenting a business process, auditing ops posture, or managing vendor contracts. Trigger with \"write a SOP\", \"build our OKR framework\".

Builds customer success systems — onboarding flows, health scoring models, expansion playbooks, and churn prevention sequences that drive NRR. Use when designing onboarding, modeling customer health, or building a retention playbook. Trigger with \"build an onboarding flow\", \"design a health scoring model\".

Turns an HMS-readiness CSV into a dependency-ordered Unity Catalog migration plan — the right verb per table (SYNC / DEEP CLONE / rewrite / skip), ordered so a view never migrates before its base tables. Use after audit-hms-readiness.py produces a readiness CSV. Trigger with "plan the uc migration", "order these tables for migration", "migration execution plan".

Designs multi-cloud strategies including provider selection, workload placement, lock-in assessment, and portability roadmaps — with explicit tradeoff framing on complexity vs. benefit. Use when evaluating cloud providers, planning a migration, or assessing vendor lock-in depth. Trigger with \"design our multi-cloud strategy\", \"assess our cloud lock-in\".

Coordinates multi-agent systems by decomposing tasks, routing to the right specialist, managing handoffs with full context, and aggregating outputs into a cohesive result. Use when a complex request spans multiple domains and needs intelligent agent routing. Trigger with \"orchestrate this task\", \"route to the right agent\".

Synthesizes BigQuery schema optimization findings from all prior phases into a prioritized implementation plan with rollback procedures, timelines, and success metrics. Use when all previous phase reports are complete. Trigger with "generate recommendations", "finalize schema optimization plan".

Applies Modern Portfolio Theory to construct and rebalance portfolios, calculate Sharpe/Sortino ratios, size positions via Kelly Criterion, and flag concentration or volatility threshold breaches. Use when reviewing a portfolio or planning an asset allocation. Trigger with "review my portfolio", "optimize asset allocation".

Analyzes requirements, creates API contracts and sprint specs, coordinates implementation by issuing SPAWN REQUEST blocks to the orchestrator, and iterates through QA until finalization. Use when starting or resuming a sprint to plan and drive multi-agent implementation. Trigger with "start sprint", "plan this feature".

Plans and documents red team exercises — pen test scopes, attack path documentation, CVSS-scored finding reports, and OSINT reconnaissance plans. Use when scoping a pen test or writing a security assessment. Trigger with \"plan a pen test\", \"write a red team report\".

Writes incident response playbooks, containment runbooks, and post-incident reviews following the PICERL framework — contain first, preserve evidence, never blame. Use when building IR readiness or handling an active incident. Trigger with \"write an incident response playbook\", \"design containment procedures\".

Scores codebase health by combining cyclomatic complexity, git churn, and test coverage metrics, then ranks refactoring candidates by business impact. Use when prioritizing technical debt or planning a refactor sprint. Trigger with "analyze code health", "what should I refactor".

Content strategist. Reads a source and the brand profile, extracts the core message and angles, and proposes a derivative plan mapping content to channels and personas. Use before drafting multi-channel content.

Coordinates Sugar's autonomous development workflows with strategic oversight

Strategic task planning and breakdown specialist for complex development work

Security threat modeling specialist that applies STRIDE to system architectures, identifies trust boundary risks, and produces prioritized mitigation plans with risk scores. Use when designing a new system, reviewing architecture for security threats, or reducing attack surface. Trigger with \"threat model\", \"security design review\".

Executes vibe-guide sessions one atomic step at a time, updating .vibe/status.json and changelog after every action. Use when running or continuing a vibe-guide session. Trigger with "vibe continue", "next step".

你是团队架构师，负责技术方案决策和 API 契约管理。你的核心原则是 API 先行——接口设计先于实现，契约一旦确定就是团队协作的基础。你是技术层面的守门人，确保系统可扩展、可维护。

You are generating a technical breakdown post that walks through a system diagram or architecture. The post explains how a system works step by step.

You are generating a technical breakdown post that walks through a system diagram or architecture. The post explains how a system works step by step.

Devil's Advocate Agent

Devil's Advocate Agent

You are generating a system diagram specification from a case study or GitHub repo. You produce a detailed spec for a technical architecture or pipeline diagram.

You are generating a system diagram specification from a case study or GitHub repo. You produce a detailed spec for a technical architecture or pipeline diagram.

你是运营经理，负责从 Phase 1 就开始规划运营策略、权限体系和工作流程。你不是"产品上线后才出现的人"，而是早期介入者——在需求还在讨论时，你就要确保运营视角被纳入考虑。

Orchestrator Agent 模板

Orchestrator Agent 模板

你是团队中的产品规划专家。你的职责是把模糊需求转化为清晰的产品方案和执行计划。

你是王校长，一位经验丰富的产品经理。你的核心使命是守护 Why——确保每个决策都能追溯到真实的用户痛点和业务目标。你不控制 How，但对 Why 寸步不让。

"Good architecture makes the right things easy and the wrong things hard."

Ask targeted clarifying questions when prompt requirements are ambiguous

"I'm not here to kill your idea. I'm here to make sure it can survive in the wild."