← ClaudeAtlas

portfolio-operatorlisted

Evidence-grounded cross-domain portfolio control plane for deciding what a user or small team should focus on across products, client work, research/academic commitments, growth, operations, and side projects. Use when the user asks what to do this week/next 7-30 days across multiple projects, how to allocate limited capacity, which commitments conflict, what to pause/drop/delegate, how to reconcile client deadlines with product/research work, or for a portfolio-wide review. Do not use for deep prioritization inside one product/repo, release GO/NO-GO, or executing a multi-skill workflow when a specialist/control-plane skill owns that task.
CometWeb-io/agent-skills · ★ 1 · AI & Automation · score 74
Install: claude install-skill CometWeb-io/agent-skills
# Portfolio Operator Protocol version: **1.1**. Operate as a cross-domain allocation control plane. Reconstruct the smallest defensible portfolio truth, expose capacity conflicts, and return a bounded plan for the active horizon. Do **not** replace Product Operator. Product Operator owns deep state reconciliation and sequencing inside a specific product/repo. Portfolio Operator decides how much attention that product should receive relative to other commitments. Do **not** replace Skill Orchestrator. When the user wants a multi-skill workflow executed end-to-end, hand off to Skill Orchestrator rather than becoming a workflow engine. ## 0. Load the control plane Always read: - [references/source-routing.md](references/source-routing.md) - [references/portfolio-model.md](references/portfolio-model.md) - [references/prioritization.md](references/prioritization.md) - [references/delegation.md](references/delegation.md) - [references/output-contract.md](references/output-contract.md) Read [references/evaluation.md](references/evaluation.md) when changing, testing, or diagnosing the skill. When filesystem + code execution are available, use `scripts/portfolio_kernel.py` for deterministic ranking, capacity-conflict detection, report validation, and human rendering. Use `scripts/run_evals.py` when modifying the skill/kernel. Never claim a script ran if it did not. ## 1. Establish the portfolio contract Resolve from current context and connected sources before asking the us