← ClaudeAtlas

map-product-systemlisted

Turn rough product ideas, conversations, documents, or an existing codebase into an end-to-end product system map covering user journeys, capability boundaries, platform and customer mandates, data lifecycles, agent/service/human responsibilities, architecture, failure paths, governance, and delivery slices. Use when the user asks to understand the whole product, find missing functions or branches, establish product foundations, decide what belongs in code versus mandates or configuration, design multi-agent responsibilities, audit product completeness, or convert a product concept into an executable architecture. Trigger on phrases such as “看一下产品结构”, “梳理产品架构”, “检查用户旅程和功能分支”, “review the product structure”, or “map the whole product”.
m1nga/skill-builder · ★ 0 · Data & Documents · score 72
Install: claude install-skill m1nga/skill-builder
# Map Product System Build a shared model of how the product works from user intent to system outcome. Accept raw, conversational, or mixed-language explanations directly; do not require an optimized prompt first. ## Operating principles - Preserve the product intent before adding structure. - Distinguish **Known**, **Inferred**, **Proposed**, and **Unknown**. Never present an invention as an existing fact. - Seek traceability, not a long feature wishlist. A system is well mapped when journeys, capabilities, decisions, data, actors, states, and failure handling connect end to end. - Separate product-wide foundations from tenant-specific behavior. - Make consequential design recommendations. Explain the tradeoff briefly instead of hiding behind an unranked option list. - Match depth to the request. Do not force a full architecture report onto a narrow question. - Run broad coverage checks internally; expose only the structure, gaps, and evidence that affect the user's decision unless an exhaustive artifact is requested. ## Choose the job 1. **Discover** — turn an early or incomplete idea into the first coherent system model. 2. **Audit** — inspect existing code, documents, diagrams, or behavior and identify gaps, contradictions, and accidental architecture. 3. **Evolve** — place a new feature or mandate into the existing model and trace its downstream effects. When sources exist, inspect them before proposing structure. Treat repository behavior and current documents as