一键导入
architect
Design complex system architectures, evaluate tradeoffs, and make critical technical decisions requiring deep reasoning
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Design complex system architectures, evaluate tradeoffs, and make critical technical decisions requiring deep reasoning
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Automated visual testing with Playwright MCP - test web apps, presentations, websites, and documents with scalable reviewer perspectives
Expert guidance on RAG (Retrieval-Augmented Generation) system design including chunking strategies, embedding selection, retrieval methods, and vector database choices
Deep code analysis identifying subtle bugs, security issues, performance problems, and architectural concerns requiring expert-level reasoning
Efficient context state inspection, task lifecycle management, and session tracking
Systematic codebase onboarding. Builds a mental model of a new or unfamiliar project by exploring structure, architecture, key data models, entry points, and auth patterns.
Systematically extract knowledge from scattered documentation to prevent catastrophic forgetting. Creates structured extraction reports with status tags.
| name | architect |
| description | Design complex system architectures, evaluate tradeoffs, and make critical technical decisions requiring deep reasoning |
| short_desc | deep tradeoff analysis for one system architecture |
| keywords | ["system design","tradeoff analysis","architecture decisions","component design","failure modes","design the system","architectural tradeoff","system architecture","architecture for"] |
| model | opus |
Purpose: Design complex system architectures, evaluate tradeoffs, and make critical technical decisions requiring deep reasoning.
Model: Opus 4.5 (expert reasoning, handles ambiguity, considers edge cases)
When to Invoke Autonomously:
Use this skill when:
DO NOT invoke for:
Is this task:
├─ Simple implementation? → Don't use this skill, just code
├─ Requires choosing between 3+ approaches? → Use this skill
├─ Involves system-wide changes? → Use this skill
├─ Has unclear requirements? → Use this skill
└─ Standard CRUD/patterns? → Don't use this skill
/architect design a [system/feature] that [requirements]
/architect evaluate [approach A] vs [approach B] for [use case]
/architect review [existing architecture] and suggest improvements
See template.md for architecture proposal structure.
Before implementing: Search for proven patterns
.claude/scripts/kg-search search "architecture" --type concepts
For deep research: Ask user "Use hybrid_search to research [system design]"
Development env: Python 3.12, Weaviate:8081, Ollama:11435, venv: source claude_mcp_servers/.venv/bin/activate
After completing architecture work:
knowledge/concepts/[architecture-pattern].md)Full reference:
~/.claude/shared/KNOWLEDGE_SYSTEMS.md
Decision tree:
kg-search CLI (fast, ~100ms)hybrid_search MCPsemantic_graph_search MCPsearch_code_graph MCPThis skill is working well if: