ai-architecture-expert
Design a production AI architecture from zero or reconstruct an existing one using evidence, evals and explicit trade-offs. Use when the user requests ai architecture expert or invokes ai-architecture-expert. Do NOT use for an unrelated implementation change or deployment execution.
- License 许可
- CC-BY-4.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- ai-architecture-expert
- license
- CC-BY-4.0
- metadata
- { "author": "AEOS", "version": "1.0.0", "owner_agent": "codenavi-agent" }
- description
- Design a production AI architecture from zero or reconstruct an existing one using evidence, evals and explicit trade-offs. Use when the user requests ai architecture expert or invokes ai-architecture-expert. Do NOT use for an unrelated implementation change or deployment execution.
02 资源文件 2
- 参考文档references/provenance.md559 B
- 参考文档references/usage-and-verification.md1.0 KB
03 SKILL.md 正文
AI Architecture Expert
Governance: CodENavi Full Workspace v2. Skill of codenavi-agent; inherit AGENTS.md.
Lifecycle: BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF.
Source roles/workers are internal lenses. Never create agent identities or bypass runtime secret/permission gates.
Governance: CodENavi v1
Mission
Design a production AI architecture from zero or reconstruct an existing one using evidence, evals and explicit trade-offs.
Architecture planes
Ingestion/governance → canonical data → retrieval/indexing → model/inference → tools/agents → policy/guardrails → evals → observability → memory → delivery/rollback.
Decision tree
- Start with prompt + context baseline.
- Add lexical/vector/hybrid retrieval when knowledge grounding is the bottleneck.
- Add reranking when retrieval precision/ordering is limiting.
- Add fine-tuning/PEFT when behavior/style/task adaptation remains deficient after prompt/context improvements and a train/eval set exists.
- Add agents/tools only for tasks requiring actions or multi-step environment interaction.
- Every architecture has offline + online evals, security model, SLOs, cost budget and rollback.
Outputs
Current-state map, target architecture, ADRs, implementation sequence, interfaces, data contracts, threat model, eval plan, observability and migration/rollback plan.
Provenance and source freshness: provenance.
Example usage and failure handling: read usage and verification when selecting this skill or a required step fails.
04 同仓库更多 Skills
workspace-brain
Operate the CodENavi workspace brain MCP and CLI — cloud DeepSeek RAG, disk corpus at WORKSPACE_BRAIN_ROOT, Jev URL curation, and event logging for Cursor/Codex/OpenCode/Claude. Use when ingesting repo knowledge, asking the brain, mapping web seeds, or recording AI-driven file changes. Do NOT use for local Ollama RAG or storing API keys in git.
workbench-profile-resolver
Provide enterprise-grade capability for `workbench-profile-resolver` inside AEOS v1.1. Use when the user requests workbench profile resolver or invokes workbench-profile-resolver. Do NOT use for unrelated tools or unapproved remote writes.
wordpress-expert
Staff-level WordPress engineering super-skill for one-shot site mapping, clean-code AI-assisted project creation/modification, the complete installed plugin universe, governed remote wp-admin operations, themes/blocks/layout, third-party integrations and production-safe changes. Use when the user requests wordpress expert or invokes wordpress-expert. Do NOT use for unrelated languages, domains or production deployment.
whatsapp-simulator
Generate synthetic WhatsApp-style conversation fixtures for testing conversational systems, support flows and automation. Use when the user requests whatsapp simulator or invokes whatsapp-simulator. Do NOT use for unrelated tools or unapproved remote writes.
web-quality-audit
Assimilated TLC/web-quality multi-area audit. Review performance, accessibility, SEO and best practices in one pass. Triggers: audit my site, review web quality, check page quality, optimize my website across areas. Do not use for a single-area job (core-web-vitals, ai-seo, best-practices, perf-lighthouse).
voiceai
Provide an evidence-backed voice interface for AEOS. Activating this skill is treated as explicit current-session consent for `voiceai` to record user audio or transcribe audio from user-authorized audio/video media within the declared scope. The skill can: Use when the user requests voiceai or invokes voiceai. Do NOT use for unrelated tools or unapproved remote writes.