跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
AI 与知识库

ai-architecture-advisor

Chooses among AI/ML approaches: classical ML, LLM, RAG, fine-tuning, agents, multimodal, embeddings/recsys, dense/MoE/SSM/diffusion. Use when picking or scaling an architecture.

vasilyu1983 · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add vasilyu1983/AI-Agents-public --skill ai-architecture-advisor

技能说明


name: ai-architecture-advisor description: "Chooses among AI/ML approaches: classical ML, LLM, RAG, fine-tuning, agents, multimodal, embeddings/recsys, dense/MoE/SSM/diffusion. Use when picking or scaling an architecture." compatibility: Portable core. Works on Claude Code and Codex. version: "1.7" last_validated: 2026-07-11

AI Architecture Advisor

The front-door decision skill for "I have problem X — what should I build with?" It owns the choice — which approach fits, when to promote complexity (and when not to), how to transfer knowledge, how to scale — then hands off to the deep skill that owns the depth. It spans the whole modeling space in one place so you can compare options that normally live in separate skills side by side:

tabular GBDT  ·  deep net  ·  Transformer/LLM  ·  RAG  ·  fine-tuning  ·  agents
multimodal/omni  ·  embeddings & retrieval  ·  recsys/ranking  ·  model architecture (dense/MoE/SSM/diffusion)

No theory dumps — decision tables, elimination logic, tradeoffs, and a pointer to the deep skill.

The architect's move is to ask before answering. The amateur hears "build an AI feature" and reaches for the model they know ("we'll fine-tune Kimi"). The architect first asks: what data type? what volume? what task? what's the success metric? do you even need a Transformer? The skill that distinguishes an architect is the willingness to say "for this, CatBoost wins," "here you need a Transformer," or "LoRA is enough here" — and to refuse to name an approach until the problem is classified. Never jump to a model before the Intake questions below are answered.

ASCII Flow

problem + data + constraints
  |
  v
0. INTAKE — ask before answering (see questions below)
  |          do NOT name a model until task + data + metric + constraints are known
  v
1. classify the problem          (tabular? text? generation? decision/action? retrieval?)
  |
  v
2. eliminate ineligible options  (with a reason each — never silently drop)
  |
  v
3. score survivors independently (accuracy, latency, cost, data need, interpretability, ops)
  |
  v
4. pick the SIMPLEST that clears the bar   (start simple, promote only on evidence)
  |
  v
5. hand off to the deep skill    (ai-ml-data-science / ai-llm / ai-rag / ai-agents ...)

Intake: Ask Before You Answer

A request like "let's fine-tune model X" is a proposed solution, not a problem statement. Do not accept it at face value. Surface the six questions that decide the architecture, and hold any model name until they're answered. If the user can't answer one, that gap is itself a finding (most often: no success metric, or no labeled data).

AskWhy it changes the answer
What's the task? classify / rank / generate / extract / retrieve / actPicks the lane before anything else — tabular-classify and open-ended-generate share no architecture
What's the data? type (tabular/text/image/audio), volume, labeled? private? fresh?Tabular+small → trees; private/fresh knowledge → RAG not fine-tune; no labels → no SFT
What's the success metric & bar? accuracy / latency / cost-per-outcome / interpretability"Make it work" can't be scored; the binding constraint eliminates most options
What are the constraints? p99 latency, $/query at volume, on-prem/cloud, no-hallucinationA <50ms or AWS-only or no-hallucination constraint forces the design more than the task does
Is there a regulatory/compliance driver? high-risk classification (EU AI Act), data residency, right-to-explanation, audit trailCan force an inherently-interpretable model (trees, not a black-box net), ban sending data to a third-party API, or mandate human-in-the-loop — overriding an accuracy-only ranking
Do you even need an LLM/Transformer?The cheapest thing that clears the bar wins — often a tree, a regex, or a single API call beats a fine-tune

Breaking ties among survivors: hard constraints (a p99 ceiling, an on-prem requirement, a regulatory bar) are gates — fail one and the option is out, no matter how it scores elsewhere. Only among options that clear every gate do the soft criteria (cost, developer familiarity, marginal accuracy) act as tie-breakers. Don't let a soft criterion overrule a failed hard constraint, and don't eliminate an option on a soft criterion before checking whether a rival actually clears every gate.

Quick Reference

You're choosing betweenDefault first movePromote whenDeep skill
Tabular model familyGradient-boosted trees (XGBoost)Within a tabular foundation model's envelope (TabPFN-3 ≤~1M rows; TabICL v2 if open-source) it now beats tuned GBDTs thereai-ml-data-science
Trees vs deep learning (tabular)TreesHuge data + raw signals (images/text/audio) embedded in featuresai-ml-data-science
Thinking effort on one modelLow/no thinkingGap is multi-step logic/planning: raise the thinking budget (it's a dial, not a separate model) before fine-tuningai-llm
LLM prompt vs RAGPrompt-onlyNeeds current/private knowledge or citations (and the corpus won't fit affordably in a long-context window)ai-rag
RAG vs fine-tuningRAGBehavior/format gap persists after RAG+prompt fixes; combine both (RAFT) for domain-specific RAGai-llm
Adapt vs post-train (RLHF/DPO/GRPO)Prompt → RAG → SFT firstBehavior/preference/reasoning gap survives SFT and you own preference or verifiable-reward dataai-post-training
Single LLM call vs agentSingle call / workflowNeeds tools (via MCP), multi-step planning, or external actionsai-agents
Omni model vs specialist pipelineOmni/VLM to validateAccuracy KPI, cost-at-volume, or no-hallucination ne
阅读完整来源 ↗