agentsop-framework-selection
Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph, LlamaIndex, DSPy, CrewAI, vLLM, Aider, Dify) into one layered rubric. Core stance: frameworks are LAYERS, not competitors — a real project usually combines DSPy (compile) + LlamaIndex (retrieve) + LangGraph (orchestrate) + vLLM (serve), and you choose ONE per layer, not one to rule all. Use when starting any LLM/agent/RAG project, or whenever the "which framework?" question is asked. Deliberately neutral
npx skills add agentsope/SkillAlchemy --skill agentsop-framework-selection --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides project kickoff by identifying required layers (modeling, retrieval, orchestration, serving, app platform, coding-surface) and assigns a per-layer framework choice, treating frameworks as layers in a stack rather than competitors.
How it works
- Activation: use at project kickoff when a framework hasn’t been chosen or when asked which framework to use.
- Core model: emphasizes a layered stack where each layer is selected separately and interop is checked; warns against fighting for a single framework across layers.
- SOP procedure: Pass A identifies needed layers; Pass B applies per-layer fit rubrics; Pass C checks interop and a gate on framework necessity.
- Per-layer rubrics: provides explicit guidelines for selecting L1 (prompting/compiler), L2 (retrieval), L3 (orchestration), L6 (serving), L7 (app platform), and the coding-surface; includes references to other SOPs for detailed implementation.
- Interop: cautions about additive vs same-layer collisions and provides an interop map example.
When to use it
Use when starting any LLM/agent/RAG project or whenever the question "which framework?" arises. Activate again only when a new layer appears or a new project phase triggers a layer decision (e.g., self-hosting, UI, or repo-state gating).
What it can touch
- L1/L2/L3/L6/L7 layers plus coding-surface as needed.
- It references and situates decisions with other SOPs (e.g., dspy-sop, llamaindex-sop, langgraph-sop, verder) but does not teach their APIs.
Caveats
- Neutral stance: does not endorse any vendor-specific framework; presents layers and interop considerations.
- Emphasizes per-layer decisions and interop checks; does not guarantee optimal production choice without considering interop constraints.
- Open-source license MIT; tool guidance includes usage of per-layer gates like [[agentsop-llm-engine-selection]] and [[agentsop-repo-state-gating]].
# Framework-Fit Decision Tree at Project Kickoff · SOP (ENHANCE overlay) > Overlay posture: this is the **capstone** Phase-D skill — the most-cited entry > at any project kickoff. It decides *which layer(s) you need* and *which > framework owns each layer*. It does **not** teach any framework's API; for that, > descend to the per-framework SOPs (`langgraph-sop`, `llamaindex-sop`, > `dspy-sop`, `crewai-sop`, `vllm-sop`, `aider-sop`, `dify-sop`). Every > load-bearing claim carries an inline source tag resolving in > `references/R1-decision-tree.md`. > > Neutrality note: vendor pages each claim the center of the universe > (LangChain: "use LangGraph for production"; LlamaIndex: "the document agent > platform"; Dify: "scaffolding is the bottleneck"). This skill quotes those > claims but does not adopt any of them. The 7 SOPs *disagree* on the crossover > points; we surface the disagreements rather than papering over them. --- ## 1. 何时激活 (When to Activate) Activate when **any** of the following fire: - A new LLM / agent / RAG project is starting and no framework has been chosen yet. - Someone asks "which framework should I use?" / "LangChain or LlamaIndex?" / "LangGraph vs CrewAI?" / "d
- 1. 何时激活 (When to Activate)
- 2. 核心心智模型 (Core Mental Model)
- 3. SOP (The Procedure)
- 4. 操作模型 (Operations)
- G0 — The "do you even need a framework?" gate (run per layer)
- OP-1 — Layer identification (Pass A)
- OP-2 — L1 Modeling pick rubric
- OP-3 — L2 Retrieval pick rubric
- OP-4 — L3 Orchestration pick rubric
- OP-5 — L6 Serving pick → delegate
- OP-6 — L7 App-platform pick rubric
- OP-7 — Coding-agent surface pick → gate first
- OP-8 — Interop check (Pass C)
- 5. 困境决策案例 (Dilemma Cases)
What does the agentsop-framework-selection skill do?
Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph, LlamaIndex, DSPy, CrewAI, vLLM, Aider, Dify) into one layered rubric. Core stance: frameworks are LAYERS, not competitors — a real project usually combines DSPy (compile) + LlamaIndex (retrieve) + LangGraph (orchestrate) + vLLM (serve), and you choose ONE per layer, not one to rule all. Use when starting any LLM/agent/RAG project, or whenever the "which framework?" question is asked. Deliberately neutral
How do I install it?
Run `npx skills add agentsope/SkillAlchemy --skill agentsop-framework-selection --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From agentsope/SkillAlchemy, a repository with 255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.