agentsope/SkillAlchemy / skills/agentsop-framework-selection
agentsop-framework-selection
VerifiedNeutral, 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 — unlike vendor docs and the LangChain-biased `framework-selection` on skill.sh, this skill has no horse in the race.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 2.3 KB |
| SKILL.md | skill md | 24.2 KB |
| intermediate/operation_candidates.json | config | 8.7 KB |
| references/R1-decision-tree.md | markdown | 9.6 KB |
README.md
View on GitHub# framework-selection (Phase D capstone skill)
A **neutral**, framework-agnostic decision tree for the question every LLM/agent/RAG
project opens with: *"which framework should I reach for?"*
This is the most-cited skill at project kickoff. Unlike vendor documentation and
the LangChain-biased `framework-selection` already on skill.sh, this skill takes
**no side** — it synthesizes the ecosystem (R5) sections of 7 landmark-project SOPs
and surfaces where they *disagree* rather than papering over it.
## Core stance
**Frameworks are layers, not competitors.** A real project usually combines:
```
DSPy (compile L1) + LlamaIndex (retrieve L2) + LangGraph (orchestrate L3)
+ vLLM (serve L6) + optionally Dify (app platform L7)
```
You choose **one framework per layer**, then check interop — you do not crown a
single winner.
## Files
| File | Purpose |
|---|---|
| `SKILL.md` | The skill: 7 sections — when to activate, layered mental model, 3-pass SOP, per-layer pick rubrics (G0 + OP-1..8), 4 dilemma cases, anti-patterns, full cross-framework map. |
| `references/R1-decision-tree.md` | Source evidence: the layered decision trees, the comparison matrices, and every inline source tag (`<sop> · <id>`) used in SKILL.md, resolved to the 7 SOPs' R5 docs and the Phase B inventory. |
| `intermediate/operation_candidates.json` | Structured atom inventory: layers, operations (G0, OP-1..8), dilemma cases, anti-patterns, with triggers/actions/outputs/evidence. |
## How it composes with sibling Phase D skills
- `[[agentsop-llm-engine-selection]]` — owns the L6 serving sub-tree (vLLM/SGLang/TGI/…).
This skill defers there the moment self-hosting is needed.
- `[[agentsop-agent-topology-selection]]` — owns the L3 single-vs-multi-agent + topology
sub-tree. This skill gates through it before any orchestrator pick.
- `[[agentsop-repo-state-gating]]` — owns the coding-agent applicability gate (existing
repo vs greenfield). This skill gates through it before any Aider/Cline/Cursor
pick.
## Source material
Synthesized from the R5 ecosystem-context sections of:
LangGraph, LlamaIndex, DSPy, CrewAI, vLLM, Aider, Dify SOPs — plus the
"where the 7 SOPs disagree" section of `phase-b-coder-agent-skill-inventory.md`
(capability **A7**, the project-kickoff framework-fit check, `core` 5/7).
Version 0.1.0.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 197k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |