agentsope/SkillAlchemy / skills/agentsop-llamaindex
agentsop-llamaindex
VerifiedOperating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query engines, routers, agents), or pick LlamaIndex vs LangChain / Haystack / raw vector store for a coding task. Encodes the 5-layer mental model (Documents → Nodes → Indices → Retrievers → Query Engines / Response Synthesizers), the canonical RAG bootstrap SOP from baseline `VectorStoreIndex` through hybrid + reranker + eval-loop hardening, the official 13-failure-mode checklist, and 5 dilemma cases distilled from docs, GitHub issues, and 2025 production post-mortems.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 1.1 KB |
| SKILL.md | skill md | 25.6 KB |
| intermediate/operation_candidates.json | config | 7.0 KB |
| references/R1-architecture.md | markdown | 8.7 KB |
| references/R2-sop-workflow.md | markdown | 8.9 KB |
| references/R3-dilemma-cases.md | markdown | 14.3 KB |
| references/R4-anti-patterns.md | markdown | 9.9 KB |
| references/R5-ecosystem-context.md | markdown | 8.2 KB |
README.md
View on GitHub# llamaindex-sop
Operating-system distillation of **LlamaIndex**, the leading RAG / document-agent framework. This skill is third-person analytical: it teaches an agent *how LlamaIndex thinks* about turning raw documents into a retrieval-grounded answer system. It captures the 5-layer mental model (Documents → Nodes → Indices → Retrievers → Query Engines / Response Synthesizers), the canonical "RAG bootstrap" SOP from `VectorStoreIndex` baseline through hybrid + reranker + eval-loop hardening, and ≥3 dilemma cases distilled from official docs, GitHub issues, and production post-mortems (chunk-size tradeoff, hybrid-vs-dense, agent-on-top-vs-RAG-as-tool, long-context-vs-retrieval). It also encodes the anti-patterns surfaced in LlamaIndex's own `rag_failure_mode_checklist`, defining when *not* to reach for LlamaIndex (small docs, pure structured SQL, hard real-time) and how it positions vs. LangChain/Haystack/raw vector store. Activate when the agent must build, debug, or harden a RAG pipeline over private/unstructured data, evaluate retrieval quality, or pick between RAG primitives and an agent.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |