← Back to Skills Marketplace
tangweigang-jpg

Llama Index Rag

by Tang Weigang · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
68
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install llama-index-rag
Description
LlamaIndex：把任意文档变 LLM 可查询知识的 Python 框架。4 大支柱（Index/Retriever/QueryEngine/Synthesizer）+ 52 条 anti-pattern 约束（5 fatal）。 LlamaIndex: a Python framework that tur...
README (SKILL.md)

这个 skill 适合什么用户？能做哪些任务？

概览

LlamaIndex 是把任意文档变成 LLM 可查询知识的 Python 框架（github.com/run-llama/llama_index）。四大支柱（Index / Retriever / QueryEngine / ResponseSynthesizer）配置化检索-合成循环；Ingestion pipeline 处理 Document → Node → Embedding → Index 转换，带 content-hash 缓存；workflow / agent 子模块（FunctionAgent / ReActAgent / CodeActAgent / multi-agent...

Doramagic 晶体页: https://doramagic.ai/zh/crystal/llama-index-rag

知识规模

  • 52 条约束 (5 fatal + 47 non-fatal)
  • 上游源码: run-llama/llama_index @ commit 0a6c90bf
  • 蓝图 ID: finance-bp-135

用法

Host AI（Claude Code / Cursor / OpenClaw）读 references/seed.yaml，按其中的：

  • intent_router 匹配用户意图
  • architecture 理解项目架构
  • constraints 应用 anti-pattern 约束
  • business_decisions 参考核心设计决策

FAQ 摘要

这个 skill 适合什么用户？能做哪些任务？

适合做企业知识库、文档问答、RAG 应用的工程师：从 PDF / Markdown / 网页等异构文档构建索引，结合 retrieve-then-synthesize 给 LLM 提供外部知识。覆盖 FunctionAgent / ReActAgent / CodeActAgent 等 agent 范式。访问 doramagic.ai/r/llama-index 查看完整用例。

需要准备什么环境？依赖什么？

Python 3.9+，至少一个 LLM provider（默认隐式 OpenAI gpt-3.5-turbo）和一个 embedding provider（默认隐式 OpenAI text-embedding-ada-002 → 1536 维）。默认用内存 SimpleVectorStore，持久化需安装对应集成包。

会踩哪些坑？这个 skill 怎么防护？

本 skill 内置 52 条约束（5 条 fatal）。典型踩坑：(1) ServiceContext 已硬删除（不是 deprecated），3 个入口直接 raise ValueError；(2) SentenceSplitter chunk_overlap 默认 200（与文档常引用的 constants.DEFAULT_CHUNK_OVERLAP=20 不一致）；

完整文档: 见 references/seed.yaml (v6.1 schema). 浏览页: https://doramagic.ai/zh/crystal/llama-index-rag

Usage Guidance
This is an instruction-only, domain-specific LlamaIndex/RAG blueprint (finance-focused). Before installing or invoking: (1) review references/seed.yaml and human_summary to confirm it targets the workflows you want (it expects ZVT and local finance data); (2) expect the host to run the listed Python precondition checks (which probe for zvt, data directories, and write permissions) and to attempt to read local files like LATEST.yaml — run in a test environment if you are uncertain; (3) note the SKILL.md mentions default OpenAI providers but does not request API keys — be cautious about supplying credentials if the agent later asks for them; (4) if you do not want the agent to access local files or run python checks, do not enable or invoke this skill. Overall the skill is internally consistent with its stated purpose, but it will interact with local tooling and data, so review included seed.yaml and preconditions before use.
Capability Analysis
Type: OpenClaw Skill Name: llama-index-rag Version: 0.1.0 The bundle exhibits a major functional discrepancy between its advertised purpose and its internal logic. While the metadata and SKILL.md describe a LlamaIndex RAG (Retrieval-Augmented Generation) tool, the references/seed.yaml and human_summary.md are almost entirely focused on the 'zvt' quantitative trading framework for A-shares. The seed.yaml file mandates the installation of the 'zvt' package, checks for trading data in '~/.zvt', and enforces 'semantic locks' for financial transactions (e.g., SL-01: sell before buy). This 'Frankenstein' configuration is highly irregular and could cause an AI agent to execute unintended financial trading logic or install unrelated software (zvt) when a user expects RAG functionality.
Capability Tags
crypto
Capability Assessment
✓ Purpose & Capability
The skill advertises LlamaIndex RAG guidance and provides a compiled blueprint (finance-bp-135). The heavy finance/ZVT content and backtest preconditions are consistent with the included seed.yaml and human_summary (this is a domain-specific LlamaIndex/RAG crystal). There is no unexpected request for unrelated credentials or binaries.
ℹ Instruction Scope
Runtime instructions require the host AI to reload and read references/seed.yaml, run precondition checks (Python commands that verify zvt installation, data directories, and write permissions), and enforce disclosure/traceback rules. These actions involve reading skill bundle files and potentially checking the host filesystem (e.g., for LATEST.yaml or ZVT_HOME). This is in-scope for a blueprint that performs local backtests, but users should expect the skill to read local files and run local Python checks.
✓ Install Mechanism
No install spec and no code files to execute; the skill is instruction-only. This minimizes install-time risk (nothing is downloaded or written by the skill itself).
ℹ Credentials
The skill does not declare or require environment variables or credentials. SKILL.md mentions Python 3.9+ and 'an LLM provider / embedding provider (default implicit OpenAI)' as runtime expectations but does not request OpenAI keys. This is a documentation/assumption mismatch (it may expect provider access at runtime), not an overt credential exfiltration request.
✓ Persistence & Privilege
always is false and autonomous invocation is allowed (platform default). The skill does not ask to persist or modify other skills or global agent configuration. It references host workspace paths for scripts/skills/trace, which is reasonable for a blueprint that expects to write traces, but it does not itself include an install step that would create persistent binaries.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install llama-index-rag
  3. After installation, invoke the skill by name or use /llama-index-rag
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
LlamaIndex RAG framework skill — 52 constraints / 5 fatal. ServiceContext removed, CJK chunking pitfalls.
Metadata
Slug llama-index-rag
Version 0.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Llama Index Rag?

LlamaIndex：把任意文档变 LLM 可查询知识的 Python 框架。4 大支柱（Index/Retriever/QueryEngine/Synthesizer）+ 52 条 anti-pattern 约束（5 fatal）。 LlamaIndex: a Python framework that tur... It is an AI Agent Skill for Claude Code / OpenClaw, with 68 downloads so far.

How do I install Llama Index Rag?

Run "/install llama-index-rag" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Llama Index Rag free?

Yes, Llama Index Rag is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Llama Index Rag support?

Llama Index Rag is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Llama Index Rag?

It is built and maintained by Tang Weigang (@tangweigang-jpg); the current version is v0.1.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463556 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259610 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200551 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191226 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190235 · by oswalpalash

💬 Comments