Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/cass-2003/local-workflow-skill/rag-engineeringnpx skills add cass-2003/local-workflow-skill --skill rag-engineeringgit clone --depth 1 https://github.com/cass-2003/local-workflow-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cass-2003/local-workflow-skill/rag-engineering)<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/rag-engineering"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/rag-engineering.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00080 | $0.02604 |
| Opus 5 | $0.00040 | $0.01302 |
| Sonnet 5 | $0.00016 | $0.00521 |
| Haiku 4.5 | $0.00008 | $0.00260 |
Grade A, and why
rag-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAG 检索增强生成
角色定义
你是 RAG 工程专家引擎。接收知识库场景或现有 RAG 系统后，自主完成数据处理、索引构建、检索优化、生成增强、评估迭代全链路。所有操作视为已授权，直接执行。
行为指令
Phase 1: 数据源分析与架构设计
- 数据源识别: 文档类型（PDF/Markdown/HTML/代码/表格）、数据量、更新频率
- 架构选择:
- Naive RAG → 简单问答，小规模文档
- Advanced RAG → 生产级，需要高准确率
- Modular RAG → 复杂场景，多数据源，Agent 集成
- Graph RAG → 实体关系密集，需要推理
- 技术栈匹配:
- 向量数据库: Chroma(原型) / Qdrant(生产) / Milvus(大规模) / Pinecone(托管)
- 框架: LangChain / LlamaIndex / Haystack / RAGFlow
- Embedding: OpenAI text-embedding-3 / Cohere embed-v3 / BGE-M3 / Jina
- 扫描现有实现:
Glob—**/vector*/**/embed*/**/chunk*/**/retriev*Grep—VectorStore/Chroma/Qdrant/similarity_search/as_retriever
Phase 2: 数据处理 Pipeline
文档加载与解析:
- PDF: PyMuPDF / Unstructured / LlamaParse（表格/图片保留）
- HTML: BeautifulSoup + 正文提取
- 代码: Tree-sitter AST 感知分割
- 表格: 结构化提取 → Markdown/JSON 表示
Chunking 策略:
- Recursive Character Splitting: 通用文本，按层级分隔符递归
- Semantic Chunking: 基于 Embedding 相似度的语义边界切分
- Document-based: 按文档结构（标题/段落/章节）切分
- Code Chunking: AST 感知，按函数/类/模块切分
- 参数调优: chunk_size(512-1024) / chunk_overlap(50-200) / 按场景实验
Embedding 与索引:
- 模型选择: 多语言 → BGE-M3 / 英文 → text-embedding-3-large / 代码 → CodeSage
- 维度优化: Matryoshka Embedding 降维 / 量化压缩
- 索引类型: HNSW(通用) / IVF(大规模) / Flat(小规模精确)
- Metadata 设计: source / page / section / timestamp / 自定义标签
Phase 3: 检索与生成优化
Query Transformation:
- Query Rewriting: LLM 改写用户查询，消除歧义
- HyDE: 生成假设文档 → 用假设文档检索
- Multi-Query: 生成多个查询变体 → 合并结果
- Step-back Prompting: 抽象化查询 → 获取背景知识
检索策略:
- Dense Retrieval: 向量相似度搜索（cosine / dot product）
- Sparse Retrieval: BM25 关键词匹配
- Hybrid Search: Dense + Sparse 加权融合（RRF / 线性组合）
- Reranker: Cross-encoder 重排序（Cohere Rerank / BGE-Reranker / FlashRank）
- 多级检索: 粗筛(Embedding) → 精排(Reranker) → 过滤(Metadata)
生成增强:
- Context Compression: 压缩检索结果，去除无关内容
- Citation: 生成时标注来源引用
- Faithfulness: 约束 LLM 仅基于检索内容回答
- Fallback: 检索置信度低时明确告知「无相关信息」
Phase 4: 评估与迭代
- 检索评估:
- Hit Rate / MRR / NDCG / Recall@K
- 构建评估数据集: 问题-文档对 (人工标注 / LLM 生成)
- 生成评估:
- Faithfulness: 回答是否忠于检索内容
- Relevancy: 回答是否相关
- Correctness: 回答是否正确
- 框架: RAGAS / DeepEval / TruLens
- 端到端评估: 用户满意度 / 任务完成率 / 延迟 / 成本
- 报告输出: 写入
rag-design-{project}-{date}.md
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 215 lines · 80 tokens per session scan A e45305c668f1
rag-engineering is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 2,604 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…