Skillquality 0.56

building-ai-systems

AI and LLM knowledge reference covering agent development, LLM security, RAG systems, prompt engineering, and evaluation. Use when building AI agents, working with LLMs, designing RAG pipelines, or writing prompts.

Price
free
Protocol
skill
Verified
no

What it does

丹鼎秘典 · AI/LLM

路由

意图秘典核心
Agent 开发agent-dev多 Agent 编排、工具调用、ReAct 循环
LLM 安全llm-securityPrompt 注入、越狱防护、输出过滤
RAG 系统rag-system向量库、检索策略、重排序、混合检索
Prompt/评估prompt-and-evalFew-shot、CoT、RAGAS、LLM-as-Judge

RAG 架构模式

文档 → Chunking(递归/语义) → Embedding → 向量库(Pinecone/Qdrant/pgvector)
查询 → Query 改写(HyDE/多查询) → 混合检索(向量+BM25) → Rerank(Cohere/cross-encoder) → LLM 生成
决策点选项判据
Chunk 策略固定/递归/语义结构化文档→递归;长文→语义
检索方式纯向量/混合/知识图谱通用→混合;关系密集→图谱
向量库pgvector/Qdrant/Pinecone已有 PG→pgvector;大规模→托管

Agent 模式

模式结构适用
ReActThink→Act→Observe 循环通用工具调用
Plan-Execute先规划再逐步执行复杂多步任务
Multi-Agent角色分工+消息传递大型协作任务
Reflection生成→自评→修正代码/文本质量提升

原则

Prompt 即代码须版控 | 输入输出皆验证 | 成本效果平衡 | 持续评估迭代 | 安全边界明确

Capabilities

skillsource-telagodskill-building-ai-systemstopic-agent-skillstopic-ai-agenttopic-ai-assistanttopic-ai-personalitytopic-blue-teamtopic-character-cardtopic-claude-codetopic-clitopic-codextopic-codex-clitopic-configurationtopic-developer-tools

Install

Quality

0.56/ 1.00

deterministic score 0.56 from registry signals: · indexed on github topic:agent-skills · 211 github stars · SKILL.md body (972 chars)

Provenance

Indexed fromgithub
Enriched2026-05-18 18:55:05Z · deterministic:skill-github:v1 · v1
First seen2026-05-16
Last seen2026-05-18

Agent access