ai

AI/LLM 能力索引。Agent 开发、LLM 安全、RAG 系统。当用户提到 AI、LLM、Agent、RAG、Prompt 时路由到此。

155 stars

bytelagod

View on GitHub Installation ↓

Best use case

ai is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

AI/LLM 能力索引。Agent 开发、LLM 安全、RAG 系统。当用户提到 AI、LLM、Agent、RAG、Prompt 时路由到此。

Teams using ai should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/ai/SKILL.md --create-dirs "https://raw.githubusercontent.com/telagod/code-abyss/main/skills/domains/ai/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/ai/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How ai Compares

Feature / Agent	ai	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

AI/LLM 能力索引。Agent 开发、LLM 安全、RAG 系统。当用户提到 AI、LLM、Agent、RAG、Prompt 时路由到此。

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

Best AI Skills for Claude

Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.

SKILL.md Source

# 丹鼎秘典 · AI/LLM

## 路由

| 意图 | 秘典 | 核心 |
|------|------|------|
| Agent 开发 | [agent-dev](agent-dev.md) | 多 Agent 编排、工具调用、ReAct 循环 |
| LLM 安全 | [llm-security](llm-security.md) | Prompt 注入、越狱防护、输出过滤 |
| RAG 系统 | [rag-system](rag-system.md) | 向量库、检索策略、重排序、混合检索 |
| Prompt/评估 | [prompt-and-eval](prompt-and-eval.md) | Few-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 |
|------|------|------|
| ReAct | Think→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
```