Skip to content

northseadl/norix-skills / llm-agent-dev

llm-agent-dev

Unverified

LLM Agent engineering: pattern selection (12-mode matrix), data simulation, convergence iteration. Covers intent routing, function calling, ReAct, MCP, prompt chaining, guardrails, evaluation.

FileKindSize
SKILL.mdskill md17.6 KB
agents/openai.yamlconfig198 B
evals/evals.jsonconfig4.7 KB
references/convergence/iteration-protocol.mdmarkdown8.0 KB
references/eval-loop.mdmarkdown9.4 KB
references/feedback-protocol.mdmarkdown6.0 KB
references/intent-patterns.mdmarkdown5.8 KB
references/paradigms/context-engineering.mdmarkdown6.0 KB
references/paradigms/decision-tree.mdmarkdown2.7 KB
references/paradigms/memory-architecture.mdmarkdown4.0 KB
references/paradigms/observability.mdmarkdown4.5 KB
references/paradigms/pattern-matrix.mdmarkdown3.3 KB
references/paradigms/performance-benchmarking.mdmarkdown15.2 KB
references/paradigms/prompt-patterns.mdmarkdown5.0 KB
references/paradigms/safety-guardrails.mdmarkdown5.5 KB
references/paradigms/tool-design.mdmarkdown2.5 KB
references/patterns/01-crex-rule-router.mdmarkdown6.8 KB
references/patterns/02-slot-filling.mdmarkdown7.1 KB
references/patterns/03-function-calling.mdmarkdown3.9 KB
references/patterns/04-workflow-agent.mdmarkdown5.0 KB
references/patterns/05-react-agent.mdmarkdown3.4 KB
references/patterns/06-router-expert.mdmarkdown3.2 KB
references/patterns/07-mcp-tool-protocol.mdmarkdown5.0 KB
references/patterns/08-handoff-delegation.mdmarkdown4.7 KB
references/patterns/09-prompt-chaining.mdmarkdown3.0 KB
references/patterns/10-parallelizing.mdmarkdown3.2 KB
references/patterns/11-orchestrator-worker.mdmarkdown4.8 KB
references/patterns/12-evaluator-optimizer.mdmarkdown5.5 KB
references/scenarios/coding-assistant.mdmarkdown2.0 KB
references/scenarios/content-generation.mdmarkdown2.7 KB
references/scenarios/customer-service.mdmarkdown2.6 KB
references/scenarios/ecommerce-shopping.mdmarkdown4.2 KB
references/scenarios/food-ordering.mdmarkdown3.1 KB
references/scenarios/knowledge-qa.mdmarkdown2.6 KB
references/simulation/data-generation.mdmarkdown8.1 KB
references/skill-templates.mdmarkdown8.0 KB

references/scenarios/content-generation.md

View on GitHub
# 场景蓝图: 内容/文案生成 Agent

> AI 驱动的内容创作全流程:商品文案、营销素材、社交媒体、SEO
> 覆盖: 结构化文案、创意生成、多渠道适配

## 架构

```
用户需求(文字/模板选择)
   │
   ▼
[意图分类]
   │
   ├─ 商品描述   ──→ ③ FC: 获取商品数据 → LLM 生成
   ├─ 营销文案   ──→ ⑤ ReAct: 分析 → 生成 → 优化
   ├─ 社交媒体   ──→ ③ FC: 获取素材 → LLM 适配平台
   ├─ SEO 内容   ──→ ⑤ ReAct: 关键词分析 → 生成 → 检查
   ├─ 批量生成   ──→ ④ Workflow: 并行生成 → 质量审查
   └─ 修改润色   ──→ ③ FC: LLM 直接编辑
```

## 商品描述文案

```
用户: "给这款蓝牙耳机写个详情页文案"

→ FC: get_product(id) → { name, specs, features, reviews_summary }
→ FC: get_competitor_content(category="蓝牙耳机") → 竞品文案参考
→ LLM 生成 (System Prompt 包含品牌调性和文案规范):
  {
    title: "沉浸式好声音,40小时超长续航",
    highlights: ["主动降噪", "蓝牙5.3", "IPX5防水"],
    description: "...",
    selling_points: ["..."],
  }
→ Response: { type: "card", content: structured_copy }
```

## 营销文案 (ReAct)

```
用户: "写一个七夕促销活动方案"

Think: 需要了解品牌定位和历史促销数据
Action: get_brand_guidelines() → 品牌规范
Action: get_past_promotions(event="七夕") → 历史活动数据

Think: 需要分析竞品的七夕营销
Action: search_competitor_campaigns("七夕 2026") → 竞品活动

Think: 现在可以生成方案了
Action: generate_campaign({
  theme: "七夕", brand: guidelines, competitors: analysis,
  channels: ["小红书", "抖音", "微信公众号"]
})

→ 输出包含: 主题、slogan、各渠道文案、时间线、预算建议
```

## 多渠道适配

同一内容自动适配不同平台调性:

```typescript
const channelAdapters = {
  '小红书': { tone: '种草分享', maxLength: 1000, features: ['emoji', 'hashtag'] },
  '抖音': { tone: '短平快', maxLength: 200, features: ['hook_first_3s'] },
  '微信公众号': { tone: '深度专业', maxLength: 3000, features: ['structured'] },
  '淘宝详情页': { tone: '卖点突出', maxLength: 5000, features: ['bullet_points', 'specs'] },
};
```

## 质量控制

```typescript
// 文案生成后的自动质量检查
interface ContentQualityCheck {
  plagiarism: boolean;       // 查重
  brandCompliance: boolean;  // 品牌规范合规
  legalCompliance: boolean;  // 法律合规(禁用"最"等绝对化用语)
  seoScore: number;          // SEO 评分
  readability: number;       // 可读性评分
}
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall