Name: examples
Author: zenHeart

Imported from zenHeart/learn-ai (ppts/prompt-context/examples/AGENTS.md). Install upstream with npx skills add zenHeart/learn-ai --skill examples. Copyright stays with the author.

AGENTS.md

项目概述

prompt-context examples 是配合《Prompt + Context + Harness》演讲的配套代码示例仓库。

目录结构

examples/
├── AGENTS.md          # 本文件，项目意图与规则
├── CLAUDE.md          # Claude Code 命令清单
├── README.md          # 示例使用指南
├── 2.1.zero-vs-few-shot/       # Zero-Shot vs Few-Shot
├── 2.2.cot-extended-thinking/  # CoT + Extended Thinking
├── 2.3.context-window/          # Token 计算与窗口占用
├── 2.4.lost-in-the-middle/     # Lost in the Middle 复现
├── 3.1.icio-framework/         # ICIO 框架最佳实践
├── 3.2.claude-code-assets/      # Claude Code 资产选择示例
├── 3.3.tool-calling/           # Tool Calling demo
├── 4.1.vue3-component/          # Vue3 组件生成
└── 4.2.bug-hunting-nn-client/  # nn-client-all Bug 调试

使用规则

所有示例必须可独立运行
每个示例包含 README.md 说明背景
代码注释必须包含中文解释关键决策
示例路径必须与演讲章节编号对应

规范

TypeScript strict mode
所有工具函数必须类型标注
测试用例覆盖核心逻辑路径

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Install examples and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "zenheart-learn-ai-examples", "kind": "skill", "name": "examples", "description": "prompt-context examples 是配合《Prompt + Context + Harness》演讲的配套代码示例仓库。", "publisher": "zenHeart", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "github-agents" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "prompt-context examples 是配合《Prompt + Context + Harness》演讲的配套代码示例仓库。" ], "primary": false, "metadata": { "source": { "provider": "github-agents", "repository": "https://github.com/zenHeart/learn-ai", "path": "ppts/prompt-context/examples/AGENTS.md", "ref": "ce2324990d2500b442bcc40f4623bbfd56b36d03", "url": "https://github.com/zenHeart/learn-ai/blob/ce2324990d2500b442bcc40f4623bbfd56b36d03/ppts/prompt-context/examples/AGENTS.md", "key": "zenHeart/learn-ai/ppts/prompt-context/examples/AGENTS.md" } }, "instructions": "# AGENTS.md\n\n## 项目概述\n\nprompt-context examples 是配合《Prompt + Context + Harness》演讲的配套代码示例仓库。\n\n## 目录结构\n\n```\nexamples/\n├── AGENTS.md # 本文件，项目意图与规则\n├── CLAUDE.md # Claude Code 命令清单\n├── README.md # 示例使用指南\n├── 2.1.zero-vs-few-shot/ # Zero-Shot vs Few-Shot\n├── 2.2.cot-extended-thinking/ # CoT + Extended Thinking\n├── 2.3.context-window/ # Token 计算与窗口占用\n├── 2.4.lost-in-the-middle/ # Lost in the Middle 复现\n├── 3.1.icio-framework/ # ICIO 框架最佳实践\n├── 3.2.claude-code-assets/ # Claude Code 资产选择示例\n├── 3.3.tool-calling/ # Tool Calling demo\n├── ", "cost": { "context_tokens": 213 } }

examples

About

AGENTS.md

项目概述

目录结构

使用规则

规范

Use it

Install examples and it becomes one more candidate the router can pick - when it fits.

Manifest

Reviews