菜单
Example skill — check HTTP endpoint health (status code, response time)
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | demo-http |
| version | 1.0.0 |
| display_name | Demo HTTP Check |
| description | Example skill — check HTTP endpoint health (status code, response time) |
| permissions | {"network":"restricted","filesystem":"none","shell":"none","timeout":30} |
| tags | ["http","demo","monitoring"] |
| icon | 🌐 |
| compatible | {"platforms":["windows","macos","linux"],"modes":["community","enterprise"]} |
Simple HTTP health check skill. Checks that a URL returns the expected status code within a time limit. Good starting point for learning Skill development.
# Install
tagent skill install examples/skills/demo-http
# Use
tagent "check if https://example.com is up"
tagent "verify https://api.example.com/health returns 200"
tagent "is https://example.com responding within 2 seconds"
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| url | string | yes | - | Target URL (must start with http:// or https://) |
| expected_status | int | no | 200 | Expected HTTP status code |
| timeout | int | no | 10 | Timeout in seconds (1-30) |
{
"status": "pass",
"summary": "https://example.com returned 200 in 230ms",
"details": {
"url": "https://example.com",
"status_code": 200,
"response_time_ms": 230
},
"checks": [
{"name": "Status Code", "expected": 200, "actual": 200, "pass": true},
{"name": "Response Time", "expected": "<10s", "actual": "230ms", "pass": true}
],
"error": null
}
| Code | Description | User Action |
|---|---|---|
| HTTP-001 | Invalid URL format | Check URL starts with http:// or https:// |
| HTTP-002 | Connection timeout | Check network/firewall, increase timeout |
| HTTP-003 | DNS resolution failed | Check domain name spelling |
tagent skill test demo-http
Example skill — verify file existence, size, and content
Example skill — send test notifications to configured channels
Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch. Evaluates SKILL.md files using an 8-dimension rubric (structure + effectiveness), runs hill-climbing with git version control, validates improvements through test prompts, and generates visual result cards. Use when user mentions "优化skill", "skill评分", "自动优化", "auto optimize", "skill质量检查", "达尔文", "darwin", "帮我改改skill", "skill怎么样", "提升skill质量", "skill review", "skill打分".
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
女娲造人：输入人名/主题/甚至只是模糊需求，自动深度调研→思维框架提炼→生成可运行的人物Skill。 两种入口：(1)明确人名→直接蒸馏 (2)模糊需求→诊断推荐→再蒸馏。 触发词：「造skill」「蒸馏XX」「女娲」「造人」「XX的思维方式」「做个XX视角」「更新XX的skill」。 模糊需求也触发：「我想提升决策质量」「有没有一种思维方式能帮我...」「我需要一个思维顾问」。