← All skills
hr-common-llm
95 / 100 · Low risk
Fine to try.
By infometa/workbuddyskills (GitHub) · coding · 443 stars · scanned at commit 33b6151
提供标准化的前端 / 后端 LLM 模型代理服务调用能力。当用户需要调用大语言模型时，根据 OpenAI 标准接口规范生成正确的前端或后端调用代码。
⚠️ 严格限制：前端接口（SSO 网关地址）只能在前端页面（浏览器端）中调用，严禁在后端代码中调用，因为后端环境缺少用户的 SSO 身份信息，调用会报错；后端接口（ESB 网关地址）只能在后端服务（Java/Node.js/Python/Go 等）中调用，严禁在前端代码中直接调用。两个地址不可混用。
触发场景：
(1) 用户需要在前端页面调用大语言模型接口
(2) 用户需要在后端服务中调用大语言模型接口
(3) 用户需要生成前端或后端访问 LLM 的 HTTP 请求代码
(4) 用户需要在前端或后端实现 AI 对话、文本生成、内容分析等功能
(5) 用户提到「调用模型」「AI接口」「LLM调用」「大模型」「智能对话」「文本生成」等关键词
(6) 用户需要使用混元模型（HY-3）
权限要求：已认证员工（前端接口）/ 无需额外权限（后端接口，服务端直连 ESB 网关）
Works with any agent that supports SKILL.md skills.
What this skill can do
Connects to the internet
The author does not mention this.
Found in 21 places.
Show 17 more
- experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 273
const response = await fetch(API_URL, { - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 364
import axios from 'axios'; - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 375
const { data } = await axios.post(API_URL, { - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 402
import axios from 'axios'; - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 404
const llmClient = axios.create({ - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 518
const response = await fetch(API_URL, { - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 619
const response = await fetch(API_URL, { - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 780
const response = await fetch(API_URL, { - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 948
const response = await fetch(API_URL, { - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 1037
const response = await fetch(API_URL, { - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 1185
const res = await fetch(LLM_API, { - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 1216
const axios = require('axios'); - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 1227
const { data } = await axios.post(API_URL, { - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 1265
const response = await fetch(API_URL, { - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 1292
const axios = require('axios'); - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 1299
const response = await axios.post(API_URL, { - experts/hr-digital-expert/skills/hr-common-llm/references/code_templates.md, line 1364
response = requests.post(
and 1 more places
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'hr-common-llm' ] || [ -L ~/.agents/skills/'hr-common-llm' ]; then echo 'A skill folder named hr-common-llm already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/infometa/workbuddyskills' "$d" && git -C "$d" checkout --quiet '33b6151ccee9aa0816c6f32d021be77d82772755' -- 'experts/hr-digital-expert/skills/hr-common-llm' && mkdir -p ~/.agents/skills && cp -R "$d"/'experts/hr-digital-expert/skills/hr-common-llm' ~/.agents/skills/'hr-common-llm' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'hr-common-llm' ~/.claude/skills/'hr-common-llm' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for infometa/workbuddyskills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/infometa/workbuddyskills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-13 | 33b6151 | 95 |
| 2026-11-09 | 0749999 | 95 |
| 2026-11-07 | 1e18d8c | 100 |