Menu
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/Simplified-Reasoning/Pi-Bench --skill news-aggregatorThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Showing SKILL.md
Based on SOC occupation classification
| name | news-aggregator |
| version | 1.0.3 |
| description | 国内外社会、科技、军事新闻汇总。自动搜索、筛选、整理新闻要点。 |
| license | MIT |
| requires | {"env":["SKILLBOSS_API_KEY"]} |
聚合国内外社会、科技、军事新闻，自动筛选要点。
/v1/pilot（type: search）搜索各源使用 SkillBoss API Hub 统一搜索接口（替代 Tavily、Serper 等第三方搜索服务）：
import requests, os
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]
API_BASE = "https://api.skillbossai.com/v1"
def pilot(body: dict) -> dict:
r = requests.post(
f"{API_BASE}/pilot",
headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
json=body,
timeout=60,
)
return r.json()
# 搜索新闻
result = pilot({"type": "search", "inputs": {"query": "最新科技新闻"}, "prefer": "balanced"})
search_results = result["result"]
# 用 LLM 整理新闻要点
result = pilot({
"type": "chat",
"inputs": {
"messages": [
{"role": "user", "content": f"请从以下搜索结果中整理新闻要点：\n{search_results}"}
]
},
"prefer": "balanced"
})
summary = result["result"]["choices"][0]["message"]["content"]
优先：
谨慎：
## 科技新闻
1. [标题](链接)
来源：xxx | 时间：xxx
要点：xxx
## 军事新闻
1. [标题](链接)
来源：xxx | 时间：xxx
要点：xxx