Kris

新闻事实核查

Knowledgev1.0.1
By KrisUpdated 2026-05-112 versions · latest released 2026-03-11news-fact-check@clawhub_krisliu16/news-fact-check
Knowledge Base Q&AInformation RetrievalSummarization#News#新闻#消息

According to AlphaMoat, as of 2026-09, 新闻事实核查 has 1,821 downloads and 1 stars — ranked #4,564 of 5,078 AI skills overall, and #400 of 442 in Knowledge.

Installs
240
Downloads
1.8K
Stars
1
Overall Rank
#4,564
Top 90% overall · Top 91% in Knowledge
PlatformInstallsDownloadsStarsComments
ClawHub ↗331.2K--
SkillHub ↗2401.8K1—

Platforms count differently and update at different times.

What this skill does

Following the “doubt first, verify later” principle, this skill guides a four-step fact-checking workflow: extract verifiable claims from the news, cross-verify each claim against authoritative outlets, official statements, fact-checking sites (Snopes, PolitiFact, FactCheck.org, and Chinese rumor-debunking services), and reverse image/video search, assess source reliability, then conclude with one of five verdicts (verified true, verified false, partially true, unverifiable, misleading) output in a fixed format with key findings, evidence sources, and caveats.

Profile published 2026-10-27

What you can do with it

  • Fact-check suspicious claims circulating in group chats or social media
  • Extract key claims from a news item and cross-verify each across multiple sources
  • Use Google Images reverse search or InVID/WeVerify to detect repurposed or spliced media
  • Assess source credibility: outlet reputation, named sources, balanced viewpoints, bias
  • Spot red flags like single-source stories, urgent forwarding pleas, and vague dates

When to use it

  • When a user needs to verify news authenticity, check sources, or confirm an event's truth
  • When handling suspected rumors or emotionally charged, sensational content
  • When building critical-thinking habits of doubting first and verifying with evidence

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Fact-check this news: extract the key claims and compare coverage against authoritative outlets
This photo looks like recycled material from an old story — verify it with reverse image search
Give me the verdict in the standard format: key findings, evidence sources, and caveats

Monthly Trend

Downloads1.8K
3751.2K1.9K2026-03 · Downloads 4822026-05 · Downloads 7822026-06 · Downloads 8892026-07 · Downloads 1.1K2026-08 · Downloads 1.3K2026-09 · Downloads 1.8K26-0326-09
Stars1
0112026-03 · Stars -2026-05 · Stars -2026-06 · Stars 12026-07 · Stars 12026-08 · Stars 12026-09 · Stars 126-0326-09

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-091.8K—1
2026-081.3K+15.3%1
2026-071.1K+27.8%1
2026-06889+13.7%1
2026-05782—-
2026-03482—-

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

3.1 KB · ClawHub v1.0.1
---
AIGC:
    ContentProducer: Minimax Agent AI
    ContentPropagator: Minimax Agent AI
    Label: AIGC
    ProduceID: 353a1fa62d9e026ed1e119c32ab2e30b
    PropagateID: 353a1fa62d9e026ed1e119c32ab2e30b
    ReservedCode1: 3044022033cbb6252fc5d80f939363e84f1e1b3e96884b5b02e1aef41b9ec5ad2fe11a51022060e1cf1c3e77a5e9c11e2d3619ab01f2e739c9bf95964d2aa3e496050d27c8ae
    ReservedCode2: 3044022030b657224bf9bb8ebc476de998ac6527132e87ec57c7a0b090441f9b314cacaa0220437688bfc1238ae1b7eaca7c99de7f231ba0bd880c100ccc101443209b735a9b
description: 新闻事实核查与真伪辨别助手。当用户需要验证新闻真实性、查证消息来源、核实事件真伪时使用。包括:(1) 给定新闻内容进行真伪判断 (2) 提供的事实核查方法和步骤 (3) 帮助用户建立批判性思维习惯
Show all (94 lines)
name: news-fact-check
---

# 新闻事实核查

## 核心原则

**先怀疑,后验证**。不要假设任何新闻是真实的或假的,始终通过证据来判断。

## 核查流程

### 第一步:识别关键声明

从新闻中提取可验证的核心事实主张(Claims),包括:
- 具体的人物、地点、时间、数据
- 直接引语和归属来源
- 事件的核心事实

### 第二步:多源验证

对每个关键声明进行交叉核实:

1. **权威新闻源比对**:对比 BBC, Reuters, AP, 新华社等权威媒体是否报道
2. **官方信息核查**:查找政府部门、机构、企业的正式声明
3. **事实核查网站**:使用以下专业工具:
   - [Snopes](https://snopes.com)
   - [PolitiFact](https://politifact.com)
   - [FactCheck.org](https://factcheck.org)
   - [中国谣言粉碎机](https://piyao.sina.cn/)
   - [腾讯新闻较真](https://news.qq.com/zt2020/page/feiyan.htm)
4. **图片/视频验证**:使用 Google Images 反向搜索或 InVID/WeVerify 工具

### 第三步:评估来源可靠性

检查原始信息来源的可信度:
- 媒体声誉和历史准确性
- 是否有明确的消息源
- 报道是否包含多方观点
- 出版时间是否最新
- 是否有明显的偏见或煽动性语言

### 第四步:给出结论

根据证据强度,给出以下结论之一:
- **已证实为真**:有多处独立可靠来源证实
- **已证实为假**:有明确证据证明为虚假信息
- **部分属实**:声明中包含真实成分但有误导性细节
- **无法核实**:缺乏足够证据做出判断
- **误导性**:技术上可能为真但呈现方式具有误导性

## 输出格式

完成核查后,以以下格式呈现:

```
📋 核查结论:[结论类型]

🔍 关键发现:
- [发现1]
- [发现2]

📚 证据来源:
- [来源1]
- [来源2]

⚠️ 注意事项:
- [任何可能影响判断的因素]
```

## 常见红旗特征

以下特征提示新闻可能不可靠:
- 来源模糊或不存在
- 情绪化、煽动性语言
- 单一来源,无其他媒体跟进
- 声称"独家报道"但无原始链接
- 使用模糊的时间表述(如"近日")
- 图片、视频可能为旧素材或移花接木
- 要求立即转发分享

## 参考资源

如需更详细的核查方法论和工具列表,参见 [references/methods.md](references/methods.md)。

Popular in Knowledge

More from Kris

Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.