Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Fact Checking

ASecurity

当需要核实一条断言/数据/引用是否真实可靠、评估来源可信度、识别幻觉或张冠李戴时使用;触发词:核实、查证、事实核查、来源可信度、真假。

3 stars
0 votes
0 copies
2 views
Added 9/19/2026
ai-agents

Works with

cursorcli

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add findscripter/everything-skills --skill fact-checking --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Fact Checking?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Fact Checking
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/findscripter-fact-checking/badge)](https://www.skillsdirectory.com/skills/findscripter-fact-checking)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: fact-checking
title: 事实核查
description: 当需要核实一条断言/数据/引用是否真实可靠、评估来源可信度、识别幻觉或张冠李戴时使用;触发词:核实、查证、事实核查、来源可信度、真假。
domain: 通用/research
tags: [research, verification, sources]
level: 进阶
status: stable
version: 0.1.0
agents: [claude-code, codex, cursor, gemini-cli]
tools: []
requires: []
related: [entity-research-dossier, news-sentiment-briefing, notebooklm-source-grounded-qa, citation-management]
combines_with: [entity-research-dossier, citation-management]
license: CC-BY-SA-4.0
---
## 何时使用

- 需要核实某条断言、统计数据、日期、人物、事件或引用是否真实、准确。
- 需要评估信息来源的可信度(一手/二手、权威性、利益冲突、时效)。
- 怀疑内容存在幻觉、张冠李戴、数字夸大、引文捏造、归因错误。
- 在产出报告/结论前,对关键事实做交叉验证。

不该用:
- 主观观点、价值判断、审美偏好、预测未来 —— 这些不可证伪,不适用事实核查。
- 纯计算/逻辑推导问题 —— 用推理而非查证;归因到本技能反而拖慢。
- 已明确标注为虚构、假设、示例的内容。
- 无法触网且无本地证据可查时,直接标注「无法核实」,不要臆断为真。

## 步骤 / 指令

```
1. 拆分断言(atomize)
   - 把待核内容拆成最小可验证单元:主体 + 谓词 + 数值/时间/地点。
   - 一句话含多个事实时,逐条拆开,分别核查。
   - 标记类型:[数据] [引用] [事件] [归因] [定义]。

2. 设定核查问题
   - 对每个单元写出可被证据证实或证伪的问题。
   - 优先核查:高风险、易错(具体数字/日期/人名)、结论所依赖的关键前提。

3. 取证(优先一手)
   - 来源优先级:一手原始 > 权威机构/同行评审 > 主流二手 > 个人/匿名。
   - 至少 2 个相互独立的来源交叉印证;独立=不同源头,转载不算独立。
   - 引用类断言必须回溯到原文出处,逐字比对,确认未断章取义。
   - 数据类断言核对:口径、单位、时间范围、统计主体是否一致。

4. 评估来源可信度(逐源打分)
   - 维度:权威性 / 一手程度 / 时效 / 利益冲突 / 可追溯性。
   - 来源互相矛盾时,倾向更一手、更权威、更新的;记录分歧。

5. 裁定并标注
   - 每个单元给出结论:[属实] / [部分属实] / [失实] / [误导] / [无法核实]。
   - [部分属实]/[误导] 说明哪部分对、哪部分偏。
   - 附证据链:来源 + 关键摘录 + 链接/定位。

6. 识别典型失真(专项检查)
   - 张冠李戴:人物/机构/时间/地点被错配。
   - 幻觉引文:引文/文献/数据看似具体但查无实据 → 判 [无法核实] 或 [失实]。
   - 数字漂移:量级、单位、百分比 vs 百分点混淆。
   - 过时为真:曾经成立但已被更新/推翻。

7. 输出
   - 逐单元给结论、置信度、证据链;保留不确定性,不强行下定论。
```

## 示例

最小核查提示词:

```
对以下文本逐条做事实核查:
"<断言原文>"
要求:
1. 拆成最小可验证单元,标类型;
2. 每个单元独立取证,至少 2 个独立来源,引用须回溯原文逐字比对;
3. 裁定 [属实/部分属实/失实/误导/无法核实] + 置信度 + 证据链(来源/摘录/链接);
4. 专项排查张冠李戴、捏造引文、数字漂移、过时信息;
5. 无证据时标 [无法核实],禁止臆测。
```

输出片段示例:

```
单元1 [数据]「X 2024 年营收增长 35%」
  裁定:失实(置信度高)
  证据:官方年报 P12,实为同比增长 13%(口径:总营收)。来源A[年报pdf] 与 来源B[监管披露] 一致。
  失真类型:数字漂移(35% vs 13%)。

单元2 [引用]「某人说过 '……' 」
  裁定:无法核实
  证据:检索一手讲话/著作未见该原话;二手转述无出处。建议不予采信。
```

## 注意事项

- 不可证伪即不核查:区分「事实陈述」与「观点/预测」,后者只评估论据质量。
- 独立来源 ≠ 多个链接:同一通稿被多家转载仍算单一来源。
- 引用必须回到原文,凭印象比对易引入二次幻觉。
- 区分「无证据支持」与「有证据反驳」:前者标 [无法核实],后者才标 [失实]。
- 注意时效:核对证据本身的发布时间,避免用过时来源裁定当下事实。
- 保留不确定性,宁可标 [无法核实] 也不要伪造确定性结论。
- 警惕确认偏误:主动找反证,不要只检索支持既有结论的来源。
- 网络来源可能被污染或互相抄错,AI 生成内容尤甚;优先权威一手。

## 互见

- related:first-principles-thinking(从第一性原理判断断言是否合理、定位最该优先核查的关键前提)。

Attribution

findscripterfindscripter
View sourceSee grades on GitHubMore from findscripter →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →