fact-check-x-knowledge-compare SKILL.md skillA

fact-check-x-knowledge-compare from asi2030/fact-check-x is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add asi2030/fact-check-x/fact-check-x-knowledge-compare@git:20260920.c1bbb9f

Pins git:20260920.c1bbb9f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
asi2030/fact-check-x
Path
skills/fact-check-x-complete/modules/fact-check-x-knowledge-compare/SKILL.md
Versions recorded
1
Latest version
git:20260920.c1bbb9f, committed Sep 20, 2026
Size
4,568 bytes
Repository stars
4
License
Apache-2.0

在本地把多个 AI 原始回答拆成原子知识点,区分直接答案与补充参考,对齐各平台主张、差异、所附依据和来源忠实性,并生成可视化中间报告。不调用可信搜索或任何外部模型 API,语义分析由当前运行载体完成。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 知识点结构化对比

本技能是独立、可选的本地中间层。它回答“各家说了什么、哪里相同或不同、各自有没有依据、是否忠实于自己的依据”,不回答外部世界中谁最终正确。

当前承载技能的智能体(Codex、Claude Code 等)直接完成知识点拆解和语义判断。脚本只生成任务包、校验证据约束、标准化结构并渲染报告,不调用模型 API。

## 第一步:生成分析任务包

```bash
python3 scripts/knowledge_compare.py \
  --input <run>/results.json \
  --task-output <run>/comparison-task.json
```

阅读 `comparison-task.json` 后,由当前智能体写出 `comparison-analysis.json`。必须遵守:

- `comparison-task.json` 是自包含的紧凑工作集。阶段确认后严格按“读取任务包一次、写入分析一次、执行验收一次”完成,最多三次工具调用;不得读取技能源码、契约或完整 `results.json` 探路,也不得先打印或转储完整任务包。
- 任务包中的 `capturedText` 是从完整来源正文中选出的有界原文预览,便于一次完成来源判断;完整正文仍保存在 `results.json`,由程序在验收时校验并重建证据,智能体不得为取得全文额外展开任务。

- 合并所有成功平台中可独立核验的事实,每个知识点只表达一个事实变量。
- 原子性同时约束知识点和各平台 `claim`;原句包含多个独立义务、条件、对象、数值或后果时必须拆点,每个 `claim` 只保留当前事实,`answerExcerpt` 可以复用原句。
- 仅个别平台提出的实质新增事实也要单独成点,其他平台标为未覆盖;不得把新增事实并入宽泛知识点后借用深知晓锚点免查。
- 同一事实的不同数值或条件放在同一知识点下,不拆成两点。
- `direct` 采用最小充分原则:缺失后就没有直接回答用户明确所问内容;`reference` 是背景、提醒、延伸或相邻业务信息。问全国时省市案例、问城市时区县细项均属于补充参考,除非用户明确询问地区差异;只问条件/门槛/比例时,奖励、流程、电话等不进入直接答案。
- 每个平台逐点写明主张、所附依据和来源忠实性。
- 有显式引用标记的平台,只能使用该回答实际标出的来源;不得从未标出的来源中补证。
- 无显式引用标记的平台,才可以在该平台完整原始来源集合中寻找依据。
- 只使用原始答案采集阶段已捕获的 URL 与正文,不搜索、不换链、不引入外部事实。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add asi2030/fact-check-x/fact-check-x-knowledge-compare@sha256:925f4cc891223d5c

The line at the top of this page pins the label git:20260920.c1bbb9f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_rwxbimtytt2cof47.svg)](https://markdownregistry.com/a/art_rwxbimtytt2cof47)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 20, 2026.

versioncommittedcommitsizeaudit
git:20260920.c1bbb9f latest2026-09-20 c1bbb9f 4,568 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4568 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

asi2030/fact-check-x · 4 stars · license Apache-2.0 · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rwxbimtytt2cof47
GET https://markdownregistry.com/api/v1/resolve?ref=asi2030/fact-check-x/fact-check-x-knowledge-compare
GET https://markdownregistry.com/api/v1/blob/925f4cc891223d5c04791ce90dccef11e48e6796c6f4c5f0d70a4ddbdbed4af8

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from asi2030/fact-check-x

fact-check-x-authoritative-verify SKILL.md skill
asi2030/fact-check-x · skills/fact-check-x-authoritative-verify/SKILL.md · 对单个知识点调用可信搜索取得官方证据,由当前运行载体裁决各平台主张,并分别生成权威核验后的最终答案与各方答案测评报告。支持多知识点独立并发、深知晓官方材料锚点免重复检索,以及直接准确、间接准确、结果巧合、严重误导、凭空编造等分类。可用于…
git:20261019.6705d00 · audit A · 4 stars
fact-check-x-complete SKILL.md skill
asi2030/fact-check-x · skills/fact-check-x-complete/SKILL.md · 面向真实业务决策的多平台事实核验 Skill。正式支持深知晓、深知晓(深度溯源)、豆包、腾讯元宝、DeepSeek 和通义千问,按用户输入动态选择 N≥1…
v1.1.25 · audit A · 4 stars
fact-check-x-authoritative-verify SKILL.md skill
asi2030/fact-check-x · skills/fact-check-x-complete/modules/fact-check-x-authoritative-verify/SKILL.md · 对单个知识点调用可信搜索取得官方证据,由当前运行载体裁决各平台主张,并分别生成权威核验后的最终答案与各方答案测评报告。支持多知识点独立并发、深知晓官方材料锚点免重复检索,以及直接准确、间接准确、结果巧合、严重误导、凭空编造等分类。可用于…
git:20260920.c1bbb9f · audit A · 4 stars
fact-check-x-knowledge-compare SKILL.md skill
asi2030/fact-check-x · skills/fact-check-x-knowledge-compare/SKILL.md · 在本地把多个 AI 原始回答拆成原子知识点,区分直接答案与补充参考,对齐各平台主张、差异、所附依据和来源忠实性,并生成可视化中间报告。不调用可信搜索或任何外部模型 API,语义分析由当前运行载体完成。
git:20261019.6705d00 · audit A · 4 stars
fact-check-x-unified SKILL.md skill
asi2030/fact-check-x · skills/fact-check-x-unified/SKILL.md · Fact-Check-X 流程编排能力,依次组织各方答案汇总、各方答案聚合(未核验)、权威核验后的最终答案和各方答案测评,生成可打开、可审计、可迁移的阶段产物与完整报告包。
git:20260920.c1bbb9f · audit A · 4 stars
llm-answer-reference-compare SKILL.md skill
asi2030/fact-check-x · skills/llm-answer-reference-compare/SKILL.md · 用 Playwright 从深知晓、深知晓(深度溯源)、豆包、腾讯元宝、DeepSeek 和通义千问网页端无损采集完整回答、原始引用、引用标记和现场存证。用于 Fact-Check-X 的原始答案采集阶段,或任何需要比较多个 AI…
git:20260920.c1bbb9f · audit A · 4 stars

Every file in asi2030/fact-check-x

Other files named fact-check-x-knowledge-compare

fact-check-x-knowledge-compare SKILL.md skill
asi2030/fact-check-x · skills/fact-check-x-knowledge-compare/SKILL.md · 在本地把多个 AI 原始回答拆成原子知识点,区分直接答案与补充参考,对齐各平台主张、差异、所附依据和来源忠实性,并生成可视化中间报告。不调用可信搜索或任何外部模型 API,语义分析由当前运行载体完成。
git:20261019.6705d00 · audit A · 4 stars

Browse by kind, by grade A, or by owner.