writing-team-workbench: Skill for Claude Code

.claude/skills/06-wu-factcheck/SKILL.md

06-wu-factcheck is a skill for Claude Code from lisitan/writing-team-workbench. It costs 0 tokens per session (1,461 once invoked), scanned A, original, MIT.

A writing-review skill that checks an article's facts, figures, quotations, logic, sources, and riskier claims. It is part of a Chinese-language writing workflow and can use project files, personal notes, and external sources when needed.

In plain words
What is it for?
Use it to review drafts containing dates, numbers, people, policies, research, citations, cause-and-effect claims, or possible legal, medical, financial, privacy, or copyright risks.
Why use it?
It helps distinguish confirmed information from claims that need checking, conflict with other sources, or should be removed before publication.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is lisitan/writing-team-workbench's own configuration. It tells Claude Code how to work on writing-team-workbench itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything writing-team-workbench configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lisitan/writing-team-workbench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lisitan/writing-team-workbench/main/.claude/skills/06-wu-factcheck/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lisitan/writing-team-workbench

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 06-wu-factcheck

README.md
[![agentmods](https://agentmods.dev/badge/skills/lisitan/writing-team-workbench/06-wu-factcheck/github.svg)](https://agentmods.dev/skills/lisitan/writing-team-workbench/06-wu-factcheck)
Your own site
<a href="https://agentmods.dev/skills/lisitan/writing-team-workbench/06-wu-factcheck"><img src="https://agentmods.dev/badge/skills/lisitan/writing-team-workbench/06-wu-factcheck/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for 06-wu-factcheck

Your own site · 80×15
<a href="https://agentmods.dev/skills/lisitan/writing-team-workbench/06-wu-factcheck"><img src="https://agentmods.dev/badge/skills/lisitan/writing-team-workbench/06-wu-factcheck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,461 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01461
Opus 5 $0.00000 $0.00731
Sonnet 5 $0.00000 $0.00292
Haiku 4.5 $0.00000 $0.00146

Measured 11d ago against content hash 98c9b38be199, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

06-wu-factcheck scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/06-wu-factcheck/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

06-wu-factcheck

核查文章中的事实、数字、引用和逻辑风险。

适用场景

  • 草稿已经完成。
  • 文章包含事实、数字、引用、人物、机构、政策、时间、因果判断或最新信息。

角色目标

把文章中的确定事实、待核查信息、冲突信息和应删除内容分清楚。

资料源

  • 必读:当前项目 README.md项目状态.md资料.md
  • 必读:过程/02-张素材.md过程/05-李文章.md
  • 必查:个人笔记库中的相关笔记和原始材料
  • 必要时联网:外部事实、数字、引用、最新信息、公开出处

可用能力

  • 项目内核查:核对草稿是否符合项目资料和素材来源。
  • 断言表抽取:把草稿中的事实、观点、推测、引用、数字、因果判断和绝对化表达抽成核查表。
  • 个人原始记录核对:用 personal-notes-readonly.personal_notes_recallpersonal_notes_get_note 核对用户自己的原始记录、旧笔记和个人资料来源。
  • 网络事实核查:核实公开事实、数据、引用、日期、政策和外部事件。
  • 断言审计:识别绝对化表达、因果跳跃和证据不足。
  • 版权和授权审计:检查图片、音视频、长引文、书摘、课程材料、人物信息是否存在侵权或授权风险。
  • 红线审计:标出可能涉及法律、监管、医疗、金融、隐私、名誉损害的高风险表述。
  • 看不见的人审计:检查被转述者、被误读者、立场不同者、二次传播语境中的潜在伤害。
  • 来源沉淀:把核查来源追加到 资料.md
  • 项目状态回写:把断言总数、待核查数、冲突数、建议删除数和最高风险更新到 项目状态.md

联网触发条件

  • 草稿出现具体数字、日期、人名、机构、政策、书名、研究、平台规则。
  • 草稿使用最新信息或可能变化的信息。
  • 草稿涉及版权、授权、人物评价、机构评价、医疗、法律、金融等高风险内容。
  • 个人笔记库和项目资料之间出现冲突。
  • 草稿有强因果判断但缺证据。

执行步骤

  1. 读取草稿、素材和项目资料。
  2. 标出所有需要核查或需要风险判断的断言,不只限于事实性陈述。
  3. 建立“断言核查表”,每条断言至少包含:原文断言、断言类型、核查方式、来源、核查状态、风险等级、处理建议。
  4. 先用项目资料和 personal_notes_recall / personal_notes_get_note 核对个人原始记录;未配置时标注“个人笔记库未配置,未检索”。
  5. 对外部事实和最新信息联网核实。
  6. 把结果分为“已确认 / 待核查 / 有冲突 / 建议删除”。
  7. 追加更新项目 资料.md 的来源记录,但不写回远端个人笔记库。
  8. 更新项目 项目状态.md 的核查与风险区。
  9. 写入 过程/06-吴查查.md

资料.md 追加格式

## 外部来源记录

- 来源类型:
- 标题/关键词:
- 链接或笔记 ID:
- 摘要:
- 可用于哪一段:
- 可信度:
- 待核查项:

输出文件

过程/06-吴查查.md
资料.md
项目状态.md

输出结构

# 06-吴查查

## 核查摘要

- 断言总数:
- 已确认:
- 待核查:
- 有冲突:
- 建议删除:
- 最高风险:
- 需要用户判断:

## 断言核查表

| 编号 | 原文断言 | 断言类型 | 核查方式 | 来源/依据 | 核查状态 | 风险等级 | 处理建议 |
|---|---|---|---|---|---|---|---|
| A1 |  | 事实/观点/推测/引用/数字/因果/绝对化表达 | 项目资料/个人笔记库/联网/逻辑审计 |  | 已确认/待核查/有冲突/建议删除 | 高/中/低 | 保留/改写/补来源/删除 |

## 已确认

## 待核查

## 有冲突

## 建议删除

## 逻辑漏洞

## 过度断言

## 版权和授权风险

## 红线风险

## 看不见的人

## 建议替换说法

## 核查来源

- 个人笔记库检索状态:
- 个人笔记库命中:
- 外部核查来源:
- 个人记录与外部事实的关系:
- 仍需人工确认的问题:

质量检查

  • 明确区分事实、观点和推测。
  • 已输出断言核查表,并覆盖草稿中的关键数字、引用、事实、因果判断、绝对化表达和高风险判断。
  • 明确区分个人记录和外部事实;外部事实、最新信息、政策、数据、人物机构信息仍需联网核查。
  • 搜不到不等于错误,只能标为待核查或未找到来源。
  • 版权、授权、隐私、名誉和平台风险已检查。
  • 核查通过金线 9:尊重看不见的人。
  • 核查来源已写回 资料.md
  • 项目状态.md 的核查与风险区已更新。
  • 没有保存、更新、删除、打标签或创建远端知识库。

Read the full file on GitHub · 146 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 146 lines · 0 tokens per session scan A 98c9b38be199

Subscribe to this mod's changes

06-wu-factcheck is a skill published in the GitHub repository lisitan/writing-team-workbench (20 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,461 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens