book-writer: Skill for Claude Code

.claude/skills/fact-check/SKILL.md

fact-check is a skill for Claude Code from tobyilee/book-writer. It costs 145 tokens per session (2,098 once invoked), scanned A, original, MIT.

A fact-checking workflow for concrete claims in book chapters, such as numbers, quotes, software versions, release dates, API details, and safety information. The checks depend on whether the book is technical or practical.

In plain words
What is it for?
Use it to verify factual statements in technical books and to check safety, health, food, travel-law, or regulatory claims in practical books.
Why use it?
It helps prevent readers from receiving incorrect details, especially claims that change over time or could affect health, safety, or legal decisions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is tobyilee/book-writer's own configuration. It tells Claude Code how to work on book-writer 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 book-writer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tobyilee/book-writer. 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/tobyilee/book-writer/main/.claude/skills/fact-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tobyilee/book-writer

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 fact-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/tobyilee/book-writer/fact-check/github.svg)](https://agentmods.dev/skills/tobyilee/book-writer/fact-check)
Your own site
<a href="https://agentmods.dev/skills/tobyilee/book-writer/fact-check"><img src="https://agentmods.dev/badge/skills/tobyilee/book-writer/fact-check/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 fact-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/tobyilee/book-writer/fact-check"><img src="https://agentmods.dev/badge/skills/tobyilee/book-writer/fact-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,098 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 $0.00145 $0.02098
Opus 5 $0.00072 $0.01049
Sonnet 5 $0.00029 $0.00420
Haiku 4.5 $0.00015 $0.00210

Measured 9d ago against content hash 1fb92676d4a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fact-check 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 9d 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/fact-check/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fact Check

챕터 초안의 구체적 사실 주장을 검증한다. 문체가 아니라 정확성만 본다. 최신 기술 주제일수록 버전·API·릴리스 연도가 빠르게 변하므로 시점 명기와 출처 대조가 핵심이고, 실용서는 틀린 안전 정보가 독자의 실제 피해로 이어지므로 안전 사실 대조가 핵심이다.

활성 장르를 먼저 확인하자. 이 스킬은 tech-bookpractical에서 작동한다 (genre는 오케스트레이터 전달 → {slug}/book_manifest.json 순). 둘 다 아니면 오케스트레이터가 팩트체크 단계를 생략한다. 장르가 검증 범위를 결정한다 — tech-book은 구체 주장 전반, practical은 안전·건강·법규 사실 한정.

무엇을 검증하나 (검증 대상 주장)

구체적이고 검증 가능한 주장만 본다. 일반적 서술·의견·비유는 대상이 아니다.

tech-book — 구체 주장 전반:

유형 예시
수치·통계·벤치마크 "응답이 3배 빨라진다", "메모리 40% 절감"
인용·귀속 "Dijkstra가 말했듯이", "공식 문서에 따르면"
버전 번호 "React 18", "Python 3.12"
릴리스 연도·시점 "2023년에 도입된", "최신 버전에서는"
API·시그니처 함수명·플래그·옵션명·기본값
단정 "최초의", "유일한", "가장 빠른"

practical — 안전·건강·법규 사실 한정 (v1.11.0):

유형 예시
식품 안전 수치 조리 심부 온도("닭고기 75℃"), 보관 기간, 해동 규칙
알레르겐·독성 익혀야 하는 재료, 교차 오염, 알레르기 유발 표시
응급·부상 대처 화상·베임 등 사고 시 대처 서술
여행 법규·안전 비자·통관 규정, 현지 법, 안전 수칙
안전 단정 "~해도 안전하다", "괜찮다"류 단정

practical의 그 밖의 서술(맛·취향·팁·모호한 분량)은 대상이 아니다 — 모호어·단계 문제는 style-guardian(체크리스트) 소관이다. practical의 안전 주장은 기본 Critical — 레퍼런스로 확정 불가 시 웹 2차 에스컬레이션 대상이며, 1차 출처는 공공 보건·식품 안전 기관(식약처·FDA·USDA 등)·정부 여행 안전 공지를 우선한다.

절차

  1. 활성 장르 확인 — tech-book·practical 둘 다 아니면 중단. practical이면 검증 범위를 안전·건강·법규 사실로 좁힌다
  2. 원문 읽기{NN}_draft.md (style 합의 후 버전 우선)
  3. 주장 추출 — 활성 장르의 유형 표에 해당하는 구체 주장을 모은다. (사실 확인 필요) 주석 지점을 최우선 목록에 올린다
  4. 대조 — 각 주장을 01_reference.md(+ research/*.md)와 맞춘다
  5. 에스컬레이션 (선택) — 레퍼런스로 판정 불가한 Critical 주장만 WebSearch/WebFetch로 공식 1차 출처 확인. 사소한 주장에 웹 호출 낭비 금지
  6. 판정 + 정정안 — 라벨별로 정리, 근거 명기
  7. 전달SendMessagechapter-writer에게 + factcheck_log.md에 append

판정 라벨

  • 확인됨 — 근거 일치, 통과 (출처 한 줄 기록)
  • 정정 필요 — 불일치/오류, 올바른 값 제시 (Critical)
  • ⚠️ 출처 없음 — 근거 부재, 보강 또는 주장 약화 (Critical)
  • 🕒 신선도 경고 — 시점 미명기/휘발성, "{버전}/{연도} 기준" 또는 경고 추가

(사실 확인 필요) 주석은 반드시 넷 중 하나로 해소한다. final에 미해소 주석이 남으면 안 된다.

의심 식별자 = 구속력 있는 검증 (절대 패시브 메모로 격하 금지)

Read the full file on GitHub · 110 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. 9d ago First seen · 110 lines · 145 tokens per session scan A 1fb92676d4a9

Subscribe to this mod's changes

fact-check is a skill published in the GitHub repository tobyilee/book-writer (81 stars, last pushed 23d ago), licensed MIT. It adds 145 tokens to every session and 2,098 once invoked, about $0.0007 per session on Opus 5. 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