harness-factory: Skill for Claude Code

.claude/skills/doc-writing/SKILL.md

doc-writing is a skill for Claude Code from Kimyongari/harness-factory. It costs 45 tokens per session (1,226 once invoked), scanned A, original, MIT.

Writing rules for README files, technical documents, design documents, change summaries, pull-request descriptions, and user-facing prose, with Korean as the default language.

In plain words
What is it for?
Use it when creating or editing project documentation, technical explanations, requirements, release notes, or other human-readable text.
Why use it?
They make documents easier to read by encouraging short sentences, clear structure, precise wording, and explicit handling of uncertainty.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Kimyongari/harness-factory's own configuration. It tells Claude Code how to work on harness-factory 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 harness-factory configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Kimyongari/harness-factory. 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/Kimyongari/harness-factory/main/.claude/skills/doc-writing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Kimyongari/harness-factory

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 doc-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimyongari/harness-factory/doc-writing/github.svg)](https://agentmods.dev/skills/kimyongari/harness-factory/doc-writing)
Your own site
<a href="https://agentmods.dev/skills/kimyongari/harness-factory/doc-writing"><img src="https://agentmods.dev/badge/skills/kimyongari/harness-factory/doc-writing/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 doc-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/kimyongari/harness-factory/doc-writing"><img src="https://agentmods.dev/badge/skills/kimyongari/harness-factory/doc-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,226 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.
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 $0.00045 $0.01226
Opus 5 $0.00023 $0.00613
Sonnet 5 $0.00009 $0.00245
Haiku 4.5 $0.00005 $0.00123

Measured 11d ago against content hash 376c3d4b0a72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

doc-writing 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/doc-writing/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

문서 작성 규칙 (Document Writing)

사람이 읽을 산문을 작성·편집할 때 따른다. IMPORTANT: 시스템/사용자 메시지가 이 스킬보다 우선한다. 기본 언어: 한국어 · 기본 톤: 간결하게 · 주 포맷: Markdown

0. 시작 전 판단

  • 새로 만들지 vs 기존 수정 — 거의 항상 기존 문서 수정이 우선.
  • 사용자가 명시 요청하지 않은 문서(README, 요약 .md 등)를 자발적으로 만들지 않는다.
  • 독자를 특정한다(입문자 / 동료 엔지니어 / 의사결정자). 깊이와 용어가 달라진다.

1. 구조

  • 결론 먼저(BLUF, Bottom Line Up Front). 무엇을·왜를 첫 단락에. 배경을 앞세우지 않는다.
  • 한 문서 = 한 목적. 목적이 둘이면 나눈다.
  • 제목 계층(H1→H2→H3)을 건너뛰지 않는다. H1은 문서당 하나.
  • 스캔 가능하게: 절차는 번호목록, 병렬 항목은 불릿, 비교는 표. 단 목록 남발 금지(연결된 논리는 문장).

2. 문장

  • 능동태·현재형·짧은 문장. 한 문장에 한 생각.
  • AI 상투구 제거. 금지 예: "본 문서에서는", "전반적으로", "결론적으로 말하자면", "~할 수 있습니다만".
  • 모호한 지시어("이것", "해당 부분") 대신 구체 명사.
  • 추측을 단정하지 않는다. 불확실하면 "확인 필요"로 표시.
<!-- 나쁨: 배경 먼저, 군더더기 -->
## 개요
본 문서에서는 우리가 전반적으로 고려한 여러 사항들을 다루며, 결론적으로
캐시 도입을 검토할 수 있습니다.

<!-- 좋음: 결론 먼저, 간결 -->
## 캐시 도입 결정
Redis 캐시를 도입한다. 조회 P99 지연이 800ms→40ms로 줄기 때문이다.

3. 코드·경로·명령어 표기

  • 파일 경로/함수명/명령어/식별자는 인라인 코드(backtick)로 감싼다.
  • 코드블록에는 언어 명시(python, bash).
  • 명령어 예시는 실제 동작하는 형태. 플레이스홀더는 ${VAR} / <your-token>로 명확히.
  • 파일 위치는 가능하면 경로:줄번호로.

4. 링크·인용 (web-research와 공유)

  • 외부 사실에는 출처 URL을 단다 → [[web-research]]의 인용 규칙.
  • 내부 문서 참조는 상대경로 링크.
  • 도구 내부 토큰을 본문에 절대 남기지 않는다: [145036†L1-L9], 【turn1†view0】 금지. 사람이 읽을 표준 인용으로 변환.
  • 깨진 URL·플레이스홀더("여기에 내용", "TODO 작성")를 최종본에 남기지 않는다.

5. 표기 규칙

  • 대시는 ASCII 하이픈(-). U+2011 비분리 하이픈·특수 유니코드 대시는 렌더링이 깨지므로 금지.
  • 이모지는 사용자가 명시 요청할 때만.
  • 상대 날짜("어제") 대신 절대 날짜(2026-05-27). 단위 일관.

6. 문서 유형별 핵심

유형 첫 줄에 둘 것 흔한 실수
README 이게 무엇이고 어떻게 실행하는지 설치법 누락, 장황한 철학
설계 문서 결정과 이유, 고려한 대안 구현 디테일만 나열
PR 본문 무엇을·왜 바꿨는지 + 테스트 방법 diff를 그대로 설명
변경 요약 사용자 영향 내부 리팩터링 자랑
주석 (작성 안 하는 게 기본) WHAT 설명, 이슈번호 박제

7. 분량

  • 필요한 만큼만. 같은 내용을 두 번 설명하지 않는다. 모든 섹션이 가치를 더해야 한다.

(산출 포맷이 docx/pdf일 때)

  • Markdown 가 docx/pdf면, 렌더링 후 페이지 이미지를 직접 보고 클리핑·깨진 표·정렬 불량을 점검한 뒤 제출한다.

체크리스트 (제출 전)

  • 결론이 맨 앞에 있는가
  • 제목 계층이 일관적인가
  • 코드/경로/명령어가 코드 표기인가
  • 도구 내부 토큰·깨진 인용·플레이스홀더가 없는가
  • ASCII 하이픈을 썼는가
  • 외부 사실에 출처가 있는가
  • 요청하지 않은 문서를 자발적으로 만들지 않았는가
  • 한 번 더 읽었을 때 군더더기·중복이 없는가

Read the full file on GitHub · 80 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 · 80 lines · 45 tokens per session scan A 376c3d4b0a72

Subscribe to this mod's changes

doc-writing is a skill published in the GitHub repository Kimyongari/harness-factory (5 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,226 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

anti-slop-design

Category-aware design skill that builds distinctive, production-grade UIs. Brand-vs-product register, color strategy commitment, scene-based theme choice, palettes, font pairings, UX patterns, shadcn/token integration, empty-error-loading copy, secondary slop signals, multimodal design parity from mocks, and a…

madebyaris/advance-minimax-m3-cursor-rules · 78 tokens

3d-web-experiences

Build distinctive, performant, production-grade 3D on the web with Three.js, React Three Fiber, and WebGL. Use when the user asks to "build a 3D scene", "add a 3D hero/landing", "make a product viewer/configurator", mentions three.js / react-three-fiber / r3f / drei / webgl / shaders, or asks to make an existing 3D…

madebyaris/advance-minimax-m3-cursor-rules · 147 tokens

deep-research

Conducts multi-step deep research on any topic using iterative search, reflection, and synthesis. Use when the user asks to research, investigate, survey, compare, analyze, deep-dive, or explore a topic in depth. Covers web research, codebase analysis, documentation review, mixed-source investigation, and M3…

madebyaris/advance-minimax-m3-cursor-rules · 72 tokens

minimax-m3-long-context

How to use MiniMax M3's 1M-token MSA context productively: what to load vs. compress, when to retrieve vs. ingest, how to keep skills shallow in the always-on prompt and deep in skills, and how to plan retention across iterations. Load when the task might exceed 200K tokens, when the user asks to "keep all of this in…

madebyaris/advance-minimax-m3-cursor-rules · 101 tokens

minimax-m3-multimodal-input

How to use MiniMax M3's native multimodal input (image, video) for grounded decisions in coding work. Covers reading attached images/frames, treating them as ground truth for visual claims, screenshot diffing, design parity from mockups, and routing visual evidence through reports and PRs. Load when the user attaches…

madebyaris/advance-minimax-m3-cursor-rules · 121 tokens

minimax-multimodal-toolkit

MiniMax-native multimodal workflow for image, video, voice, music, and media-processing tasks. Use when the user asks to generate image/video/audio assets, wants MiniMax-specific media APIs, needs TTS or voice workflows, wants reproducible local media outputs, or needs FFmpeg-style processing around generated media.…

madebyaris/advance-minimax-m3-cursor-rules · 97 tokens