writing-guide

writing-guide is a skill for Claude Code from minorun365/my-claude-code-settings. It costs 84 tokens per session (15,125 once invoked), scanned A, a copy of smart-search, MIT.

A general writing guide for producing clear, natural Japanese text, including blogs, presentations, books, and technical documents. It explains how to introduce terms, choose examples, handle numbers, and structure paragraphs.

In plain words
What is it for?
Use it when writing, rewriting, or reviewing Japanese articles, documentation, slides, newsletters, or other longer-form material.
Why use it?
It helps remove mechanical or translated-sounding phrasing and avoids common patterns associated with AI-generated writing. It also keeps short public-facing copy from becoming vague or overworked.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it when writing, rewriting, or reviewing Japanese articles, documentation, slides, newsletters, or other longer-form material.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/minorun365/my-claude-code-settings/writing-guide
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add minorun365/my-claude-code-settings --skill writing-guide
Clone the repo
git clone --depth 1 https://github.com/minorun365/my-claude-code-settings

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 writing-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/minorun365/my-claude-code-settings/writing-guide.svg)](https://agentmods.dev/skills/minorun365/my-claude-code-settings/writing-guide)
Your own site
<a href="https://agentmods.dev/skills/minorun365/my-claude-code-settings/writing-guide"><img src="https://agentmods.dev/badge/skills/minorun365/my-claude-code-settings/writing-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,125 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 83% copy Near-identical to another mod 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 $0.00084 $0.15125
Opus 5 $0.00042 $0.07562
Sonnet 5 $0.00017 $0.03025
Haiku 4.5 $0.00008 $0.01512

Measured 8d ago against content hash 9f422eded293, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

writing-guide 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 8d 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.

Origin

This is a copy

83% identical to smart-search — 433 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

claude/skills/writing-guide/SKILL.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

汎用執筆ガイド — AI臭さを消す文章術

技術ブログ、社内資料、手順書、スライド、書籍など、あらゆる書き物に共通する文章スタイルルール。 各プロジェクト固有ルール(CLAUDE.md等)と併用して使う。

このスキルの使い方

執筆作業時の「品質チェックリスト」として使う。

  1. 執筆前: このルールを頭に入れてから書き始める
  2. 執筆中: AI臭い表現が出てきたら即座に書き直す
  3. 執筆後: 完成した文章を禁止リストと照合してセルフレビュー

**「提案段階のドラフト」も執筆として扱う。**本文候補の1段落・見出し案・キャッチコピー案をユーザーへ提示する時点で、すでに禁止リストの検品対象。承認後・反映時に直せばよいと後回しにすると、初稿の型(逆接タメ・「のです」締め・比喩スローガン締め等)がそのまま指摘対象になる。

**200〜300字の短い対外文こそ検品対象。**登壇のセッション概要、イベントページの掲載文、プロフィール紹介文、書籍の内容紹介など、外部に載る短い紹介文は「原稿ではないから」「短いから」と素通りしやすい。しかし短い文ほど最後の一文が目立つので、キメ台詞構文(「〜のは◯◯です」)が締めに紛れ込む確率はむしろ高い。書く前にこのスキルを開き、書いたあとに最頻出パターン6つと照合してから提示する。

 直し方は言い換えではなく削除。この種の締めは、直前の文で内容が完結しているところへ教訓を足しているだけなので、平明な言い方へ置き換えても蛇足のまま残る。

何度も再発している最頻出パターン(書き終えたら、まずこの9つを見る)

下の禁止リストは長いので、再発指摘を受けた回数が多いものだけをここへ抜き出す。書いた直後にこの9つだけは必ず自分で見返す。全部が下の表にも載っているが、表の中に埋もれると素通りしてしまう。

  1. 段落末の回収まとめ文(「これが◯◯の形です」「〜という方針は、こうして形にできます」「〜と考えると整理しやすくなります」「◯◯そのものです」)。**記録上いちばん再発している型で、しかも既存原稿より自分が新しく書く文で出る。**説明が済んだ直後に抽象ラベルへ包み直す一文を足さない。言い終えたらそのまま終える

  2. 「効く」の全用法(効く/効きます/効いてきます/効かせる)

  3. ダッシュ(—、──、―、- での区切り)

  4. 体言止めの列挙を「。」で締める(「〜する会議のメモ。」)→ 「〜など。」で終わらせる

  5. こなれ比喩動詞でのキメ(届かない/拾ってくれます/地続き/一撃で/仕込みます)

  6. 一段落が長いまま改行しない(とくにMEMO・コラムなど囲みの中)

  7. AIの挙動を断定する(「〜されます」と一通りに言い切る。実際は複数のやり方がありうる)

  8. 箇条書きの行頭を「太字ラベル+コロン」で始める(「- 見た目を自分で決められる:HTMLの体裁は〜」)。§1 の「項目名: 説明のセット形式」と「太字の多用」が同時に出る型で、説明文をREADME・報告・資料へ書くときにほぼ毎回出る。直し方は言い換えではなく箇条書きごと地の文の段落へ戻す(ラベルを外して並べ直すだけだと、今度は同じ構文の箇条書きが残る)。2つ3つの項目を立てたくなったら、それは段落1つで書ける内容だと考える

    ⚠️ ただし「箇条書きを使うな」ではない。禁じているのは行頭太字+コロンという形であって、箇条書きそのものではない。 このルールを丸ごと適用して地の文だけで押し通すと、条件の列挙まで段落へ溶けて逆に読めなくなる。地の文へ戻すのは「1段落で書ける内容を2〜3項目に割ったとき」だけで、並列に並ぶ条件・対象・例外が4つ以上あるなら箇条書きが正しい。判断基準は §6 の「GitHubのREADME」節にある形の選び方の表を使う

  9. 成果物への絵文字の散布。見出しの頭(## 🚀 アプリ)、箇条書きやカードのアイコン代わり(📊 パワポ作るマン)が二大パターン。**1個ずつ見ると可愛いが、並ぶと一気にAIが書いた資料になる。**装飾として足したくなった箇所は、何も足さないのが正解。チャットの応対に絵文字を混ぜるのは別ルール(~/.claude/AGENTS.md 冒頭)なので混同しない

※ ただしそのプロジェクトで承認済みの正式概念語は対象外。例:ある書籍で「ガードレール」を節見出しに採用しているなら、その本の中では禁止語ではなく用語として扱う。禁止語の一括 grep を機械実行しないのはこのため(誤検出が多すぎて使われなくなる)。

Read the full file on GitHub · 384 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. 8d ago First seen · 384 lines · 84 tokens per session scan A 9f422eded293

Subscribe to this mod's changes

writing-guide is a skill published in the GitHub repository minorun365/my-claude-code-settings (129 stars, last pushed 9d ago), licensed MIT. It adds 84 tokens to every session and 15,125 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to smart-search, differing in 433 lines, and is treated as a copy.

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens