agentmods.dev

copilot-agent-workspace: Skill for Claude Code

.github/skills/document-writer/SKILL.md

document-writer is a skill for Claude Code, Codex from kanazawazawa/copilot-agent-workspace. It costs 61 tokens per session (947 once invoked), scanned A, original, MIT.

A Japanese-language skill for creating business documents in Markdown, a plain-text format that is easy to reuse and track in version control.

In plain words
What is it for?
It is for preparing Japanese proposals, reports, specifications, agendas, requirements documents, and meeting records.
Why use it?
It gives proposals, reports, and meeting minutes a clear structure and requires the outline to be approved before drafting.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is kanazawazawa/copilot-agent-workspace's own configuration. It tells Claude Code and Codex how to work on copilot-agent-workspace 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 copilot-agent-workspace configures →

not rated 5repo 5mo ago A scan 61 tokens original MIT
View source ↗ kanazawazawa/copilot-agent-workspace
Reuse

Borrowing it

Nothing to install: this file belongs to kanazawazawa/copilot-agent-workspace. 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/kanazawazawa/copilot-agent-workspace/master/.github/skills/document-writer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kanazawazawa/copilot-agent-workspace

Made for: Claude Code, Codex.

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 document-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/kanazawazawa/copilot-agent-workspace/document-writer/github.svg)](https://agentmods.dev/skills/kanazawazawa/copilot-agent-workspace/document-writer)
Your own site
<a href="https://agentmods.dev/skills/kanazawazawa/copilot-agent-workspace/document-writer"><img src="https://agentmods.dev/badge/skills/kanazawazawa/copilot-agent-workspace/document-writer/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 document-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/kanazawazawa/copilot-agent-workspace/document-writer"><img src="https://agentmods.dev/badge/skills/kanazawazawa/copilot-agent-workspace/document-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 947 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 $0.00061 $0.00947
Opus 5.5 $0.00024 $0.00379
Sonnet 5.5 $0.00012 $0.00189
Haiku 4.5 $0.00006 $0.00095

Measured 2mo ago against content hash 9791bb90f0df, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

document-writer 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 2mo 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.

.github/skills/document-writer/SKILL.md · 114 lines

What it actually says

Markdown ドキュメント作成スキル

概要

提案書・報告書・議事録などのビジネスドキュメントを Markdown で作成する。 再利用性・検索性・差分管理に優れた形式で、そのまま使える品質を目指す。

トリガーワード

  • 「提案書」「報告書」「議事録」「ドキュメント作成」
  • 「Word」「Markdown で書いて」「文書作成」
  • 「アジェンダ」「要件定義書」「仕様書」

使用しない場合

  • PPT / スライド作成（→ slide-creator）
  • README やコード内コメント
  • API ドキュメントの自動生成

作成ワークフロー

Step 1: 要件確認

確認項目 質問
目的 何のためのドキュメント？（提案、報告、教育、共有）
対象読者 誰が読む？（経営層、技術者、顧客、社内）
分量 目安は？
トーン フォーマル？カジュアル？

Step 2: アウトライン提示

必ず内容作成の前にアウトラインを提示し、承認を得る。

Step 3: コンテンツ作成

承認後、セクションごとに内容を作成する。

ドキュメント種別テンプレート

提案書

  1. エグゼクティブサマリー
  2. 現状の課題
  3. 提案するソリューション
  4. 期待される効果（定量＋定性）
  5. 実施スケジュール
  6. 概算費用
  7. 体制・サポート
  8. 次のステップ

技術調査報告

  1. 調査の目的
  2. 調査範囲と手法
  3. 調査結果（サマリー）
  4. 詳細分析
  5. 比較表（該当する場合）
  6. 推奨事項
  7. 参考文献

議事録

  1. 会議情報（日時・参加者・目的）
  2. アジェンダ
  3. 議論内容
  4. 決定事項
  5. アクションアイテム（担当者・期限）

対象読者別の調整

対象 フォーカス 避けるべきこと
経営層 ビジネスインパクト、ROI、リスク 技術詳細、専門用語
技術者 アーキテクチャ、実装、選定理由 曖昧な表現、マーケ用語
顧客 課題解決、具体的なメリット 自社都合の話

図表の使い方

  • Mermaid ダイアグラムを積極的に使う（フローチャート、シーケンス図、ガントチャート）
  • 比較は Markdown テーブルで
  • 数字は表やリストで視覚的に整理する

出力ルール

保存先

output/documents/YYYY-MM-DD_HHmmss_ドキュメント名/document.md

品質基準

  • 日本語で作成する
  • そのまま使える品質を目指す
  • 具体的な数字・事実を優先する（「多くの」ではなく「80%の」）
  • ドキュメントの最後に情報源一覧を入れる
  • 既存ファイルは絶対に上書き・削除しない
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. 2mo ago First seen · 114 lines · 61 tokens per session scan A 9791bb90f0df

Subscribe to this mod's changes

document-writer is a skill published in the GitHub repository kanazawazawa/copilot-agent-workspace (5 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 947 once invoked, about $0.0002 per session on Opus 5.5. 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.

DocumentsWriting and docs
Related

document-writer compared with skills from other repositories

document-writer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
document-writerkanazawazawa/copilot-agent-workspaceSkill55mo agoMITA61Claude Code, Codex
orbit-notionnexu-io/open-designSkill106kyesterdayApache-2.0A117Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35k2d agoApache-2.0A123Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill49kyesterdayMITA48Claude Code
legal-holdanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A68Claude Code
ppt-reviewOrkas-AI/OrkasSkill9.0ktodayMITA2Claude Code, Codex
feishuHmbown/CodeWhaleSkill41k5d agoMITA33Claude Code, Codex