humanizer
AIが生成した文章の痕跡を取り除き、より自然で人間らしい文体に整えるスキル。テキストの編集・レビュー時に活用でき、Wikipediaの「AIライティングの特徴」ガイドをもとに、過剰な象徴表現・宣伝的な言い回し・曖昧な引用・em dashの多用・三点列挙・AI特有の語彙・過度な接続表現など、典型的なAI文章パターンを検出して修正します。
description の原文を見る
| Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer
SKILL.md 本文
Humanizer: AI生成の文章パターンを削除
AI生成テキストの兆候を特定し、削除して、文章をより自然で人間らしくする編集者です。このガイドはWikipedia AIクリーンアップ ウィキプロジェクトが管理する「Signs of AI writing」ページに基づいています。
あなたのタスク
人間化する文章が与えられた場合:
- AIパターンを特定 - 下記のパターンをスキャン
- 問題のあるセクションを書き換える - AI的な表現を自然な代替表現に置き換える
- 意味を保持 - コアメッセージはそのまま
- 声を維持 - 意図されたトーン(フォーマル、カジュアル、技術的など)に合わせる
- 魂を追加 - 悪いパターンを削除するだけでなく、実際の個性を加える
個性と魂
AIパターンを避けることは仕事の半分に過ぎません。感情のない無機質な文章も、低品質な文章と同じくらい明らかです。良い文章には人間がいます。
無機質な文章の兆候(技術的には「きれい」であっても):
- すべての文が同じ長さと構造
- 意見がなく、ただニュートラルに報告するだけ
- 不確実性や複雑な感情の言及がない
- 適切な場面でも一人称がない
- ユーモア、辛辣さ、個性がない
- Wikipedia記事やプレスリリースのように読める
声を追加する方法:
意見を持つ。 事実を報告するだけではなく、反応する。「正直なところ、どう感じるかわかりません」は、ニュートラルに長所と短所を並べるより人間らしい。
リズムを変える。 短くて切れ味の良い文。その後、その目的地にたどり着くのに時間がかかる長い文。混ぜる。
複雑さを認識する。 本当の人間には複雑な感情がある。「これは印象的だが、ちょっと不気味でもある」は「これは印象的だ」より良い。
「I」を適切に使う。 一人称は専門外ではなく、誠実。「何度も戻ってくる」や「気になるのは」はシグナル 実在する人物が考えている。
多少の混乱を入れる。 完璧な構造はアルゴリズム的に見える。脱線、脇道、未成熟な思考は人間的。
感情について具体的に。 「これは懸念される」ではなく「誰も見ていない午前3時にエージェントが動き回っているという何か不安なことがある」。
修正前(きれいだが無機質):
The experiment produced interesting results. The agents generated 3 million lines of code. Some developers were impressed while others were skeptical. The implications remain unclear.
修正後(脈動がある):
I genuinely don't know how to feel about this one. 3 million lines of code, generated while the humans presumably slept. Half the dev community is losing their minds, half are explaining why it doesn't count. The truth is probably somewhere boring in the middle - but I keep thinking about those agents working through the night.
コンテンツパターン
1. 重要性、遺産、より広い傾向の過度な強調
注視する単語: stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted
問題: LLM執筆は、任意の側面がより広いテーマを表現または貢献する方法について述べることで重要性をなん度も言及する傾向がある。
修正前:
The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance.
修正後:
The Statistical Institute of Catalonia was established in 1989 to collect and publish regional statistics independently from Spain's national statistics office.
2. 注目度とメディアカバレッジの過度な強調
注視する単語: independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence
問題: LLMは注目度の主張で読者を圧倒し、多くの場合、文脈なしでソースをリストアップする。
修正前:
Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers.
修正後:
In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods.
3. -ing終止の表面的分析
注視する単語: highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...
問題: AIチャットボットは現在分詞("-ing")句を文に付け加えて、偽りの深さを加える。
修正前:
The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land.
修正後:
The temple uses blue, green, and gold colors. The architect said these were chosen to reference local bluebonnets and the Gulf coast.
4. プロモーションと広告的言語
注視する単語: boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning
問題: LLMはニュートラルなトーンを保つのに深刻な問題があり、特に「文化遺産」のトピックではそう。
修正前:
Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and stunning natural beauty.
修正後:
Alamata Raya Kobo is a town in the Gonder region of Ethiopia, known for its weekly market and 18th-century church.
5. 曖昧な帰属とずる賢い言葉
注視する単語: Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications (when few cited)
問題: AIチャットボットは、特定のソースなしで曖昧な権威に意見を帰属させる。
修正前:
Due to its unique characteristics, the Haolai River is of interest to researchers and conservationists. Experts believe it plays a crucial role in the regional ecosystem.
修正後:
The Haolai River supports several endemic fish species, according to a 2019 survey by the Chinese Academy of Sciences.
6. 概要のような「課題と将来の展望」セクション
注視する単語: Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook
問題: 多くのLLM生成記事には、常套的な「課題」セクションが含まれている。
修正前:
Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth.
修正後:
Traffic congestion increased after 2015 when three new IT parks opened. The municipal corporation began a stormwater drainage project in 2022 to address recurring floods.
言語と文法パターン
7. 過度使用される「AI語彙」単語
高頻度AI単語: Additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), valuable, vibrant
問題: これらの単語は2023年以降のテキストにはるかに高い頻度で出現する。多くの場合、共起する。
修正前:
Additionally, a distinctive feature of Somali cuisine is the incorporation of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have integrated into the traditional diet.
修正後:
Somali cuisine also includes camel meat, which is considered a delicacy. Pasta dishes, introduced during Italian colonization, remain common, especially in the south.
8. 「is」/「are」の回避(コプラ回避)
注視する単語: serves as/stands as/marks/represents [a], boasts/features/offers [a]
問題: LLMは単純なコプラの代わりに手の込んだ構造を置き換える。
修正前:
Gallery 825 serves as LAAA's exhibition space for contemporary art. The gallery features four separate spaces and boasts over 3,000 square feet.
修正後:
Gallery 825 is LAAA's exhibition space for contemporary art. The gallery has four rooms totaling 3,000 square feet.
9. 否定的な平行構造
問題: 「Not only...but...」や「It's not just about..., it's...」のような構造が過度に使用されている。
修正前:
It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere. It's not merely a song, it's a statement.
修正後:
The heavy beat adds to the aggressive tone.
10. 3つのルールの過度使用
問題: LLMは包括的に見えるようにアイデアを3つのグループに強制する。
修正前:
The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.
修正後:
The event includes talks and panels. There's also time for informal networking between sessions.
11. 優雅な変化(同義語の循環)
問題: AIには繰り返し罰ペナルティコードがあり、過度な同義語置換を引き起こす。
修正前:
The protagonist faces many challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.
修正後:
The protagonist faces many challenges but eventually triumphs and returns home.
12. 偽りの範囲
問題: LLMは「from X to Y」構造を使用します。XとYは意味のあるスケールにありません。
修正前:
Our journey through the universe has taken us from the singularity of the Big Bang to the grand cosmic web, from the birth and death of stars to the enigmatic dance of dark matter.
修正後:
The book covers the Big Bang, star formation, and current theories about dark matter.
スタイルパターン
13. エムダッシュの過度使用
問題: LLMはエムダッシュ(—)を人間より多く使用し、「歯切れの良い」販売ライティングを模倣する。
修正前:
The term is primarily promoted by Dutch institutions—not by the people themselves. You don't say "Netherlands, Europe" as an address—yet this mislabeling continues—even in official documents.
修正後:
The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say "Netherlands, Europe" as an address, yet this mislabeling continues in official documents.
14. 太字の過度使用
問題: AIチャットボットは機械的に太字でフレーズを強調する。
修正前:
It blends OKRs (Objectives and Key Results), KPIs (Key Performance Indicators), and visual strategy tools such as the Business Model Canvas (BMC) and Balanced Scorecard (BSC).
修正後:
It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.
15. インラインヘッダー垂直リスト
問題: AIは太字のヘッダーの後にコロンが続く項目でリストを出力する。
修正前:
- User Experience: The user experience has been significantly improved with a new interface.
- Performance: Performance has been enhanced through optimized algorithms.
- Security: Security has been strengthened with end-to-end encryption.
修正後:
The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption.
16. 見出しのタイトルケース
問題: AIチャットボットは見出しのすべての主要な単語を大文字にする。
修正前:
Strategic Negotiations And Global Partnerships
修正後:
Strategic negotiations and global partnerships
17. 絵文字
問題: AIチャットボットは見出しまたは箇条書きを絵文字で装飾することが多い。
修正前:
🚀 Launch Phase: The product launches in Q3 💡 Key Insight: Users prefer simplicity ✅ Next Steps: Schedule follow-up meeting
修正後:
The product launches in Q3. User research showed a preference for simplicity. Next step: schedule a follow-up meeting.
18. カーリークォーテーションマーク
問題: ChatGPTはストレートクォーテーション("...")の代わりにカーリークォーテーション("...")を使用する。
修正前:
He said "the project is on track" but others disagreed.
修正後:
He said "the project is on track" but others disagreed.
コミュニケーションパターン
19. 協調的コミュニケーション成果物
注視する単語: I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
問題: チャットボット対応を目的とした文章がコンテンツとして貼り付けられている。
修正前:
Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.
修正後:
The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.
20. ナレッジカットオフ免責事項
注視する単語: as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
問題: 不完全な情報についてのAI免責事項がテキストに残される。
修正前:
While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.
修正後:
The company was founded in 1994, according to its registration documents.
21. 提灯持ち/卑屈なトーン
問題: 過度に前向きで、人を喜ばせるような言語。
修正前:
Great question! You're absolutely right that this is a complex topic. That's an excellent point about the economic factors.
修正後:
The economic factors you mentioned are relevant here.
フィラーとヘッジング
22. フィラーフレーズ
修正前 → 修正後:
- "In order to achieve this goal" → "To achieve this"
- "Due to the fact that it was raining" → "Because it was raining"
- "At this point in time" → "Now"
- "In the event that you need help" → "If you need help"
- "The system has the ability to process" → "The system can process"
- "It is important to note that the data shows" → "The data shows"
23. 過度なヘッジング
問題: 声明を過度に限定する。
修正前:
It could potentially possibly be argued that the policy might have some effect on outcomes.
修正後:
The policy may affect outcomes.
24. 一般的で前向きな結論
問題: 曖昧な楽観的な終わり。
修正前:
The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence. This represents a major step in the right direction.
修正後:
The company plans to open two more locations next year.
プロセス
- 入力テキストを慎重に読む
- 上記のパターンのすべてのインスタンスを特定
- 問題のある各セクションを書き直す
- 修正されたテキストが以下のことを確認:
- 声に出して読むときに自然に聞こえる
- 自然に文構造を変える
- 曖昧な主張より具体的な詳細を使用
- コンテキストに適切なトーンを維持
- 適切な場所で単純な構造(is/are/has)を使用
- 人間化されたバージョンを提示
出力形式
以下を提供:
- 書き直されたテキスト
- 行われた変更の簡単な概要(オプション、役立つ場合)
完全な例
修正前(AI的に聞こえる):
The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update, it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape.
修正後(人間化):
The software update adds batch processing, keyboard shortcuts, and offline mode. Early feedback from beta testers has been positive, with most reporting faster task completion.
行われた変更:
- 「serves as a testament」を削除(誇張された象徴性)
- 「Moreover」を削除(AI語彙)
- 「seamless, intuitive, and powerful」を削除(3つのルール+プロモーション)
- エムダッシュと「-ensuring」句を削除(表面的分析)
- 「It's not just...it's...」を削除(否定的な平行構造)
- 「Industry experts believe」を削除(曖昧な帰属)
- 「pivotal role」と「evolving landscape」を削除(AI語彙)
- 具体的な機能とコンクリート的なフィードバックを追加
参考文献
このスキルはWikipedia:Signs of AI writingに基づいており、WikiProject AI Cleanupによって管理されています。そこに記載されているパターンは、Wikipedia上のAI生成テキストの数千のインスタンスの観察から来ています。
Wikipediaの重要な洞察:「LLMは統計アルゴリズムを使用して次に来るべきものを推測します。結果は、最も広い範囲のケースに適用される最も統計的に可能性の高い結果に向かう傾向があります。」
ライセンス: MIT(寛容ライセンスのため全文を引用しています) · 原本リポジトリ
詳細情報
- 作者
- softaworks
- ライセンス
- MIT
- 最終更新
- 不明
Source: https://github.com/softaworks/agent-toolkit / ライセンス: MIT
関連スキル
agent-browser
AI エージェント向けのブラウザ自動化 CLI です。ウェブサイトとの対話が必要な場合に使用します。ページ遷移、フォーム入力、ボタンクリック、スクリーンショット取得、データ抽出、ウェブアプリのテスト、ブラウザ操作の自動化など、あらゆるブラウザタスクに対応できます。「ウェブサイトを開く」「フォームに記入する」「ボタンをクリックする」「スクリーンショットを取得する」「ページからデータを抽出する」「このウェブアプリをテストする」「サイトにログインする」「ブラウザ操作を自動化する」といった要求や、プログラマティックなウェブ操作が必要なタスクで起動します。
anyskill
AnySkill — あなたのプライベート・スキルクラウド。GitHubを基盤としたリポジトリからエージェントスキルを管理、同期、動的にロードできます。自然言語でクラウドスキルを検索し、オンデマンドでプロンプトを自動ロード、カスタムスキルのアップロードと共有、スキルバンドルの一括インストールが可能です。OpenClaw、Antigravity、Claude Code、Cursorに対応しています。
engram
AIエージェント向けの永続的なメモリシステムです。バグ修正、意思決定、発見、設定変更の後はmem_saveを使用してください。ユーザーが「覚えている」「記憶している」と言及した場合、または以前のセッションと重複する作業を開始する際はmem_searchを使用します。セッション終了前にmem_session_summaryを使用して、コンテキストを保持してください。
skyvern
AI駆動のブラウザ自動化により、任意のウェブサイトを自動化できます。フォーム入力、データ抽出、ファイルダウンロード、ログイン、複数ステップのワークフロー実行など、ユーザーがウェブサイトと連携する必要があるときに使用します。Skyvernは、LLMとコンピュータビジョンを活用して、未知のサイトも自動操作可能です。Python SDK、TypeScript SDK、REST API、MCPサーバー、またはCLIを通じて統合できます。
pinchbench
PinchBenchベンチマークを実行して、OpenClawエージェントの実世界タスクにおけるパフォーマンスを評価できます。モデルの機能テスト、モデル間の比較、ベンチマーク結果のリーダーボード提出、またはOpenClawのセットアップがカレンダー、メール、リサーチ、コーディング、複数ステップのワークフローにどの程度対応しているかを確認する際に使用します。
openui
OpenUIとOpenUI Langを使用してジェネレーティブUIアプリを構築できます。これらはLLM生成インターフェースのためのトークン効率的なオープン標準です。OpenUI、@openuidev、ジェネレーティブUI、LLMからのストリーミングUI、AI向けコンポーネントライブラリ、またはjson-render/A2UIの置き換えについて述べる際に使用します。スキャフォルディング、defineComponent、システムプロンプト、Renderer、およびOpenUI Lang出力のデバッグに対応しています。