Introduction

Hello. My name is Yamazumi, and I work in sales at Classmethod.

At Classmethod, not only engineers but also members involved in sales and back-office operations are using generative AI to improve work efficiency.
We catch up on update information that appears rapidly every day and incorporate it into our work.

Among these tools, Claude has been gaining popularity among employees. While I myself mainly used Gemini in Google Workspace until recently, Claude is now becoming my main tool. Claude's capabilities have increased considerably.

Today, I'd like to introduce the Sales plugin for Claude, a set of sales-oriented functions.
Along with each feature, I'll share my review as a frontline sales person who has actually used them.

What is Claude's "Sales plugin"?

How to start using the plugin?

The Sales plugin is Anthropic's sales support plugin that can be used in Claude desktop app's "Cowork mode".

Installation is easy. You can install it using either of the following methods:

• With Claude desktop app installed, install the plugin from the Claude official website
• From the "+" button on the "New Task" screen in Claude desktop app's Cowork screen, go to "Plugins" > "Add plugin"
  
  ⇧You can add from here.

For plugin functionality, there are methods to add from "Anthropic & Partner" (plugins created by Anthropic official or partners like SalesForce), or to add those created by general users from GitHub or marketplaces.

The Sales plugin introduced here is officially created by Anthropic.
For plugins other than official ones, there may be some that have not been verified for operation, so caution is needed when using them.

I have only used Anthropic official plugins so far.

Inside the plugin

The "Sales plugin" can be thought of as a "collection of useful functions for sales professionals."

The plugin consists of 9 Skills.
(When the plugin was first released, it consisted of 6 Skills and 3 Commands, but with a recent plugin update, everything has been integrated into Skills.)

What are Skills?
These are features that are automatically triggered during conversations between users and Claude. For example, if you say "research company X," Claude will determine "I should use that skill for this case!" and launch the appropriate skill for you. You can also explicitly call them using the / command.

You can check the list of Skills and the contents of each Skill from the customization screen. You can also edit them. You can have Claude edit them through dialogue, or you can directly edit the Markdown files yourself.

⇧You can check the contents of each Skill like this.

You can also use connectors to integrate with external tools like CRM (SalesForce, HubSpot, etc.), calendar, email, Slack, and more.
Here are the connectors prepared by default in the Sales plugin:

You can manage permissions for each tool. You can set whether to give only read permission or write permission for each service and function. This is an example of Google Calendar.

While integration greatly enhances functionality, you can use it without external service integration for now without any issues.

Skills can also be customized later. If you're thinking "I don't understand this well!", it's probably best to try them individually with default settings first, and then customize as needed.

Introduction of All 9 Functions

From here, I'll introduce all functions along with my actual usage experience.

1. Account Research

Just by saying "research X company," you can get the following information at once:

• Company overview (business description, size, industry)
• Latest news (funding, M&A, executive movements, etc.)
• Hiring trends (what kind of talent they're looking for, whether they're expanding, etc.)
• Key person information (management, decision makers)
• Overview of products and services

Let's actually try it. I'll instruct: "Research Classmethod Inc."

What you see at the bottom of the chat is the working folder name. I specified a folder for writing this blog. By specifying a folder, you can have all files created in this session organized here.
If there's other information that should be referenced, you can just put it in this folder.

With just one line of instruction, as shown in "Progress" on the right, it creates a work plan and proceeds with the research.
Since I have enabled the HubSpot connector, it includes checking HubSpot, but this time I'll have it proceed with research using only web search. I can simply instruct Claude from the side: "Please use only web search without connectors."

The research was completed in just a matter of minutes. I think it took less than 5 minutes.

Here's the account research report that was created:

# Research: クラスメソッド株式会社（Classmethod, Inc.）
**Generated:** 2026年3月16日 **Sources:** Web Search

---

## Quick Take

クラスメソッドは日本最大級のAWSプレミアパートナーであり、クラウド総合支援・データ活用・生成AIを中心に急成長を続けるSIer。売上高は2025年度に950億円を突破し、グローバル展開（ドイツ、カナダ、インド、韓国、マレーシア等）も加速中。直近ではAnthropic社とのリセラー契約やdbt Labs公式トレーニングパートナー認定など、AIとデータ領域でのパートナーシップ拡大が顕著。

---

## Company Profile

|Field|Value|
|---|---|
|**会社名**|クラスメソッド株式会社|
|**Website**|[https://classmethod.jp/](https://classmethod.jp/)|
|**業種**|システムインテグレータ（SIer）/ クラウドコンサルティング|
|**従業員数**|単体 560名 / グループ全体 840名（2025年10月時点）|
|**本社**|東京都港区西新橋1-1-1 日比谷フォートタワー26F|
|**設立**|2004年7月7日|
|**資本金**|1億円|
|**売上高**|950億5,600万円（2025年度）|
|**代表者**|横田 聡|
|**平均年齢**|37.5歳|

### What They Do

企業向けにAWS・Google Cloud等のクラウド総合支援、データ分析基盤構築、生成AIコンサルティング、アプリケーション開発（LINE/iOS等）、SaaS導入支援を提供。直取引で業界・規模問わず4,000社以上の支援実績を持つ。技術ブログ「DevelopersIO」は30,000本以上の記事を公開し、技術コミュニティへの貢献でも知られる。

### 売上高推移

|年度|売上高|
|---|---|
|2019年度|74億円|
|2020年度|131億円|
|2021年度|216億円|
|2022年度|304億円|
|2023年度|427億円|
|2024年度|590億円|
|2025年度|**950億円**|

→ 過去6年間で約13倍の急成長

---

## Recent News（直近90日）

- **Anthropic社とリセラー契約を締結**（2026年3月2日）— Amazon Bedrock経由でのClaude再販が可能に。エンタープライズ企業の生成AI活用を推進。
- **日本初のdbt Labs公式トレーニングパートナー認定を取得**（2026年3月10日）— データ活用基盤支援の強化。
- **マレーシア・クアラルンプールオフィス開設**（2026年1月）— グローバル展開のさらなる加速。
- **Google Cloud Partner Top Engineer 2026受賞**（2026年1月）— 5名のエンジニアが受賞。マルチクラウド対応力の証明。
- **Classmethod Showcase開催発表**（2026年2月）— データ活用を事例で学ぶオンラインカンファレンス。

---

## Hiring Signals（採用動向）

- **87件の求人**を公式キャリア採用サイトで公開（2025年1月時点）
- 主な募集領域：プロジェクトマネージャー、エンタープライズマイグレーション、Google Cloudデータ分析、セールス/カスタマーサクセス、事業企画/マーケティング
- **新卒採用**もマイナビ2027で展開中
- 成長指標：年間売上が前年度比60%増のペースで、積極採用が続いていると推察

---

## Key People

### 横田 聡 — 代表取締役社長

|Field|Detail|
|---|---|
|**役職**|代表取締役|
|**備考**|クラスメソッド創業者。AWS関連事業を日本トップクラスに育て上げた|

---

## グループ会社

|会社名|概要|
|---|---|
|**プリズマティクス株式会社**|EC/CRM基盤|
|**ネクストモード株式会社**|SaaS導入支援|
|**クラスメソッドオペレーションズ株式会社**|運用支援（旧アノテーション、2025年12月社名変更）|
|**プロパゲート株式会社**|—|
|**アンダースコア株式会社**|—|
|**クラスメソッドテクノロジーズ株式会社**|—|

---

## 受賞歴・パートナーシップ

### AWS関連

- ✅ **SI Partner of the Year – GLOBAL**（2022）— グローバル最優秀SIパートナー
- ✅ **SI Partner of the Year – APJ**（2023）— アジア太平洋最優秀
- ✅ **Education Consulting Partner of the Year – Global**（2024）
- ✅ **Consulting Partner of the Year – Japan**（2025）
- ✅ **AWS生成AIイノベーションセンター PIA**に日本企業初参画（2025年11月）
- ✅ AWS生成AIコンピテンシー取得（2025年6月）
- ✅ AWSプレミアティアサービスパートナー（2015年以降継続）
- ✅ 3,500以上のAWS認定資格保有

### その他

- ✅ LINEヤフー Partner Award 2025「Best LINEミニアプリ Award」
- ✅ Snowflake「Rising Star Partner of the Year」
- ✅ 三菱UFJ銀行DX支援スキーム参画

---

## 事業領域

|サービス|概要|
|---|---|
|**クラウド総合支援**|AWS/GCPの設計・構築・運用・移行（5,000件以上、35,000+AWSアカウント管理）|
|**データ活用基盤構築**|Snowflake、dbt、Redshift等を活用したデータ分析環境の構築|
|**生成AIコンサルティング**|Anthropic Claude、Amazon Bedrockを活用したAI導入支援|
|**アプリ開発**|LINE、iOS等のアプリケーション企画・開発|
|**SaaS導入支援**|各種SaaSの導入・活用コンサルティング|
|**EC/CRM基盤**|プリズマティクスによるEC・CRMシステム構築|

---

## 主要クライアント（公開情報）

Honda、資生堂、サントリー、カプコン、スシローなど大手企業を多数支援

---

## グローバル拠点

東京（本社）、大阪、福岡、札幌、ベルリン（ドイツ）、バンクーバー（カナダ）、バンガロール（インド）、ソウル（韓国）、クアラルンプール（マレーシア／2026年1月〜）

---

## Sources

- [クラスメソッド 会社情報](https://classmethod.jp/company/)
- [ニュース・プレスリリース](https://classmethod.jp/news/)
- [Anthropicリセラー契約プレスリリース](https://prtimes.jp/main/html/rd/p/000000441.000014901.html)
- [キャリア採用サイト](https://careers.classmethod.jp/)
- [数字でわかるクラスメソッド](https://careers.classmethod.jp/feature/number/)
- [Classmethod English Overview](https://classmethod.jp/english/company-overview/)
- [AWS GenAIIC参画ニュース](https://classmethod.jp/english/news/251114-aws-genaiic/)
- [NIKKEI COMPASS](https://www.nikkei.com/compass/company/wU1tFWw1jHpYU7A5YHQ8Lq)

Company research that would have involved navigating between corporate sites and news sites can be completed in a matter of minutes. Information sources are also listed with links. Even when there is information mentioned with "Where was this information taken from?", you can quickly check the sources.
I didn't specifically instruct it, but it's good that it picked up "News from the last 90 days." Also, it seems to have looked at external job posting sites as well. Amazing.

If you just want to "get a quick overview," this Skill is quite sufficient. I use it to "see the big picture first, and then dig deeper into any areas of interest."

If you need a more detailed report, you might use other deep research services like Gemini's DeepResearch, or customize the Skill according to your needs.

2. Call Prep

When you say "prepare for a meeting with X company," it generates the following meeting preparation materials:

• Account overview and background
• Information about attendees and their interests
• Expected agenda
• Suggested discovery questions
• Proposed meeting approach

Let's try it out. From the Cowork "New Task" screen, if you just enter /call-prep to start a session, you'll be asked questions like this. This time, let's try "enter company name".

It asks various questions. Let's choose "Discovery".

It still asks more questions. It's very thorough. When asked for a company name and participant name, I responded with "Classmethod Inc. CEO Satoshi Yokota".

It confirms "what phase of the sales meeting it is," "who you're meeting with," and "what you want to achieve" before proceeding with the work. This is quite helpful.

Here's what was created:

Call Prep: クラスメソッド株式会社
**ミーティング:** ディスカバリー（初回商談） **参加者:** 横田 聡（代表取締役社長） **あなたのゴール:** 課題・ニーズの把握

---

## アカウントスナップショット

|項目|内容|
|---|---|
|**会社名**|クラスメソッド株式会社|
|**設立**|2004年7月7日|
|**代表**|横田 聡|
|**業種**|クラウドインテグレーション・技術コンサルティング|
|**従業員数**|単体520名 / グループ820名（2025年7月時点）|
|**売上高**|約950億円（2025年6月期）|
|**資本金**|1億円（100%自己資本）|
|**本社**|東京都千代田区|
|**ドメイン**|classmethod.jp|
|**ステータス**|新規プロスペクト|

---

## 会社概要

クラスメソッドは日本最大級のクラウドインテグレーターで、AWS、データ分析、生成AI、モバイル開発を中心とした技術支援を事業会社向けに提供しています。「すべての人々の創造活動に貢献し続ける」を企業理念に掲げ、累計5,000社超・35,000以上のAWSアカウントを支援してきた実績があります。

主要サービスは「クラスメソッドメンバーズ」（AWS総合支援サービス、24時間365日体制）で、ストック型ビジネスモデルが売上の大部分を占めます。また、技術ブログ「DevelopersIO」（50,000記事超）による情報発信で技術コミュニティでの高い認知度を誇ります。

### グローバル展開

- ドイツ・ベルリン（2016年〜）
- カナダ
- インド
- 韓国
- **マレーシア・クアラルンプール（2026年1月 新設）**

---

## 横田 聡 社長について

### プロフィール

- **役職:** 代表取締役社長（創業者）
- **年齢:** 40代後半（2004年創業時26歳）
- **経歴:** 家電量販店店員 → ITベンチャー → 技術研修講師（月200万円の売上） → 2004年にクラスメソッドを300万円の自己資本で創業
- **特徴:** 技術者出身の経営者。VCからの出資を一切受けず、「身の丈経営」を信条とする

### 経営スタイル

- **100%自己資本経営** — 外部からの資金調達なし
- **ストック型ビジネス重視** — 大型調達や大量雇用をしない堅実な成長
- **技術コミュニティ重視** — DevelopersIOブログを経営の柱に据える
- **創業メンバーが15年以上在籍** — 「友人3人を誘って4人でスタート、今も全員在籍」

### トーキングポイント

- 「身の丈経営で売上950億円まで成長」という経営哲学への敬意
- DevelopersIOの技術コミュニティへの貢献について
- 2004年の創業から20年超、100%自己資本を貫く姿勢

---

## 最新ニュース（2025〜2026年）

### 2026年の注目トピック

|日付|ニュース|商談への示唆|
|---|---|---|
|**2026年3月**|**Anthropic社とリセラー契約を締結**（Amazon Bedrock経由の再販も可能に）|生成AI領域への本格参入。Anthropic/Claudeの活用ニーズが高い可能性|
|**2026年3月**|dbt Labs公式トレーニングパートナー認定取得（日本初）|データ分析基盤の強化に注力中|
|**2026年1月**|マレーシア・クアラルンプールにオフィス開設|グローバル展開を加速中|
|**2026年1月**|「グロースパック for LINE」機能拡充|自社サービスも積極的に展開|

### 2025年の主な実績

|実績|詳細|
|---|---|
|**AWS Partner Award**|「Consulting Partner of the Year – Japan」受賞（2025年5月）|
|**AWS Generative AI Innovation Center**|日本初のPartner Innovation Alliance参加企業に選出|
|**AI駆動開発コンソーシアム**|共同設立（取締役 大橋力丈氏が発起人）|
|**Snowflake**|「Rising Star Partner of the Year」受賞|
|**三菱UFJ銀行**|「DX支援スキーム」に参画、中堅・中小企業のDX推進を支援|

---

## 推奨アジェンダ

### 1. オープニング（5分）

- 横田社長の経歴と「身の丈経営」への敬意を示す
- Anthropic社とのリセラー契約締結など、最近の動きに触れる
- ミーティングの目的と時間配分を確認

### 2. 現状の理解（15分）

- クラスメソッドとして今、最も注力している事業領域は？
- 生成AI関連の取り組み（Anthropicリセラー契約後の展開）
- グローバル展開の方向性と課題

### 3. 課題・ニーズのヒアリング（15分）

- 現在感じている経営上の課題や、成長のボトルネック
- 技術的なチャレンジや人材面での課題
- 「こういうものがあれば」という理想像

### 4. ネクストステップ（5分）

- 次回のアクションを明確にする
- 社内の他のステークホルダーへの展開可能性を確認

---

## ディスカバリー質問

相手の状況を深く理解するための質問リスト：

### 事業全体

1. 「売上950億円規模に成長されましたが、次の成長フェーズとしてどのような領域に注力されていますか？」
2. 「AWSに加えて、Anthropicとのリセラー契約やdbt Labs認定など、パートナーシップを拡大されていますが、この戦略の背景にある考えは？」

### 課題・ペイン

3. 「グループ820名規模になられて、組織としてのチャレンジはどのようなものがありますか？」
4. 「グローバル6拠点に拡大されていますが、海外展開で特に感じている課題は？」

### 意思決定プロセス

5. 「新しいサービスやツールの導入を検討される際、どのようなプロセスで進められますか？」
6. 「技術選定において、横田社長が特に重視されるポイントは？」

### 成功の定義

7. 「今後1〜2年で『これを実現できたら大きい』と考えていることは何ですか？」

---

## 想定される反論・懸念

|懸念|対応策|
|---|---|
|「自社で技術力があるので外部は不要」|クラスメソッドの技術力を尊重した上で、補完的な価値（専門性の深さ・スピード・リソース）を提示|
|「身の丈経営なのでコストに慎重」|ROIを明確にし、ストック型ビジネスとの相性を強調。段階的な導入を提案|
|「既存パートナーとの関係がある」|競合ではなく補完関係としてのポジショニングを明確に|
|「今は忙しい・タイミングではない」|Anthropic契約やグローバル展開など、今だからこそのタイミングを示す|

---

## ミーティング後のアクション

- 商談メモを記録（`/call-summary` を実行）
- フォローアップメールのドラフト作成
- CRMにコンタクト・商談情報を更新
- 社内関係者への共有サマリーを作成

Similar to Account Research introduced earlier, but this output is specifically focused on "meeting preparation." Rather than just company information, it summarizes information from the perspective of "how to proceed with this meeting."
This time I created it based on meeting with Classmethod's CEO Yokota. For those planning to meet with our CEO Yokota, please feel free to use this as a reference.

In this example, I didn't provide any information about "what kind of products we handle and what we want to propose." Therefore, the output is somewhat generic and thin. However, if you properly input "what products your company has and what goals you aim for in this meeting," the quality of the output should improve.

I haven't used this function much yet, but while writing this blog, I started thinking "Maybe this is better than Account Research?" I appreciate how it researches not just basic customer information but also recent news based on "what to talk about in the actual meeting." At the current level of usage, I think it's useful at least for creating ice-breaking topics.

I plan to try various approaches with more detailed input information to find more effective ways to use it.

3. Daily Briefing

When you ask "Tell me today's schedule," it looks at connected services (email, calendar, CRM, etc.) and generates a briefing that organizes your meetings for the day, priority tasks, pipeline movements, and more.

In my case (with Gmail, Google Calendar, and HubSpot connectors enabled), it summarized information on the following topics:

• Today's top priorities
• Today's numbers (number of deals expected to close this month, number of meetings today, number of incomplete tasks)
• Today's meetings (what meetings are scheduled at what time, who are the participants, brief summary of the content. Google Calendar information)
• Pipeline focus deals (list of high-importance deals scheduled to close at the end of this month)
• Email check status (whether there are emails requiring replies)
• Things to do today

However, I don't struggle much with checking emails or calendars, so I don't use this feature often.

Since I tend to handle many deals, I find the HubSpot pipeline management (content such as "Here are the deals scheduled to close in March") useful for getting an overview.

4. Draft Outreach - Automatically Generate Personalized Emails

When you say "Write an email to X," it first researches the person via web search and then generates a personalized email draft.

It writes text that doesn't feel like a template, tailored to the recipient's situation. For example, mentioning a new service recently released by the recipient's company while suggesting connections with your own solution.

However, I don't struggle much with composing email content, so I don't use this feature often.

This would be effective for salespeople who conduct numerous new business development activities and outbound calls.

5. Competitive Intelligence

When you enter your company name and product, it automatically generates a competitive comparison matrix in HTML format.

The output includes:

• Feature comparison matrix
• Differentiation points
• Recent releases and trends of competitors
• Sales talk track (how to respond to specific questions)
• Strategies for handling tricky questions

Since other companies' names would appear explicitly, I cannot share a sample in this blog, but when you enter "Classmethod Inc.," it instantly creates a decent-looking HTML comparison table.

(This is the only part I can show. In the actual output, there are buttons to select other companies to the right of "Classmethod." In the image above, I've blacked these out. I hope you can see that it creates a decent-looking HTML at a single stroke.)

It lists about 5 competitors and provides "patterns to win against A company," "patterns to win against B company" for each. It also provides "how to talk when a competitor's name comes up," "landmines (questions that expose competitors' weaknesses)," and "anticipated objections and how to handle them."

Here too, if you use it as is, the output will be based on web searches, so it tends to be somewhat general (i.e., somewhat thin) content.

This time I created it based on Classmethod itself, but it might also be interesting to use it to research what players are competing with a customer's company and what strengths each company has.

If you want to know competitive information in addition to Account-research and Call-prep introduced above, this function could be useful.

6. Create an Asset - Instantly Create Draft Proposal Materials

It generates sales assets such as landing pages, one-pagers, proposal decks, and workflow demos for customers. When you communicate the customer's challenges and targets, it creates customized materials accordingly.

It quickly creates a landing page like this.

Like the competitive battle card mentioned earlier, it creates something with a decent appearance at a single stroke, but naturally, by default it doesn't apply your company's logo or design regulations, so it's probably not at a level that can be published externally as is.

Also, this Skill alone can only output in HTML. While for sales materials you might want PowerPoint slides, to generate PowerPoint, you need to add a separate Skill to handle pptx files. This is also officially distributed by Anthropic, so it's easy to install. (Since the pptx skill is not included in the sales plugin, I won't introduce it in detail in this article.)

I think it can be used as an initial draft for creating materials or for internal discussion purposes.

7. /call-summary (Create Minutes, Summary, and Follow-up Email)

Activated with the /call-summary command, when you paste meeting notes or text, it automatically generates:

Personally, I think this is a function that could be quite useful.

• Structured minutes (who said what)
• Extraction of action items (with assignees and deadlines)
• Follow-up email draft
• Internal summary

In addition to detailed minutes, it lists out "priority themes," "new proposal opportunities," and "action items." The minutes seem to be readable and comprehensive. Furthermore, it also creates a draft follow-up email. It's good that it organizes next actions without omissions, allowing you to move quickly to the next action.

For input information, handwritten scribbled notes or transcribed data from Gemini are both fine.
(Separately, if you incorporate voice recognition models like Whisper, you can also create minutes from recorded audio data. When I tried it, it took quite a long time...
For handling audio data, the following article is detailed:
https://dev.classmethod.jp/articles/claude-cowork-whisper-summary/

There are many AI-powered minute-taking tools available today, but I found it convenient to be able to do this quickly on Claude without any customization.

If you integrate with Gmail or CRM, it seems you can also send emails or register activities and tasks in CRM directly from the Claude desktop app.
I haven't used this yet, but if you want further automation, please feel free to try it. (※Follow your company's policies and check with each system administrator before proceeding!)

8. /pipeline-review - Check Pipeline Health

Activated with /pipeline-review, when you provide pipeline data (via CSV upload or CRM integration), it analyzes:
(※Using CRM integration requires connection via MCP, etc.)

• Pipeline health score
• Deal prioritization
• Risk flags (stalled deals, overdue close dates, etc.)
• Weekly action plan

At Classmethod, we use HubSpot for deal management, so it reviewed based on HubSpot "deals" information.

What I found particularly interesting is that it not only does simple aggregation but also scores the entire pipeline out of 100 points. I felt my back straighten when it pointed out issues like "There's a problem with the basic data quality. Here are how many deals where the amount or close date hasn't been entered." Sales people, let's properly enter deal information, shall we?

It also presents high-priority deals & immediate action plans.

While this is a very useful feature, effective data analysis is impossible unless the underlying deal information is correctly entered. Let's start by registering correct data. (I say this with self-reflection)

9. /forecast - Automatically Generate Sales Forecasts

Activated with /forecast, when you provide pipeline data and quota (target), it generates:

• Weighted forecast (based on probability)
• Best/standard/worst case scenarios
• Commit vs. upside breakdown
• Gap analysis (deviation from target)

Like the pipeline-review mentioned earlier, I think this feature demonstrates its true value when integrated with CRM.
(Again, good reports cannot be generated unless the underlying deal information is correctly entered...)

Whether you can make good use of this feature largely depends on how you manage your pipeline data in the first place. Rather than just how to use the tool itself, the design and proper operation of the entire business flow is important. (I say this with self-reflection)

Actual Usage in Sales Activities

So far, I've introduced the individual functions available in the sales plugin.
In terms of use cases within typical sales activities, it might look something like this:

Before a meeting → Research the company with Account Research → For important meetings, also create preparation materials with Call Prep. If you want to know about competitor information or the customer market, research with Competitive Intelligence.

After a meeting → Organize notes & create follow-up emails with /call-summary

During a competition → Create battle cards with Competitive Intelligence

When developing new business → Create personalized emails with Draft Outreach

Deal management & internal reporting → Manage pipeline with /pipeline-review and /forecast

My Impressions After Using It

I get the impression that what Claude can do has expanded even further.
(Although I didn't introduce it in this article), by adding various Skills, you can now work with Excel and PowerPoint in Claude, and recently I've been spending more time working in the Claude desktop app.
Within that, I found it very convenient to be able to prepare for meetings and organize next actions after meetings without going back and forth between other apps and browsers. It feels like we're approaching a world where most tasks can be completed within Claude. It's also good that these are plugins provided officially by Anthropic, so they can be used with confidence and introduced quickly.

Among the various functions, I think Account Research, call-prep, and call-summary are immediately practical.
For research functions, even without specific instructions, they research not only corporate site information and IR materials, but also news articles and job postings. The impression is that they collect information much faster and more comprehensively than searching the web yourself. They also clearly indicate the information sources, making fact-checking easy.
For call-summary which compiles minutes, my first impression was that the resulting minutes are easy to read. I appreciated that it not only lists conversation content but also summarizes topics with different levels of importance in the form of "emphasized points," allowing for a smooth transition to next actions.

In this article, I mainly introduced what can be done with the default state. The sales plugin is a collection of functions that apply to many types of sales activities, a kind of greatest common denominator.
Therefore, you might feel "this doesn't quite fit my work?" In such cases, it would be good to adjust Skills to your liking or add integrations with external services to customize it.

Points to Be Careful About

While convenient, there are certainly aspects we should be careful about. Here are a few things I try to keep in mind:

• Always fact-check the output

Fact-checking the output is essential. Since it's AI output, it may contain incorrect information. When using AI output information in materials, I always make sure to verify the accuracy of the information. For information based on web searches, if you say "show me the information sources," it will generally properly report the sources, so if you have any doubts, I always check the primary information with my own eyes.

• Occasionally check if Claude is behaving strangely

Claude Cowork creates a work plan and autonomously completes tasks for you. Depending on the content, it can work silently for over 10 minutes. Usually, things progress without issues, but rarely, work may not proceed as expected and it keeps retrying.

From my own experience, when I enabled "Claude in Chrome" which allows Claude to use a web browser for operations, there was a time when it said "I'll directly operate the browser since access to the connected service isn't working well" and launched a browser, working in an RPA-like manner. Looking at the browser operations, it seemed to be repeating unproductive trial and error like toggling column display/hide in spreadsheets, so I stopped it. When this happens, it's wasteful to consume tokens without making progress, so be careful.

Also, if you suddenly hand over Excel files with large amounts of data, it can waste time and tokens processing it,
so I try to avoid giving unnecessary information and provide appropriate input information tailored to the purpose.

While it's good to introduce many Skills and connector integrations, it's also important to check if they're behaving as expected, and if not, to delete them to reduce unnecessary elements.

• If you don't want your input data to be used for learning, opt out from the settings screen

This isn't limited to the sales plugin. By default, Claude has the setting "Allow Anthropic to use your chats and coding sessions to train and improve Anthropic AI models" enabled. If you cannot accept this, make sure to turn off this setting in the settings screen before using it.

Finally

Claude's Sales plugin has a total of 9 functions, but I don't think you need to master all of them.

For now, I think it's best to try the ones that seem easy to use or suitable for your work, and then customize Skills or add other Skills as needed.

"Customizing Skills" might sound difficult, but it's not at all. You don't need to write complicated code; in the Cowork chat screen, you can simply say "please modify this Skill in this way," and Claude will run "a Skill that creates Skills" and make nice modifications for you without any problems.
After modification, you can try it again, and if there's something you don't like, you can modify it again. This cycle of gradual improvement becomes increasingly enjoyable.

If you're curious about "what it's like," I recommend trying Account Research, Call-Prep, and /call-summary first. You'll get decent results even without other Skills or external connector integrations.

There are many plugins beyond sales. I think it's fun to find ones that fit your own work.

Although I'm just a salesperson speaking presumptively, personally, I believe generative AI doesn't replace salespeople but serves as a good assistant to improve sales quality. I want to continue exploring various ways to use it, primarily focusing on how to enhance the quality of customer meetings and communications.

If you think "Claude isn't relevant to me because I'm not an engineer," especially if you're in sales, please try Claude!

That's all.