# AI use cases for Knowledge Work Plugins (anthropics/knowledge-work-plugins)

Repo: [anthropics/knowledge-work-plugins](https://github.com/anthropics/knowledge-work-plugins) | Use cases: 5 | Page: https://dedupedai.com/use-cases/anthropics-knowledge-work-plugins/

A collection of open source Claude plugins, each bundling skills, connectors, slash commands, and sub-agents for a knowledge worker role such as sales, legal, finance, or support.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Prep for sales calls with prospect research: https://dedupedai.com/use-cases/anthropics-knowledge-work-plugins/prep-sales-calls-with-plugin/
- Write SQL queries for warehouse data: https://dedupedai.com/use-cases/anthropics-knowledge-work-plugins/write-data-queries-with-plugin/
- Triage support tickets and draft replies: https://dedupedai.com/use-cases/anthropics-knowledge-work-plugins/triage-support-tickets-with-plugin/
- Search email, chat, docs, and wikis at once: https://dedupedai.com/use-cases/anthropics-knowledge-work-plugins/search-company-tools-in-one-query/
- Customize a plugin for your company's tools: https://dedupedai.com/use-cases/anthropics-knowledge-work-plugins/tailor-plugin-to-company-stack/

## How to prep for sales calls with prospect research with Knowledge Work Plugins

Repo: [anthropics/knowledge-work-plugins](https://github.com/anthropics/knowledge-work-plugins) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Install the sales plugin and run a call-prep command to research a prospect before a meeting.

**Who it is for:** A sales rep with a discovery call tomorrow who wants account context pulled from connected CRM and notes tools without manual searching.

**The problem:** Preparing for a call means searching CRM records, past notes, and company information across several tools.

**The outcome:** A call prep brief for the prospect, generated by Claude using the sales plugin's skills and connectors.

### Steps

1. Run `claude plugin marketplace add anthropics/knowledge-work-plugins`
2. Run `claude plugin install sales@knowledge-work-plugins`
3. Connect the sales connectors you use, such as HubSpot or Slack, by editing `.mcp.json` or through Cowork
4. Start a session and run `/sales:call-prep` with the prospect name

### Prompt to paste into your agent

```text
Using the anthropics/knowledge-work-plugins repo, install the sales plugin and run /sales:call-prep for <prospect name>. Expected output: a prep brief covering the account and recent activity. Verify that each claim in the brief traces to a connected tool or the user's notes.
```

### Caveat

The README lists HubSpot and other CRM connectors for the sales plugin but does not document their setup, so connector authentication steps must come from each vendor's own docs.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/anthropics-knowledge-work-plugins/prep-sales-calls-with-plugin/

## How to write SQL queries for warehouse data with Knowledge Work Plugins

Repo: [anthropics/knowledge-work-plugins](https://github.com/anthropics/knowledge-work-plugins) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Use the data plugin to draft and refine queries against a connected warehouse.

**Who it is for:** A data analyst or product manager who needs a query against Snowflake, Databricks, or BigQuery but does not want to write the SQL from scratch.

**The problem:** Writing a correct query against an unfamiliar warehouse schema takes time and back-and-forth.

**The outcome:** A SQL query drafted by Claude through the data plugin's write-query command, ready for review before running.

### Steps

1. Run `claude plugin marketplace add anthropics/knowledge-work-plugins`
2. Run `claude plugin install data@knowledge-work-plugins` (inferred, check the README)
3. Connect your warehouse, such as Snowflake, Databricks, or BigQuery, through its connector
4. Run `/data:write-query` and describe the question in plain language

### Prompt to paste into your agent

```text
Using the anthropics/knowledge-work-plugins repo, install the data plugin and run /data:write-query for <question about the dataset>. Expected output: a SQL query that answers the question. Verify the query against the table and column names in the connected warehouse before running it.
```

### Caveat

The README names the write-query command but does not say which SQL dialects or warehouses are tested, so check the generated query against your warehouse before running it.

Risk, credentials: The warehouse connector needs database credentials, so store them in your secret manager and do not commit them to the .mcp.json file.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/anthropics-knowledge-work-plugins/write-data-queries-with-plugin/

## How to triage support tickets and draft replies with Knowledge Work Plugins

Repo: [anthropics/knowledge-work-plugins](https://github.com/anthropics/knowledge-work-plugins) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Use the customer-support plugin to sort tickets, draft responses, and package escalations.

**Who it is for:** A support lead or agent with a queue of open tickets who needs faster first responses and clean escalations to engineering.

**The problem:** Tickets arrive in mixed quality, and drafting consistent replies and escalation notes takes time away from resolving issues.

**The outcome:** Triaged tickets, draft responses, and escalation packages prepared by Claude using the customer-support plugin.

### Steps

1. Run `claude plugin marketplace add anthropics/knowledge-work-plugins`
2. Run `claude plugin install customer-support@knowledge-work-plugins` (inferred, check the README)
3. Connect Intercom or HubSpot and Jira through their connectors
4. Ask Claude to triage the ticket and draft a reply, and to package an escalation if needed

### Prompt to paste into your agent

```text
Using the anthropics/knowledge-work-plugins repo, install the customer-support plugin and triage <ticket ID or pasted ticket text>. Expected output: a priority, a draft reply, and an escalation summary if the issue needs engineering. Verify that the draft does not promise anything the support policy does not allow.
```

### Caveat

The README lists the customer-support connectors but does not describe the commands for this plugin, so the triage workflow relies on natural language requests rather than a documented slash command.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/anthropics-knowledge-work-plugins/triage-support-tickets-with-plugin/

## How to search email, chat, docs, and wikis at once with Knowledge Work Plugins

Repo: [anthropics/knowledge-work-plugins](https://github.com/anthropics/knowledge-work-plugins) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Install the enterprise-search plugin to run one query across the company's connected tools.

**Who it is for:** Any employee who knows an answer exists somewhere in the company but cannot tell which tool holds it.

**The problem:** Information is scattered across email, chat, docs, and wikis, and checking each one by hand is slow.

**The outcome:** One search across connected tools that returns results from all of them in a single answer.

### Steps

1. Run `claude plugin marketplace add anthropics/knowledge-work-plugins`
2. Run `claude plugin install enterprise-search@knowledge-work-plugins` (inferred, check the README)
3. Connect the tools you use, such as Slack, Notion, Guru, or Microsoft 365
4. Ask Claude a question in plain language that spans those tools

### Prompt to paste into your agent

```text
Using the anthropics/knowledge-work-plugins repo, install the enterprise-search plugin and search for <topic> across connected tools. Expected output: an answer that cites which tool each piece came from. Verify that at least one cited source opens and matches the answer.
```

### Caveat

Search results are only as complete as the connectors you enable, so content in tools you have not connected will not appear.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/anthropics-knowledge-work-plugins/search-company-tools-in-one-query/

## How to customize a plugin for your company's tools with Knowledge Work Plugins

Repo: [anthropics/knowledge-work-plugins](https://github.com/anthropics/knowledge-work-plugins) | Difficulty: Advanced | Time: 1 hour | Basis: From the README

Point a plugin's connectors and skill files at your own tool stack and terminology.

**Who it is for:** A team admin rolling out Claude to a function whose tools and terms differ from the generic plugin defaults.

**The problem:** The out-of-the-box plugins use generic tools and workflows, so answers do not match how the team actually works.

**The outcome:** A forked plugin that uses the company's connectors, terminology, and processes, ready to share with the team.

### Steps

1. Fork the repo on GitHub and clone your fork
2. Edit `.mcp.json` in the plugin folder to point at your tool stack
3. Add your company terms, org structure, and processes to the skill files
4. Run `claude plugin marketplace add anthropics/knowledge-work-plugins` to test the published version, or install your fork's marketplace in the same way
5. Open a pull request or share the plugin folder with your team

### Prompt to paste into your agent

```text
Using the anthropics/knowledge-work-plugins repo, fork the <plugin name> plugin and update its .mcp.json and skill files for <company tool stack and terms>. Expected output: a modified plugin folder with valid JSON and markdown. Verify that the .mcp.json file parses as valid JSON and that no secrets are written into it.
```

### Caveat

The README says plugins are markdown and JSON with no build steps, but it does not document how to install a forked marketplace, so confirm that step in the Claude Code docs before rolling it out.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/anthropics-knowledge-work-plugins/tailor-plugin-to-company-stack/
