DEDUPED Hot AI repos, turned into use cases Get the Monday 5

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

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

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

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

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

What you need first

  • Access to Claude Cowork or Claude Code
  • Accounts for the tools you want to connect, such as your CRM, warehouse, or ticketing system
  • Credentials for each connector you enable

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 for your agent

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.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page