knowledge-work-plugins  by anthropics

AI plugins for specialized knowledge work automation

Created 1 week ago

New!

1,492 stars

Top 27.4% on SourcePulse

GitHubView on GitHub
1 Expert Loves This Project
Project Summary

<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> This repository provides a collection of open-source plugins designed to transform Claude AI into a specialized assistant for knowledge workers. Targeting users of Claude Cowork and Claude Code, these plugins enhance AI capabilities by integrating role-specific skills, workflows, and external tool connectors, enabling more consistent and professional output tailored to individual or team needs.

How It Works

Plugins are structured as self-contained directories containing a manifest (plugin.json), tool connection configurations (.mcp.json), explicit slash commands (commands/), and automatic domain-specific skills (skills/). This file-based, no-code approach simplifies integration and customization. Users can tailor plugins by editing Markdown and JSON files to incorporate company-specific terminology, processes, and preferred tool stacks, allowing Claude to operate with deep contextual understanding.

Quick Start & Requirements

Install plugins directly within Claude Cowork using claude plugins add knowledge-work-plugins or specify individual plugins like claude plugins add knowledge-work-plugins/sales. The system implicitly requires access to Claude Cowork or Claude Code. No explicit code dependencies or build steps are mentioned, suggesting a straightforward setup.

Highlighted Details

  • Features 11 pre-built plugins for diverse functions: productivity, sales, customer support, product management, marketing, legal, finance, data analysis, enterprise search, bio-research, and plugin management.
  • Supports integration with a wide array of external tools via connectors, including Slack, Notion, Jira, HubSpot, Microsoft 365, Snowflake, and more.
  • Enables deep customization by allowing users to modify skills, commands, and connectors to match organizational workflows and terminology.
  • The file-based structure (Markdown/JSON) facilitates easy contribution and modification without requiring traditional software development.

Maintenance & Community

The project encourages community contributions via pull requests. Specific details regarding active maintainers, community channels (like Discord/Slack), or a public roadmap are not detailed in the provided README.

Licensing & Compatibility

The README does not specify a license type. This omission requires further investigation to determine usage restrictions, particularly for commercial applications or integration into closed-source systems.

Limitations & Caveats

The provided plugins serve as generic starting points and necessitate customization to achieve optimal performance within specific organizational contexts. The effectiveness and utility are directly tied to the quality and depth of user-defined configurations and integrations.

Health Check
Last Commit

4 days ago

Responsiveness

Inactive

Pull Requests (30d)
7
Issues (30d)
2
Star History
1,744 stars in the last 11 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), Vincent Weisser Vincent Weisser(Cofounder of Prime Intellect), and
4 more.

Biomni by snap-stanford

0.4%
3k
Biomedical AI agent for autonomous research tasks
Created 10 months ago
Updated 1 week ago
Feedback? Help us improve.