#203203rd of 389 in Skills, plugins and prompts
knowledge-work-plugins
Role-specific plugins for Claude Cowork and Claude Code, written as markdown
- Stars
- 35.4k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Language
- Python
11,277 on 21 Apr 202635,433 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Anthropic is hiring: 677 open roles
Overview
A marketplace of 11 file-based plugins from Anthropic, each bundling skills, slash commands and MCP connectors for a job function such as sales, finance, legal, data or support. Install through Cowork or with `claude plugin marketplace add anthropics/knowledge-work-plugins`, then edit the markdown and `.mcp.json` to match your company's tools and terms.
Who it is for: Teams customizing Claude Cowork or Claude Code for roles like sales or legal
Strengths
- Plain markdown and JSON, no code, infrastructure or build step
- Each plugin ships skills, slash commands and MCP connector config for one role
- Connectors are editable in .mcp.json to match your own tool stack
- Includes a plugin-management plugin for creating or customizing plugins
Weaknesses
- Targets Claude Cowork and Claude Code only; other agents are not mentioned
- README calls them generic starting points that need company-specific tuning
- Many connectors depend on third-party SaaS accounts such as Slack or Snowflake
- No release tags published
What it needs
- no GPU
- Needs Claude Cowork or Claude Code, MCP servers for connectors (Slack, Notion, Jira, Snowflake, etc.)
- Models: Claude
Quick answers
Is knowledge-work-plugins open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in Skills, plugins and prompts
See all 389| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |