|
1 | 1 | --- |
2 | 2 | author: Harald Binkle |
3 | | -pubDatetime: 2026-01-28T10:00:00Z |
| 3 | +pubDatetime: 2026-01-28T20:00:00Z |
4 | 4 | title: GitHub Copilot Context Extensions Compared |
5 | 5 | postSlug: github-copilot-context-extensions-compared |
6 | 6 | featured: false |
7 | | -draft: true |
| 7 | +draft: false |
8 | 8 | tags: |
9 | 9 | - GitHub Copilot |
10 | 10 | - Copilot |
@@ -41,6 +41,12 @@ The last three are the focus of this comparison. |
41 | 41 |
|
42 | 42 | ## Custom Agents |
43 | 43 |
|
| 44 | +<img |
| 45 | + src="/assets/custom-agents-icon.svg" |
| 46 | + alt="Custom Agents - Multiple AI personas" |
| 47 | + style="float: right; width: 120px; margin: 0 0 1rem 1rem;" |
| 48 | +/> |
| 49 | + |
44 | 50 | > 📖 [VS Code Custom Agents Documentation](https://code.visualstudio.com/docs/copilot/customization/custom-agents) |
45 | 51 |
|
46 | 52 | Custom Agents (previously known as "custom chat modes") let you create specialized AI personas for specific development roles or tasks. They combine instructions with tool restrictions to create focused configurations that you can switch between during your work. |
@@ -98,6 +104,12 @@ Don't make code changes unless they're documentation-related (comments, JSDoc, R |
98 | 104 |
|
99 | 105 | ## Agent Skills |
100 | 106 |
|
| 107 | +<img |
| 108 | + src="/assets/agent-skills-icon.svg" |
| 109 | + alt="Agent Skills - Folders with capabilities" |
| 110 | + style="float: right; width: 120px; margin: 0 0 1rem 1rem;" |
| 111 | +/> |
| 112 | + |
101 | 113 | > 📖 [VS Code Agent Skills Documentation](https://code.visualstudio.com/docs/copilot/customization/agent-skills) | [Agent Skills Standard](https://agentskills.io/) |
102 | 114 |
|
103 | 115 | Agent Skills are the newest addition to the Copilot extension ecosystem in VS Code. They follow an open standard that works across multiple AI tools, including VS Code, GitHub Copilot CLI, and GitHub Copilot coding agent. Unlike instruction files that primarily define guidelines, skills teach Copilot specialized capabilities that can include scripts, examples, and other resources. |
@@ -152,6 +164,12 @@ When testing web applications: |
152 | 164 |
|
153 | 165 | ## MCP Tools |
154 | 166 |
|
| 167 | +<img |
| 168 | + src="/assets/mcp-tools-icon.svg" |
| 169 | + alt="MCP Tools - External service connections" |
| 170 | + style="float: right; width: 120px; margin: 0 0 1rem 1rem;" |
| 171 | +/> |
| 172 | + |
155 | 173 | > 📖 [VS Code MCP Documentation](https://code.visualstudio.com/docs/copilot/customization/mcp-servers) | [Model Context Protocol](https://modelcontextprotocol.io/) |
156 | 174 |
|
157 | 175 | Model Context Protocol (MCP) is an open standard for connecting AI models to external services and data sources. Think of it as a "USB-C port for AI applications" that provides standardized access to databases, APIs, file systems, and other external tools. |
@@ -201,6 +219,12 @@ MCP servers run either locally or remotely and expose tools, resources, and prom |
201 | 219 |
|
202 | 220 | ### MCP Apps: The Next Evolution |
203 | 221 |
|
| 222 | +<img |
| 223 | + src="/assets/mcp-apps-icon.svg" |
| 224 | + alt="MCP Apps - Interactive AI applications" |
| 225 | + style="float: right; width: 100px; margin: 0 0 1rem 1rem;" |
| 226 | +/> |
| 227 | + |
204 | 228 | > 📖 [GitHub MCP Server Registry](https://github.com/mcp) |
205 | 229 |
|
206 | 230 | Beyond traditional MCP servers, a new type is emerging: **MCP Apps**. While MCP servers expose tools and resources for AI invocation, MCP apps take this further by providing interactive experiences that combine AI capabilities with user interfaces. They present information visually, enable user interaction, and create richer workflows than pure tool invocations. |
|
0 commit comments