Skip to main content

Packaging skills in a plugin, this time for GitHub Copilot CLI

Note: this post is part of a series. Part one covered packaging a skill in a plugin for Claude Code. Same idea, different tool, this time focussing on GitHub Copilot.

After writing that first post I got the obvious follow-up question: does this also work for GitHub Copilot?

Short version: yes, SKILL.md itself is portable, but the plugin wrapper isn't. Copilot CLI has its own plugin format, laid out slightly differently from Claude Code's.

What's the same?

A skill is still just a folder with a SKILL.md inside: YAML frontmatter (name, description, optionally license), then a Markdown body with instructions. Copy that file as-is between tools — nothing about the skill content needs to change.

What's different?

Where Claude Code wants the manifest tucked inside .claude-plugin/plugin.json, Copilot CLI puts plugin.json straight at the plugin root:

api-testing-plugin/
├── plugin.json           # Required manifest, at the root
├── agents/                # optional
│   └── helper.agent.md
├── skills/                # optional
│   └── api-testing/
│       └── SKILL.md
├── hooks.json             # optional
└── .mcp.json              # optional

Remark: f you’re porting a Claude Code plugin folder over, notice that you have to move the plugin.json up one level, out of .claude-plugin/.

Step 1: write the manifest

{
  "name": "api-testing-plugin",
  "description": "Skills for API testing and contract validation",
  "version": "1.0.0",
  "author": {
    "name": "Bart Wullems"
  },
  "license": "MIT",
 "skills": ["skills/"]
}

The skills field is an array, so you can point at more than one directory if your skills live in different places — ["skills/", "extra-skills/"], for example.

Step 2: drop the skill in

api-testing-plugin/
└── skills/
    └── api-testing/
        └── SKILL.md

Same shape as a standalone Copilot skill. The only difference is it now ships inside a plugin instead of sitting loose in .github/skills/.

Step 3: install and verify locally

copilot plugin install ./api-testing-plugin


copilot plugin list

Or from inside an interactive session:

/plugin list
/skills list

Tip: plugin components get cached on install. If you edit the skill and don't see the change, that's why — run copilot plugin install ./my-plugin again to pick it up.

Publishing to a marketplace

Same story as the Claude Code post: a bare SKILL.md or a locally installed plugin covers you and your immediate team but as you've maybe seen in the screenshot above, the local install option is deprecated. 

To make it something anyone can grab with one command, you need a marketplace.

A Copilot CLI marketplace is a repository with one required file: marketplace.json

Step 1: create the marketplace file

my-marketplace/
├── .github/
│   └── plugin/
│       └── marketplace.json
└── plugins/
    └── api-testing-plugin/
        ├── plugin.json
        └── skills/
            └── api-testing/
                └── SKILL.md
{
  "name": "my-plugins",
  "owner": {
    "name": "Bart Wullems"
  },
  "metadata": {
    "description": "Curated plugins for API and dev tooling",
    "version": "1.0.0"
  },
  "plugins": [
    {
      "name": "api-testing-plugin",
      "description": "Skills for API testing and contract validation",
      "version": "1.0.0",
      "source": "./plugins/api-testing-plugin"
    }
  ]
}

Remark: source is relative to the repository root, and the leading ./ is optional — "plugins/api-testing-plugin" resolves the same as "./plugins/api-testing-plugin". Copilot CLI also accepts marketplace.json under .claude-plugin/, so a repo doing double duty as both a Claude Code and Copilot marketplace can often share one file.

Step 2: put the plugin where it points

The source path has to actually resolve. Add the full plugin directory (manifest, skills, everything from the previous post) at plugins/api-testing-plugin/ in the same repo.

Step 3: push and share

copilot plugin marketplace add wullemsb/my-plugins

That's the whole install instruction you hand to anyone who wants your plugins. From there, installing one specific plugin uses the same form as before:

copilot plugin install api-testing-plugin@my-plugins

Tip: a marketplace repo doesn't have to live on GitHub. Any other git URL works too.

That's it! Same SKILL.md, two different containers depending on which agent picks it up.

More information

Popular posts from this blog

Podman– Command execution failed with exit code 125

After updating WSL on one of the developer machines, Podman failed to work. When we took a look through Podman Desktop, we noticed that Podman had stopped running and returned the following error message: Error: Command execution failed with exit code 125 Here are the steps we tried to fix the issue: We started by running podman info to get some extra details on what could be wrong: >podman info OS: windows/amd64 provider: wsl version: 5.3.1 Cannot connect to Podman. Please verify your connection to the Linux system using `podman system connection list`, or try `podman machine init` and `podman machine start` to manage a new Linux VM Error: unable to connect to Podman socket: failed to connect: dial tcp 127.0.0.1:2655: connectex: No connection could be made because the target machine actively refused it. That makes sense as the podman VM was not running. Let’s check the VM: >podman machine list NAME         ...

Cache stampede: when our cache turned against us

While investigating some performance issues, we ran into an ASP.NET Core API that cached a fairly expensive aggregation query for 60 seconds. Under normal load, that was fine: one request rebuilds the cache, everyone else reads from it. Under peak load, dozens of requests would arrive in that same expiry window, all see a cache miss, and all fire the same expensive query in parallel. The database didn't like that. That was the moment when our caching layer stopped helping and started hurting. A burst of requests comes in at the same time, all miss the cache, and all go hammer the database or the downstream API at once. That's a cache stampede . The cache was supposed to protect our backend, and for a few hundred milliseconds it did the opposite. Why this happens IMemoryCache.GetOrCreate (and its async sibling) looks like it protects you, but it doesn't add any locking on its own. Look at the naive version: public async Task<Report> GetReportAsync(string key) ...

A complex system designed from scratch never works

A few years ago, I worked as an architect on a big mainframe rewrite. I still count it as one of my failures. Not because the technology was wrong, but because I couldn't convince the management team to simplify the approach. Years later, the organization is still struggling to get the new system up and running. I left the project at the time, because I couldn't put my name behind an approach that would take very long and cost a lot of money without a working system to show for it along the way. Gall’s Law That memory keeps coming back to me, because it's a textbook case of Gall's Law playing out in real life. Gall's Law , from John Gall's Systemantics , states it plainly: A complex system that works is invariably found to have evolved from a simple system that worked. A complex system designed from scratch never works, and it cannot be patched to make it work. You have to start over with a simple system that works. What does that mean in practice,...