Add skills command for AI coding assistants

[ericcurtin]

Install Docker Model Runner skills for AI coding assistants like OpenAI Codex CLI, Claude Code, and OpenCode. The skills provide configuration files that help these assistants understand how to use Docker Model Runner effectively for local model inference. Includes comprehensive documentation in markdown format with usage examples and API details.

[gemini-code-assist]

Summary of Changes

Hello @ericcurtin, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the Docker Model Runner's utility for AI developers by introducing a dedicated skills command. This command automates the setup of configuration files, allowing popular AI coding assistants to seamlessly integrate with and utilize Docker Model Runner for local model inference. The change also provides extensive documentation to guide users through the process and maximize their productivity.

Highlights

• New skills command introduced: A new skills command has been added to the Docker CLI, designed to help AI coding assistants integrate with Docker Model Runner.
• AI Assistant Integration: The command allows installation of configuration files (skills) for specific AI coding assistants like OpenAI Codex CLI, Claude Code, and OpenCode, enabling them to understand and utilize Docker Model Runner for local model inference.
• Flexible Installation Options: Users can specify predefined installation paths for supported assistants or provide a custom destination directory. A --force flag is available to overwrite existing skill files without prompting.
• Comprehensive Documentation: Detailed markdown documentation has been added, including a SKILL.md for AI assistants on how to use Docker Model Runner, and a docker-model-guide.md providing a complete reference for Docker Model Runner's CLI, API, SDK examples, and troubleshooting.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• cmd/cli/commands/root.go
  • Integrates the new skills command into the main CLI application.
• cmd/cli/commands/skills.go
  • Implements the core logic for the skills command, handling argument parsing, target directory resolution, and file installation using Go's embed feature.
• cmd/cli/commands/skills/docker-model-runner/SKILL.md
  • Provides a high-level guide for AI assistants on how to interact with Docker Model Runner, including common workflows and API endpoints.
• cmd/cli/commands/skills/docker-model-runner/references/docker-model-guide.md
  • Offers an in-depth reference for Docker Model Runner, covering installation, CLI commands, API details, SDK examples, and troubleshooting.

Activity

• No human activity has been recorded on this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[sourcery-ai]

Hey - I've found 2 issues, and left some high level feedback:

• In runSkills, failing on the first target directory aborts installation for all subsequent targets; consider aggregating errors per-target and reporting partial success instead of returning on the first failure.
• In installSkills, encountering a pre-existing file without --force aborts the entire walk; if feasible, consider reporting/skipping the conflicting file and continuing with the rest so that one conflict doesn’t prevent all skills from being installed.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- In `runSkills`, failing on the first target directory aborts installation for all subsequent targets; consider aggregating errors per-target and reporting partial success instead of returning on the first failure.
- In `installSkills`, encountering a pre-existing file without `--force` aborts the entire walk; if feasible, consider reporting/skipping the conflicting file and continuing with the rest so that one conflict doesn’t prevent all skills from being installed.

## Individual Comments

### Comment 1
<location> `cmd/cli/commands/skills/docker-model-runner/references/docker-model-guide.md:67` </location>
<code_context>
+# Search Docker Hub
+docker model search llama
+
+# Search HuggingFace
+docker model search hf.co/bartowski
+
</code_context>

<issue_to_address>
**nitpick (typo):** Consider using the official spelling "Hugging Face" (two words).

This keeps the name consistent with the official project name and documentation.

Suggested implementation:

```
# Search Docker Hub
docker model search llama

# Search Hugging Face
docker model search hf.co/bartowski

```

Search the rest of `docker-model-guide.md` (and related docs, if applicable) for any other occurrences of "HuggingFace" and update them to "Hugging Face" to keep naming consistent throughout the documentation.
</issue_to_address>

### Comment 2
<location> `cmd/cli/commands/skills/docker-model-runner/SKILL.md:18` </location>
<code_context>
+
+2. **List available models** with `docker model list` to see what's already pulled
+
+3. **Search for models** on Docker Hub or HuggingFace:
+   - `docker model search <query>` to find models
+   - Popular models include: `ai/gemma3`, `ai/llama3.2`, `ai/smollm2`, `ai/qwen3`
</code_context>

<issue_to_address>
**nitpick (typo):** Use the official spelling "Hugging Face" instead of "HuggingFace".

Consider updating `HuggingFace` to `Hugging Face` to match the official branding.

```suggestion
3. **Search for models** on Docker Hub or Hugging Face:
```
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[gemini-code-assist]

Code Review

This pull request introduces a skills command to facilitate the installation of configuration files for various AI coding assistants, which is a great feature for improving usability with other tools. The implementation is well-structured, leveraging embed.FS to package the skill files and providing comprehensive documentation in markdown. The code is clean and the command-line interface is intuitive. I have one minor suggestion to improve code clarity in cmd/cli/commands/skills.go.

[ericcurtin]

This is loosely based on a skills adder mlx and huggingface teams did recently