Images, Models, and Skills
Add reference images and choose the Runner capabilities that fit a request.
What this covers: You will give Runner the right context and working tools before sending a request.
Images show Runner what you mean. Models and skills change the capabilities available for the next request. Use them deliberately; a clear request is still the most important input.
Entry path: Open a store project → conversation composer.
Before you start
- Use only images you are allowed to share with the current workspace.
- Remove secrets, payment data, and unnecessary customer information.
- Check plan and browser access when a model, Skill, or screen-capture action is missing.
Composer controls
| Control | What happens when you select it |
|---|---|
| Add | On desktop, opens Upload image and, when supported, Take screenshot. |
| Upload image | Opens the image picker for JPG/JPEG, PNG, GIF, WebP, BMP, or TIFF files. |
| Take screenshot | Starts screen capture when the browser and account support it. The browser may ask for permission. |
| Picture on mobile | Opens the mobile image picker. It is the only upload choice in the mobile sheet. |
| Model selector | Lists the Runner models available to the account. A locked model opens the relevant Plan & Billing path instead of selecting it. |
| Quick commands or Skills | Opens available shortcuts that can be added to the request. |
| More actions | Reveals composer tools that do not fit in the current layout. |
Runner ignores an image with the same name and size as one already in the draft and shows Duplicate image ignored. Unsupported files are ignored with Use a JPG, PNG, GIF, WebP, BMP, or TIFF image. In a mixed selection, supported images remain available. Runner currently accepts up to 10 images per message, up to 32 MB each.
Add an image
- Draft enough of the request to explain why the file matters.
- Select Add on desktop, or the upload button on mobile.
- Choose Upload image, Picture, or Take screenshot, depending on what is shown.
- Pick or capture the relevant image.
- Confirm that it appears with the draft.
- Remove it before sending if it is the wrong reference.
- Select Send.
If screen capture is unavailable or permission is denied, take a screenshot with your device and upload the saved image instead.
Choose a model
- Select the current model in the composer.
- Review the models Runner makes available.
- Choose the model that matches the task.
- Confirm the selected model is shown before you send.
If a model is locked, keep the current model or follow the plan information Runner opens. A locked choice is not applied to the draft.
Add a skill
- Open Quick commands, Skills, or the command palette.
- Search or browse for the capability you need.
- Select an already available skill to add or remove it from the request.
- Select a discoverable skill to add it when your plan permits.
- Return to the composer and confirm the intended skill is present.
- Send the request.
When the current plan does not include a skill, Runner can open the Agent or upgrade path instead. Memory choices appear only when memory is enabled for the account.
Troubleshooting
| Problem | What to do |
|---|---|
| The image is not added | Use a supported image format, keep it under 32 MB, and keep the message at 10 images or fewer. |
| Duplicate image ignored | The same name-and-size image is already in the draft. Keep the existing copy or remove it before selecting the image again. |
| Unsupported-file warning | Choose a JPG/JPEG, PNG, GIF, WebP, BMP, or TIFF image. Videos, spreadsheets, and other files are not added. |
| Take screenshot is missing | Use a saved image; live capture is conditional. |
| Screen capture stops | Allow the browser permission when appropriate, or attach a normal screenshot. |
| A skill will not toggle | Finish any conflicting composer action and confirm that the plan includes the skill. |
| A locked model opens billing | Close the plan screen to keep the current model, or review access with the workspace owner. |