Image Posting

Documents

image-posting

Image Posting is an Agent Skill for documents published in the xuiltul/animaworks repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Skill for embedding images in chat replies: URL detection from tool results, Markdown image syntax, and assets paths. Use when: surfacing images from search or generation tools, pasting Markdown images, or showing attachments.

View on GitHub ↗

QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

Open your project in Codex.
Copy and paste the prompt below.
Review files and risks before approving any action.

Prompt to paste

Inspect the Agent Skill at https://github.com/xuiltul/animaworks/blob/HEAD/templates/en/common_skills/image-posting/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/image-posting, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

image-posting — Displaying Images in Chat Responses

Overview

There are two ways to include images in chat responses:

Auto-extraction from tool results — When tool results contain image URLs or paths, the framework auto-detects and displays them in the chat bubble
Markdown image syntax — Write ![alt](url) in response text for frontend rendering

Method 1: Auto-Display from Tool Results

When a tool (web_search, image_gen, etc.) returns results containing image information, the framework automatically displays images in the chat bubble. No special action needed.

Auto-Detection Rules

The following patterns in tool result JSON are detected as images:

Path detection: Paths starting with assets/ or attachments/ → source: generated (trusted)
URL detection: URLs starting with https:// ending in .png .jpg .jpeg .gif .webp → source: searched (proxied)
Key detection: Values under image_url, thumbnail, src, url keys with image URLs

Up to 5 images per response.

Proxy Restrictions for Searched Images

External URL images are served through a security proxy. Allowed domains:

cdn.search.brave.com
images.unsplash.com
images.pexels.com
upload.wikimedia.org

Image URLs from other domains are blocked by the proxy.

Method 2: Markdown Image Syntax

Write Markdown image syntax directly in response text to display images.

Short Paths (Recommended)

The frontend automatically prepends the API path with your Anima name. Just write the filename:

![description](attachments/filename)
![description](assets/filename)

Example:

Here's a screenshot!
![ANA Top Page](attachments/ana_top.png)

Full Paths

You can also write the full API path explicitly:

![description](/api/animas/{your_name}/assets/{filename})
![description](/api/animas/{your_name}/attachments/{filename})

Saving Screenshots

When taking screenshots with agent-browser, save directly to your own attachments directory:

agent-browser screenshot ~/.animaworks/animas/{your_name}/attachments/screenshot.png

Example (for aoi):

agent-browser screenshot ~/.animaworks/animas/aoi/attachments/page_screenshot.png

Then include in your response:

![Page screenshot](attachments/page_screenshot.png)

Files saved to ~/.animaworks/tmp/attachments/ will also work via fallback, but the temp directory does not guarantee persistence.

Notes

Cannot directly reference other Animas' asset paths (no permission)
Direct external URL linking is discouraged; only proxy-allowed domains are displayed
Image generation tool results (generate_fullbody, etc.) are auto-displayed — no Markdown syntax needed
Auto-display is capped at 5 images per response