AWorld is an agent harness, meaning a framework that coordinates an AI agent’s tools, memory, context, and execution so expert knowledge can be turned into reusable skills and autonomous agents. It is for building domain-specific agent applications and workflows, with the catalogue entries representing skills, agents, and commands that operate within the AWorld ecosystem.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add inclusionAI/AWorld --skill ad_image_create_skillgit clone --depth 1 https://github.com/inclusionAI/AWorldWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/inclusionai/aworld/ad_image_create_skill)<a href="https://agentmods.dev/skills/inclusionai/aworld/ad_image_create_skill"><img src="https://agentmods.dev/badge/skills/inclusionai/aworld/ad_image_create_skill.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.01667 |
| Opus 5 | $0.00034 | $0.00834 |
| Sonnet 5 | $0.00013 | $0.00333 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
ad_image_create scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Image Creation
What this skill does
Generate advertising images from product assets with two output styles:
- Single hero image
- Collage image (multiple sub-images stitched into one final canvas)
Core method: decide the final target ratio first, then compute sub-image sizes, and call image_generator directly with matching size (no manual pre-crop/pre-pad on source assets).
Required workflow
- Understand final deliverable:
- Final ratio and size (for example
16:9,1920x1080) - Single image or collage layout (
2x2,1x3,1x2)
- Final ratio and size (for example
- Activate product understanding:
SKILL__active_skill(skill_name="media_comprehension")- Extract product style, tone, audience, and suitable scene category.
- Design scenes that match product positioning:
- Keep style consistent with product quality/tone.
- Avoid mismatched backgrounds (for example: minimal product + ultra-baroque palace).
- Generate each sub-image using
image_generatorwith exact request params. - Stitch sub-images (if collage), then validate final size/ratio.
- Social copy: After images are final, add one short line of ad copy per deliverable image—the same count as the exported ad files (one hero → one line; four separate exports → four lines; one stitched collage file usually → one line unless the user asked for per-panel copy). Keep each line simple, fun, and tightly tied to that image’s scene and benefit; aim for 小红书 / 抖音 scroll appeal, not generic brand platitudes.
Supporting actor references (Mode 2/3)
When the ad needs a supporting actor beyond the product—either because the user asked for one or because they supplied material—do not fetch companion assets from TikTok or similar platforms. Use what is already available:
- User supplied still image(s): Use the provided file path(s) as
reference_imagesforimage_generatorafter a quickmedia_comprehensioncheck that the image shows the intended actor/look. - User supplied video: Capture one or more frames (screenshots) from that video in the workspace, run
SKILL__active_skill(skill_name="media_comprehension")on each candidate frame, and pick a frame where the model confirms the desired supporting actor/appearance. Use that frame image asreference_images.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 168 lines · 67 tokens per session scan A 04416833c5c9
ad_image_create is a skill published in the GitHub repository inclusionAI/AWorld (1,229 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,667 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hive.image-generation
Required before calling imagegenerate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2…
scientific-slides
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and…
infographics
Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.
paper-2-web
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.
pptx-posters
Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual…
data-artist
Create beautiful data visualizations with mathematical elegance, color theory, and narrative design - the "Data is Beautiful" aesthetic.