How do I install the Pixeldojo skill?

Run npx skillmds@latest add dvcrn/pixeldojo in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Pixeldojo safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: CAUTION, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Pixeldojo?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Pixeldojo free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Pixeldojo?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Pixeldojo by dvcrn — Agent Skill

Name: Pixeldojo
Rating: 4.2 (5 reviews)
Author: dvcrn

Pixeldojo

Access PixelDojo's API for AI image and video generation. Use when an agent needs to create images or videos, choose a model from the live PixelDojo catalog, check async job status, or download finished assets. PixelDojo is a subscription-based creative platform that exposes multiple generation models through one API, including general image, editing-oriented image, and video workflows.

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

PixelDojo

Use PixelDojo's async API to generate and download AI images or videos.

Setup

Runtime requirements:

Environment variable: PIXELDOJO_API_KEY
Binaries: curl, jq, python3
Optional override: PIXELDOJO_API_BASE

Set the API key before running any helper:

export PIXELDOJO_API_KEY=your_api_key_here

Optional local env file:

cp ~/.openclaw/skills/pixeldojo/.env.example ~/.openclaw/skills/pixeldojo/.env

Default API base: https://pixeldojo.ai/api/v1

Workflow

Check the live model catalog first.
Pick a model that matches the requested workflow.
Submit the job with generate.sh or the Nano Banana helper.
Poll status until complete, then return the downloaded asset path.

Do not guess model IDs.

Check the live catalog

bash ~/.openclaw/skills/pixeldojo/models.sh

For a pinned snapshot of known-good model IDs and example picks, read:

references/model-catalog.md

Generate an image

bash ~/.openclaw/skills/pixeldojo/generate.sh image "editorial product photo of a silver robot" flux-2-pro --aspect-ratio 16:9

Good defaults:

Best general image quality: flux-2-max
Prompt adherence and typography: nano-banana-2
Editing-oriented image work: flux-kontext-pro

Generate a video

bash ~/.openclaw/skills/pixeldojo/generate.sh video "cinematic ocean waves at sunset" seedance-1.5 --duration 5

Use --image-url for image-to-video models:

bash ~/.openclaw/skills/pixeldojo/generate.sh video "slow camera push-in" wan-2.6-flash --image-url https://example.com/input.png --duration 5

Nano Banana helper

Use this when the user specifically wants Nano Banana 2 or strong prompt adherence:

python3 ~/.openclaw/skills/pixeldojo/scripts/generate-nano-banana.py "clean ecommerce hero shot of running shoes" --aspect-ratio 16:9 --output ~/Desktop/shoes.png

Check job status

bash ~/.openclaw/skills/pixeldojo/status.sh job_abc123

Output paths

Default download folders:

~/Pictures/AI Generated/images/
~/Pictures/AI Generated/videos/

Override with:

--output /path/to/file.png

Notes

generate.sh supports --aspect-ratio, --duration, --image-url, --output, --poll-interval, and --max-wait.
generate.sh covers the shared prompt-based API flow. If a request needs model-specific editing payloads, inspect the live catalog and API behavior before improvising.
PixelDojo markets full commercial rights for generated output, but the user is still responsible for complying with the service terms and any third-party model restrictions.

---name: pixeldojodescription: Access PixelDojo's API for AI image and video generation. Use when an agent needs to create images or videos, choose a model from the live PixelDojo catalog, check async job status, or download finished assets. PixelDojo is a subscription-based creative platform that exposes multiple generation models through one API, including general image, editing-oriented image, and video workflows.---# PixelDojoUse PixelDojo's async API to generate and download AI images or videos.## SetupRuntime requirements:- Environment variable: `PIXELDOJO_API_KEY`- Binaries: `curl`, `jq`, `python3`- Optional override: `PIXELDOJO_API_BASE`Set the API key before running any helper:```bashexport PIXELDOJO_API_KEY=your_api_key_here```Optional local env file:```bashcp ~/.openclaw/skills/pixeldojo/.env.example ~/.openclaw/skills/pixeldojo/.env```Default API base: `https://pixeldojo.ai/api/v1`## Workflow1. Check the live model catalog first.2. Pick a model that matches the requested workflow.3. Submit the job with `generate.sh` or the Nano Banana helper.4. Poll status until complete, then return the downloaded asset path.Do not guess model IDs.## Check the live catalog```bashbash ~/.openclaw/skills/pixeldojo/models.sh```For a pinned snapshot of known-good model IDs and example picks, read:- `references/model-catalog.md`## Generate an image```bashbash ~/.openclaw/skills/pixeldojo/generate.sh image "editorial product photo of a silver robot" flux-2-pro --aspect-ratio 16:9```Good defaults:- Best general image quality: `flux-2-max`- Prompt adherence and typography: `nano-banana-2`- Editing-oriented image work: `flux-kontext-pro`## Generate a video```bashbash ~/.openclaw/skills/pixeldojo/generate.sh video "cinematic ocean waves at sunset" seedance-1.5 --duration 5```Use `--image-url` for image-to-video models:```bashbash ~/.openclaw/skills/pixeldojo/generate.sh video "slow camera push-in" wan-2.6-flash --image-url https://example.com/input.png --duration 5```## Nano Banana helperUse this when the user specifically wants Nano Banana 2 or strong prompt adherence:```bashpython3 ~/.openclaw/skills/pixeldojo/scripts/generate-nano-banana.py "clean ecommerce hero shot of running shoes" --aspect-ratio 16:9 --output ~/Desktop/shoes.png```## Check job status```bashbash ~/.openclaw/skills/pixeldojo/status.sh job_abc123```## Output pathsDefault download folders:- `~/Pictures/AI Generated/images/`- `~/Pictures/AI Generated/videos/`Override with:```bash--output /path/to/file.png```## Notes- `generate.sh` supports `--aspect-ratio`, `--duration`, `--image-url`, `--output`, `--poll-interval`, and `--max-wait`.- `generate.sh` covers the shared prompt-based API flow. If a request needs model-specific editing payloads, inspect the live catalog and API behavior before improvising.- PixelDojo markets full commercial rights for generated output, but the user is still responsible for complying with the service terms and any third-party model restrictions.

Frequently asked questions