dreamifly-batch
Automates the Dreamifly image and video generation pipeline with cost estimation and batch processing.
Install
mkdir -p .claude/skills/dreamifly-batch && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12053" && unzip -o skill.zip -d .claude/skills/dreamifly-batch && rm skill.zipInstalls to .claude/skills/dreamifly-batch
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Batch-generate Dreamifly images/videos from prompt queues. Use when the user asks to batch-generate images, edit images with references, create text-to-video or image-to-video, validate or estimate Dreamifly job cost, retry failed media jobs, or summarize Dreamifly outputs.Key capabilities
- →Batch-generate Dreamifly images/videos from prompt queues
- →Validate Dreamifly job configurations
- →Estimate the cost of Dreamifly jobs
- →Retry failed media generation tasks
- →Summarize Dreamifly generation outputs
How it works
The skill processes prompt queues using Python scripts to validate, estimate, and execute Dreamifly generation jobs, and can retry failures or summarize results.
Inputs & outputs
When to use dreamifly-batch
- →Batch generate images from prompts
- →Estimate job costs
- →Retry failed media jobs
- →Summarize generation outputs
About this skill
Dreamifly Batch
Quick Start
- Write real prompts to
prompts.txtor provide--prompts jobs.jsonl. - Run
python3 dreamify.py --validate. - Run
python3 dreamify.py --estimate. - Run
python3 dreamify.py --dry-run. - Run
python3 dreamify.py --check. - If any item costs 5+ credits, stop and ask for explicit confirmation before running.
- Run
./run.shorpython3 dreamify.py -n N. - Report with
python3 dreamify.py --summary; inspectresults.jsonlandrun.logonly if needed.
Useful Commands
python3 dreamify.py --validatepython3 dreamify.py --estimatepython3 dreamify.py --summarypython3 dreamify.py --retry-failedpython3 dreamify.py --prompts jobs.jsonl --results-file results.jsonl
References
- Model choice and cost rules:
references/model-selection.md - Output and reporting contract:
references/output-contract.md - Failure lessons and hard boundaries:
references/gotchas.md - Trigger eval cases:
references/evals.md - JSONL job examples:
examples/prompts.jsonl
When not to use it
- →When the user wants to inspect or debug UI
- →When the user wants to troubleshoot generic MAUI build failures
Prerequisites
Limitations
- →Requires explicit user confirmation for high-cost models (5+ credits)
- →Relies on Python 3 and network access to dreamifly.com
- →Does not provide a full action library or full runtime automation
How it compares
This skill automates the batch generation of images and videos from prompt queues, including validation, cost estimation, and retry mechanisms, which is more efficient than submitting individual generation requests.
Compared to similar skills
dreamifly-batch side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| dreamifly-batch (this skill) | 0 | 1mo | No flags | Intermediate |
| gemini-logo-remover | 9 | 8mo | Review | Beginner |
| slack-gif-creator | 6 | 3mo | Review | Intermediate |
| image-crop-rotate | 0 | 10mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
gemini-logo-remover
bear2u
Remove Gemini logos, watermarks, or AI-generated image markers using OpenCV inpainting. Use this skill when the user asks to remove Gemini logo, AI watermark, or any logo/watermark from images.
slack-gif-creator
anthropics
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."
image-crop-rotate
instavm
Image processing skill for cropping images to 50% from center and rotating them 90 degrees clockwise. This skill should be used when users request image cropping to center, image rotation, or both operations combined on image files.
sora
davila7
Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.
post-process-logo
tradingstrategy-ai
Post-process original logos into standardised 256x256 PNG format
compress_image
CoderWanFeng
压缩图片文件大小，通过调整质量参数控制输出体积。当用户提到压缩图片、图片减肥、缩小图片体积、降低图片质量时使用。