agnes-ai-skill
Agnes AI Skill brings multimodal generation—text, images, and video—to your terminal through the agnes-ai-cli. It wraps Agnes's models (text-to-image, image-to-image, image-to-video, and keyframe video) in a streamlined CLI interface, handling auth, file uploads, and polling automatically. Use it for prototyping, creative iteration, or agent-driven content workflows.
Agnes AI Skill lets you generate text, images, and videos through the agnes-ai-cli command line.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-06-13
Agnes AI Skill lets you generate text, images, and videos through the agnes-ai-cli command line. Agnes AI Skill brings multimodal generation—text, images, and video—to your terminal through the agnes-ai-cli. It wraps Agnes's models (text-to-image, image-to-image, image-to-video, and keyframe video) in a streamlined CLI interface, handling auth, file uploads, and polling automatically. Use it for prototyping, creative iteration, or agent-driven content workflows.
Use it when
- Agnes AI Skill requires API key authentication to access generation models.
- Agnes AI Skill supports image-to-video generation with keyframe support built in.
Verify before relying
Read SKILL.md below before installing (40 files). Open directory: indexed for reading, not audited.
Install
jomeswang/agnes-ai-skill/agnes-ai-skill
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I use Agnes AI for text generation via the CLI?
Agnes AI Skill provides a command-line interface to generate text, images, and videos. To generate text, install the agnes-ai-cli package, authenticate with your API key, and run text generation commands through the terminal. The CLI handles authentication and polling automatically, letting you prototype and iterate quickly without manual API calls.
How do I set up and configure Agnes AI with an API key?
Agnes AI Skill requires API key authentication to access generation models. After installing agnes-ai-cli via npm, configure your API key in the environment or config file as instructed in the setup guide. Once authenticated, the CLI automatically manages token refresh and request signing, so you can focus on generation workflows.
Can I generate video with Agnes AI, and does it support keyframes?
Agnes AI Skill supports image-to-video generation with keyframe support built in. You can convert images or prompts into videos by specifying keyframes through the CLI. The skill wraps Agnes's video models and handles polling automatically, making it easy to create frame-by-frame video content from your terminal.
What multimodal generation capabilities does Agnes AI Skill offer?
Agnes AI Skill brings text-to-image, image-to-image, image-to-video, and keyframe video generation into one platform. All models are accessible through the agnes-ai-cli, letting you compose multiple images, edit existing ones, and convert between formats—all from the command line without switching tools.
How can I integrate Agnes AI generation into agent workflows?
Agnes AI Skill is designed for agent-driven content workflows. You can integrate it into scripts and automation by calling the CLI commands programmatically or embedding generation logic into larger agent pipelines. The skill handles file uploads and async polling, making it straightforward to chain generation steps in complex workflows.
Is Agnes AI Skill free to use, and what license does it have?
Agnes AI Skill is released under the MIT license, making it free to use and modify. Access to Agnes's generation models requires an API key; check Agnes's pricing and free-tier policy for model usage costs. The CLI itself is open-source and ready to deploy locally or in agent environments.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Agnes AI Skill
Use this skill when the user wants Agnes AI text, image, or video generation.
This skill is now CLI-first: prefer agnes-ai-cli for all live
(truncated - see the full file via the links below)
File tree — 15 files
.gitattributes
.gitignore
LICENSE
README.md
README.zh-CN.md
SKILL.md
agents/openai.yaml
assets/apps/beijing-map-ui.jpg
assets/apps/cinematic-ai-landing.jpg
assets/apps/watch-experience.jpg
assets/images/agnes-frontier-models-banner.jpg
assets/images/brand-envelope-perfume.png
assets/images/cyberpunk-bridge.jpg
assets/images/latte-infographic.jpg
assets/images/pencil-editorial-fashion.png
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Generate text, images, or videos using Agnes AI through the CLI”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Call Agnes AI's text, image, and video generation APIs directly from your agent. The skill wraps Agnes 2.0 Flash for text, Agnes Image 2.1 Flash for image generation and editing, and Agnes Video V2.0 for text-to-video, image-to-video, and keyframe animation with polling-based retrieval.
Haizei Agnes Image Gen harnesses the Agnes Image 2.1 Flash model to create images from text descriptions, edit existing images, or blend multiple images together. The skill runs on Node.js with no external dependencies, handling all image data via Base64 encoding for seamless integration.
This execution layer routes image generation requests to four different API providers—MuleRun Nano Banana 2, APImart GPT Image 2, Atlas Cloud GPT Image 2, and Agnes Image 2.1 Flash—switchable via the `--provider` parameter. It supports both pure text-to-image generation and reference-image-based editing in single or batch modes, designed to be called by other skills rather than used directly.
Short Video Cover creates platform-optimized 3:4 vertical thumbnails for short-form video platforms by analyzing your video script and producing covers with bold typography, host imagery, and UI elements that drive engagement. Choose from 11 visual styles—from dark tech to split-screen narrative—or use the default deep-tech look, then let the skill generate and self-check your cover before delivery.
Analyzes technical articles to pinpoint sections worth illustrating—abstract concepts, processes, comparisons, and system architecture—then generates 16:9 diagrams in your choice of seven visual styles. Supports notebook sketches, professional infographics, cozy handdrawn, tech doodles, cartoon layouts, whiteboard sketches, and executive-tech designs. Keeps long-form content engaging without cluttering every paragraph.
Edu Subject Infographic transforms any topic into a vertical teaching graphic by automatically identifying the subject, breaking down 3–5 core concepts, assigning a cohesive color scheme, and generating illustrated descriptions for each section. The skill includes dual-layer accuracy verification—checking prompts against subject-specific guidelines before generation, then visually reviewing the rendered PNG for text clarity, formulas, and diagram logic. Batch generation lets you create multiple infographics at once with consistent styling but distinct color palettes.
More skills Article Explainer Video (unlicensed) · Wan Video (NOASSERTION)