agnes-ai-skill

Agnes AI Free Text, Image & Video Generation Skill

Agnes AI Skill is a free multimodal Agent Skill for Codex, Claude Code, OpenClaw, Claude Desktop, Hermes, WorkBuddy, Cherry Studio, Opencode, and similar AI agent tools. It helps agents use Agnes 2.0 APIs for text generation, image generation, image editing, text-to-video, image-to-video, and API integration through a single root SKILL.md.

Use this Agnes skill when you want an Agnes AI skill, image generation skill, video generation skill, text to image workflow, image to video workflow, free AI API workflow, or free AI model workflow that fits Codex skills, Claude Code skills, and OpenClaw skills.

中文：Agnes AI 免费文本 / 生图 / 图片编辑 / 生视频 Agent Skill，支持 Codex、 Claude Code、OpenClaw、Claude Desktop、Hermes、WorkBuddy、Cherry Studio、 Opencode 等工具。

Quick Start

Install the skill with a repository-aware skills installer:

npx skills add jomeswang/agnes-ai-skill -g

Or copy this sentence to your agent:

Please read and install Agnes AI Skill: https://github.com/jomeswang/agnes-ai-skill

After installation, create an Agnes API key at platform.agnes-ai.com/settings/apiKeys and configure it as AGNES_API_KEY. Then tell the agent generate an image, generate a video, edit this image, or integrate Agnes API, and it can choose the proper Agnes model and execution path automatically.

This skill helps agents:

• set up Agnes AI and persist an AGNES_API_KEY
• use agnes-2.0-flash for chat, coding, streaming, and tool calling
• use agnes-image-2.0-flash and agnes-image-2.1-flash for AI image generation, image editing, and image-to-image workflows
• use agnes-video-v2.0 for text-to-video, image-to-video, and async video generation
• prefer the companion agnes-ai-cli for live requests

Compatible tools: Codex, Claude Code, Claude Desktop, OpenClaw, Hermes, WorkBuddy, Cherry Studio, Opencode, Kimi Work, and other Agent Skills / SKILL.md-compatible environments.

Important Announcement

Agnes 2.0 full-modal model APIs are officially open for free global calls.

• No fixed end date, full-modal access, and free API calls within RPM 20
• Register on the official platform, create a key, and call directly
• Text, image, and video are all supported
• Models keep upgrading while free access is maintained

Official platform: https://platform.agnes-ai.com

The live official model docs also include pricing sections. For cost, quota, or commercial use, check the current official docs first.

This repository packages a single root SKILL.md so coding agents can quickly:

• get and persist an Agnes API key
• use agnes-2.0-flash for chat, coding, streaming, and tool calling
• use agnes-image-2.0-flash and agnes-image-2.1-flash for image generation and editing
• use agnes-video-v2.0 for asynchronous video generation and polling

It is designed for the exact pitch that makes Agnes easy to try:

• one provider for text, image, and video
• public free-access positioning that lowers experimentation friction
• agent, creative, and prototyping workflows where repeated calls matter

The skill stays intentionally lightweight. It teaches agents how to make Agnes API calls successfully without copying the full docs into the repository.

Install

With a repository-aware skills installer:

npx skills add jomeswang/agnes-ai-skill -g

Because this repository uses a single root SKILL.md, installers that support repository-root skills can discover it directly.

Verified Install Path

This repository has been validated with:

npx skills add jomeswang/agnes-ai-skill --list
npx skills add jomeswang/agnes-ai-skill --agent codex --yes

The repository is discoverable as a single root-level skill named agnes-ai-skill.

Companion CLI

The published companion execution layer is:

• npm: agnes-ai-cli
• GitHub: jomeswang/agnes-ai-cli

Install it when you want stable commands instead of hand-written requests:

npm install -g agnes-ai-cli
agnes --help

Model Guide

Use the repository skill with these defaults:

• agnes-2.0-flash
  • chat, coding, streaming, tool calling, and agent workflows
  • default when text chat runs without --model
• agnes-image-2.1-flash
  • default for new text-to-image and image-to-image work
  • strongest fit for denser layouts, richer detail, and better semantic alignment
  • default when image text2img, image img2img, or image compose runs without --model
• agnes-image-2.0-flash
  • better when you explicitly need its documented tags: ["img2img"] flow, multi-image composition, or seed-based reproducibility
• agnes-video-v2.0
  • text-to-video, image-to-video, multi-image guided video, keyframes, and asynchronous polling
  • current default when any video generate command runs without --model

The official docs also give each model fairly different best practices:

• Image 2.1 leans into high-information-density visuals and composition preservation
• Image 2.0 is more explicit about edit/composition workflows, response fields, and OpenAI Images-style compatibility
• Video 2.0 is task-based and documents multiple generation modes, task states, result polling, and frame-count constraints

Showcase

The strongest outside prompt libraries all do the same three things well: lead with a preview, keep the prompt compact enough to scan, and organize examples by outcome instead of by raw API parameter lists. This gallery follows that pattern with 9 compact cases regenerated with Agnes on June 1, 2026. The image prompts were tightened toward the shorter, more editorial style seen in awesome-gpt-image-2, the video prompts were rebuilt around ad-film, animation, and cinematic beats inspired by awesome-seedance, and the HTML cases were regenerated as brighter, more public-facing product experiences.

Image Cases

agnes-image-2.1-flash

Video Cases

agnes-video-v2.0