Agnes AI Generation Skill
A Python script calls the Agnes AI API for text, images and video from a prompt, a photo or keyframes, and polls for the result
- 425 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The script calls the external Agnes API with your key and sends prompts and image links there
- The author suggests sending the key to the agent in chat, and a key in chat history stays exposed
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/agnes-ai-generation-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The script calls the external Agnes API with your key and sends prompts and image links there
- The author suggests sending the key to the agent in chat, and a key in chat history stays exposed
This is third-party code. Review the repository files before installing.
What it does
The skill wraps the official Agnes AI APIs in a single `scripts/agnes_api.py` command. The agent generates text with `agnes-2.0-flash`, including streaming, creates and edits images with `agnes-image-2.1-flash`, and makes video with `agnes-video-v2.0` from text, one image, a set of images or between two keyframes. Video is created asynchronously: the script takes a task id, polls the status with `--poll` and returns links to the finished files. Image and video prompts in another language are first translated into English by `agnes-2.0-flash`, because Agnes video comes out more stable from English. The `--no-translate-prompt` flag turns the translation off. After generation the skill returns links only and downloads nothing to disk until you ask for a file. For video the script fills in `--num-frames 121 --frame-rate 24` and checks that the frame count has the form 8n+1 and does not exceed 441.
Who it is for. Users of Claude Code, Codex, Cursor and Windsurf with an Agnes platform account who want images and clips from an agent chat without handling REST by hand.
Good fit when
- A short cinematic clip is built from a text description and picked up by link
- A single image is brought to life with a light camera move and natural lighting
- Two images are joined with a smooth transition in keyframe mode
- A photo scene is redrawn in another style while keeping the composition
- Before building a pipeline, `smoke-test` runs to see whether text and images respond
Not a fit when
- The agent has to run multi-turn function calling through the Agnes Responses API: the author calls that loop unreliable
- You need dependable multi-image and keyframe video modes: the author has not tested them end to end
- You have no account and key on the Agnes platform
- You want files on disk at once: the skill returns links by default
Example request
Using Agnes, make a 5-second cinematic video of a cat walking on a beach at sunset, wait for it to finish and return the linkLimitations
A key from the Agnes platform (`https://platform.agnes-ai.com/`) is required, set in `AGNES_API_KEY`, `AGNES_API_TOKEN` or `APIHUB_AGNES_API_KEY`. Requests go to `https://apihub.agnes-ai.com`. The author has not fully tested the multi-image and keyframe modes, and once the server returned a `division by zero` error while polling a task, so try the modes one at a time. Tool calling is supported only as a request shape: the multi-turn Responses API does not suit an automatic agent loop. The author suggests sending the key to the agent in chat, but an environment variable is safer because the key stays out of the history. The latest release is v0.1.0, with commits from June 2026.
How to disable. Delete the `agnes-ai-generation` skill folder from the agent's skills directory and unset `AGNES_API_KEY` in the environment. If you set it at the Windows user level, delete the entry in environment settings. Delete the key on the Agnes platform by hand if you no longer need it.
FAQ
How do I connect Agnes to Claude Code or Codex?
Run `npx skills add Yacey/agnes-ai-generation-skill`, adding `--all` for every supported agent. Then get a key on the Agnes platform and set it in the `AGNES_API_KEY` variable.
Which models does the skill call?
`agnes-2.0-flash` for text, `agnes-image-2.1-flash` for images and image edits, and `agnes-video-v2.0` for video from text, an image, a set of images or keyframes.
How do I get the finished video?
Run `python scripts/agnes_api.py video --prompt "..." --poll`. The script creates a task, polls its status by `video_id` and returns a link to the mp4. `video-get` with the id shows the task status on its own.
Why does the skill translate my prompt into English?
Agnes produces more stable video and images from English prompts, so the script translates other languages with `agnes-2.0-flash`. To send your original text, add `--no-translate-prompt`.
Does the skill download files to disk?
No, by default it returns only the `urls` field. A file lands on disk when you directly ask to download or save the result.
Discussion
No questions or reviews yet.
Related
SkillsThree skills call the free Agnes AI models: chat, images and video through Python scripts and a key from an environment variable
A skill that turns an idea, a link or a screen recording into finished video: HeyGen avatar, b-roll, captions and quality checks
Three HeyGen skills: an avatar from a photo, a video with that avatar on screen from a brief, and translation of finished videos with dubbing and lip-sync
A skill that writes prompts for video, image and music generation on 14 platforms and can submit them in the browser
Image generation and editing from any agent: the imagegen-agent CLI and a skill with the Codex prompt library for compatible APIs
Two skills for generative video and images: video writes Seedance, Kling and Veo prompts by dramaturgy rules, image picks the model and its syntax
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Agnes AI Generation Skill (this card) | no | 425 | |
| AI Video Generator | no | 456 | ten skills prepare detailed Seedance 2.0 prompts; this skill calls the Agnes API itself and returns finished files |
| Nano Banana 2 Skill | no | 417 | images through Gemini; here Agnes models and video, including keyframe video |
README in short
The page goes step by step: get a key, install the skill, set the variable, send a first request. Then come command examples for text, images and video, a section on prompt language, a list of what was and was not tested against the real API, and the repository layout. An English version exists.
README badge
Original SKILL.md
--- name: agnes-ai-generation description: Call Agnes AI / Sapiens AI generation APIs for text, image, and video. Use when the user asks to use Agnes models, Agnes Image, Agnes Video, Agnes 2.0 Flash, apihub.agnes-ai.com, or to generate text, images, edit images, create videos, animate images, create keyframe videos, or test Agnes API calls. --- # Agnes AI Generation Use this skill to call Agnes text, image, and video generation APIs through `https://apihub.agnes-ai.com`. ## Quick Start 1. Read `references/api.md` when endpoint details, parameters, or response fields are needed. 2. Use `scripts/agnes_api.py` for real API calls instead of rewriting curl by hand. 3. Require an API key in `AGNES_API_KEY`, `AGNES_API_TOKEN`, or `APIHUB_AGNES_API_KEY`. Never print the key. 4. For light live verification, run `smoke-test`; it avoids video creation by default. Add `--include-image-edit` for image-to-image, and add `--video-case <case>` explicitly for video modes. Treat the skill as fully tested only when basic text, text streaming, text tool calling, text-to-image, image-to-image, text-to-video, image-to-video, multi-image video, keyframe video, and video retrieval return successful responses. ## Commands Text generation: ```bash python scripts/agnes_api.py text --prompt "Write a concise product tagline for an AI assistant." ``` Streaming text: ```bash python scripts/agnes_api.py text --prompt "Write a short product intro." --stream ``` Streaming output is normalized and includes aggregated `content`, `events`, `done`, and a short `raw_prefix`. Image generation: ```bash python scripts/agnes_api.py image --prompt "A luminous floating city above a misty canyon at sunrise, cinematic realism" --size 1024x768 ``` Image-to-image: ```bash python scripts/agnes_api.py image --prompt "Turn the scene into a rainy cyberpunk night while preserving composition" --image https://example.com/input.png --size 1024x768 ``` Text-to-video with polling: ```bash python scripts/agnes_api.py video --prompt "A cinematic shot of a cat walking on the beach at sunset" --poll ```