skills
67 agent skills from scenario-labs/skills — including scenario, scenario-game-assets, scenario-video. Install with npx skills add scenario-labs/skills.
NezhaGate 是 OpenAI 兼容的 AI 模型网关:换掉 base_url 和 Key,一个接口即可调用 GPT、Claude、Gemini、Grok、DeepSeek、Kimi、GLM、Qwen 对话与生图…
Translation pending
SkillsPythonGitHub @gaoorangeOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Agent Skills for NezhaGate: Seedance 2.5 / 2.0 text-to-video and image-to-video from Claude Code, Codex and Cursor
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
Agent Skills that let coding agents (Claude Code, Codex, Cursor and other skill-aware agents) use the
NezhaGate API directly: ask in plain words, and the agent picks the model,
sends your files, waits for the job and saves the result.
*Made with this skill in one request: seedance-2.5, 8 s, 720P, one reference image, generated soundtrack.
Watch the clip · storyboard*
Manual install: copy skills/nezhagate-seedance/ into your agent's skills folder, for example
~/.claude/skills/nezhagate-seedance/ for Claude Code or ~/.codex/skills/nezhagate-seedance/ for Codex.Read the full README ↗Agent Skills that let coding agents (Claude Code, Codex, Cursor and other skill-aware agents) use the NezhaGate API directly: ask in plain words, and the agent picks the model, sends your files, waits for the job and saves the result.
Made with this skill in one request: seedance-2.5, 8 s, 720P, one reference image, generated soundtrack.
Watch the clip · storyboard
| Skill | What it does |
|---|---|
nezhagate-seedance | Text-to-video and video from reference images, videos and audio with ByteDance Seedance 2.5 / 2.0, including the per-clip Seedance 2.0 Clip and Seedance 2.5 30s, native soundtrack. Includes a zero-dependency Python helper that lists the models on sale with live prices, checks the request before you pay, then submits, waits and downloads. |
One line, from our site:
npx skills add https://nezhagate.com
or from this repository:
npx skills add gaoorange/nezhagate-skills
Manual install: copy skills/nezhagate-seedance/ into your agent's skills folder, for example
~/.claude/skills/nezhagate-seedance/ for Claude Code or ~/.codex/skills/nezhagate-seedance/ for Codex.
Create a key at https://nezhagate.com/keys, then make it available to the agent:
export NEZHAGATE_API_KEY=your_key # macOS / Linux
$env:NEZHAGATE_API_KEY = "your_key" # Windows PowerShell (current window)
setx NEZHAGATE_API_KEY "your_key" # Windows, for windows opened later
Start the agent from a shell where the variable is set. The skill never needs the key in your project files.
Use the nezhagate-seedance skill: make an 8-second 16:9 clip with seedance-2.5 of the woman in ./hero.png
turning to the camera on a rooftop at golden hour, slow dolly in, and save it to ./out/rooftop.mp4.
Or run the helper yourself:
python skills/nezhagate-seedance/scripts/seedance.py --models # models on sale, live prices
python skills/nezhagate-seedance/scripts/seedance.py --model seedance-2.5 --image ./hero.png \
--prompt "The woman from @Image1 turns to the camera on a rooftop at golden hour, slow dolly in" \
--duration 8 --ratio 16:9 --dry-run # check the request, submit nothing
python skills/nezhagate-seedance/scripts/seedance.py --model seedance-2.5 --image ./hero.png \
--prompt "The woman from @Image1 turns to the camera on a rooftop at golden hour, slow dolly in" \
--duration 8 --ratio 16:9 --out ./out/rooftop.mp4 # submit, wait, download
For a long or multi-line prompt, put it in a UTF-8 file and pass --prompt-file prompt.txt instead of --prompt.
The prompt behind the demo clip:
Golden-hour rooftop in an old Chinese city. The young woman from @Image1, in a cream trench coat, turns from the railing toward the camera; the wind lifts her hair, she hesitates, then breaks into a small relieved smile as distant temple bells ring. Slow dolly-in from medium shot to close-up, shallow depth of field, warm rim light, film grain, soft strings over the city hum.
Some Seedance models bill per second and others per clip, in NezhaGate credits. Current prices: --models or
https://nezhagate.com/en/pricing.
well-known/agent-skills/ holds the agentskills.io discovery index and the
archive it points to, served at https://nezhagate.com/.well-known/agent-skills/. Rebuild both after editing a skill:
python tools/build_archive.py
MIT