Agent Skills for generating and editing AI media — image, video, audio, 3D — on the WaveSpeed platform. One general skill teaches the agent the image and video shortcuts and the find → inspect → run workflow, on the open-source wavespeed CLI or the WaveSpeed MCP tools. The bundled @wavespeed/mcp server exposes the same platform as MCP tools.
The skill follows the Agent Skills SKILL.md format, and the repo root is an Agent Plugins 1.0 package (plugin.json + mcp.json + skills/), so it installs as-is into Kiro, Codex, Qwen Code, OpenHands and any other Agent Plugins consumer.
wavespeed covers generating and editing images, generating, editing and extending videos with the shortcuts (the same default models as the WaveSpeed /chat page), and every other model in the catalog through one generic run: search models, read a model's schema, quote the price, run, upload local files with @path.
Any agent that reads .agents/skills/ or .claude/skills/ (Claude Code, Codex, Cursor, OpenCode, Kimi Code, Antigravity, Copilot CLI, Amp, Droid, ...):
npx skills add WaveSpeedAI/agent-skillsKiro — Powers panel → Add Custom Power → Import power from GitHub → https://github.com/WaveSpeedAI/agent-skills.
Qwen Code / Codex / Kimi Code — the repo is an Agent Plugins package: qwen extensions install WaveSpeedAI/agent-skills, or the dedicated packages below.
OpenClaw — on ClawHub under @wavespeed: clawhub install wavespeed.
Dedicated packages (same skill, native packaging):
- Claude Code: WaveSpeedAI/claude-plugins
- Codex: WaveSpeedAI/codex-plugins
- Kimi Code CLI: WaveSpeedAI/wavespeed-kimi-plugin
- Gemini CLI: WaveSpeedAI/wavespeed-gemini-extension
- DeepSeek Harness: WaveSpeedAI/wavespeed-dsh-skill
npm install -g @wavespeed/cli
wavespeed login # opens https://wavespeed.ai/accesskey and stores the keyWAVESPEED_API_KEY in the environment also works, and the MCP server shares the CLI's stored login. The skill tells the agent never to ask a user to paste a key into the chat.
mcp.json starts @wavespeed/mcp over stdio with npx. Tools: list_models, get_model_schema, get_price, upload_file, run_model, generate_image, edit_image, generate_video, edit_video, extend_video, get_prediction, list_predictions, delete_predictions, get_balance, get_usage, list_billings. The skill's CLI commands map one-to-one onto these tools.
Images: Seedream 5 Pro (wavespeed generate image / edit image). Video: Seedance 2.5 (wavespeed generate video, edit video, extend video), with Kling 4.0, Wan 3.0 and MiniMax H3 (cheap, native audio, 768p) as alternatives. Everything else is one wavespeed models <query> away.
- Support: support@wavespeed.ai · GitHub issues
- Privacy policy: https://wavespeed.ai/static/privacy
- Terms of service: https://wavespeed.ai/static/terms
- Security: see SECURITY.md
MIT — same as the CLI and the MCP server.
WaveSpeedAI — AI image & video generation platform. Try it in the browser: Image generator · Video generator