OpenHands · chengzeyi · Sep 5, 2026
diff --git a/marketplaces/openhands-extensions.json b/marketplaces/openhands-extensions.json
@@ -834,6 +834,19 @@
         "pull-request",
         "automation"
       ]
+    },
+    {
+      "name": "wavespeed",
+      "source": "./skills/wavespeed",
+      "description": "Generate and edit AI media (image, video, audio, 3D) on the WaveSpeed platform through the open-source wavespeed CLI: live catalog search, per-model schema, price quotes, local-file upload.",
+      "category": "integrations",
+      "keywords": [
+        "wavespeed",
+        "image-generation",
+        "video-generation",
+        "audio",
+        "3d"
+      ]
     }
   ]
 }
diff --git a/skills/index.js b/skills/index.js
diff --git a/skills/wavespeed/.claude-plugin b/skills/wavespeed/.claude-plugin
@@ -0,0 +1 @@
+.plugin
diff --git a/skills/wavespeed/.codex-plugin b/skills/wavespeed/.codex-plugin
@@ -0,0 +1 @@
+.plugin
diff --git a/skills/wavespeed/.plugin/plugin.json b/skills/wavespeed/.plugin/plugin.json
@@ -0,0 +1,20 @@
+{
+  "name": "wavespeed",
+  "version": "1.0.0",
+  "description": "Generate and edit AI media (image, video, audio, 3D) on the WaveSpeed platform through the open-source wavespeed CLI: live catalog search, per-model schema, price quotes, local-file upload.",
+  "author": {
+    "name": "WaveSpeedAI",
+    "email": "support@wavespeed.ai"
+  },
+  "homepage": "https://github.com/WaveSpeedAI/agent-skills",
+  "repository": "https://github.com/WaveSpeedAI/agent-skills",
+  "license": "MIT",
+  "keywords": [
+    "wavespeed",
+    "image-generation",
+    "video-generation",
+    "audio-generation",
+    "3d-generation",
+    "media"
+  ]
+}
diff --git a/skills/wavespeed/README.md b/skills/wavespeed/README.md
@@ -0,0 +1,22 @@
+# WaveSpeed
+
+Generate and edit AI media — image, video, audio, 3D — on the [WaveSpeed](https://wavespeed.ai) platform from OpenHands, through the open-source [`wavespeed` CLI](https://github.com/WaveSpeedAI/wavespeed-cli).
+
+The skill teaches the agent the find → inspect → run pattern: search the live model catalog, read the selected model's input schema, quote the price, run it with `--json`, and upload local files with the `@path` marker. The agent never asks the user to paste an API key into the chat; `wavespeed login` (or `WAVESPEED_API_KEY` in the sandbox environment) handles auth.
+
+## Setup
+
+```bash
+npm install -g @wavespeed/cli
+wavespeed login          # or export WAVESPEED_API_KEY=...
+```
+
+## Example prompts
+
+- "Generate a 16:9 hero image of a cyberpunk skyline at golden hour."
+- "Animate ./hero.jpg into a 5-second clip with subtle parallax."
+- "Replace the background of ./product.png with a sunlit kitchen, and tell me the cost first."
+
+## More
+
+Per-model skills (Seedream, Seedance, Veo 3.1, Wan, Nano Banana, MiniMax Speech, upscalers, face swap, watermark removal) and the `@wavespeed/mcp` server declaration live in [WaveSpeedAI/agent-skills](https://github.com/WaveSpeedAI/agent-skills).
diff --git a/skills/wavespeed/SKILL.md b/skills/wavespeed/SKILL.md
@@ -0,0 +1,89 @@
+---
+name: wavespeed
+description: Generate or edit AI media (image, video, audio, 3D) by calling the wavespeed CLI on the user's machine. Use whenever the user asks to create, edit, animate, upscale, or transform a visual asset, generate audio/TTS/music, or produce marketing creatives. Every model on the WaveSpeed platform is one `wavespeed run <id>` call.
+triggers:
+- wavespeed
+- generate image
+- generate video
+- text to image
+- image to video
+- text to video
+- upscale
+- text to speech
+---
+
+# WaveSpeed
+
+You have access to the `wavespeed` CLI. Every generation flows through one verb. There are no `image` / `video` shortcuts; the model id is always explicit.
+
+## The three-step pattern
+
+```bash
+# 1. FIND a model — search the live catalog
+wavespeed models "seedream"
+wavespeed models --type image-to-video --popular
+
+# 2. INSPECT its inputs — dynamic schema, per model
+wavespeed run bytedance/seedream-v5.0-pro -h
+
+# 3. RUN it — always pass --json so you can read the result
+wavespeed run bytedance/seedream-v5.0-pro \
+  -p "a cyberpunk skyline at golden hour" \
+  -i aspect_ratio="16:9" -i resolution="2k" --json
+```
+
+`run --json` returns `{ id, model, prompt, outputs: [url, ...], saved: [path, ...], elapsed_ms, raw }`. Keep `id` — it is the handle for `wavespeed show <id>` if anything is interrupted. Use the URL when the user wants a link. Add `--download` if they need bytes on disk.
+
+## Recommended defaults
+
+| Use case | Model |
+|---|---|
+| Text → image | `bytedance/seedream-v5.0-pro` |
+| Image edit (instruction-driven) | `bytedance/seedream-v5.0-pro/edit` — requires `images: [url, ...]` |
+| Text → video | `wavespeed-ai/minimax-h3/text-to-video` |
+| Image → video | `wavespeed-ai/minimax-h3/image-to-video` — requires `image: url` |
+| Video edit (instruction-driven) | `wavespeed-ai/minimax-h3/video-edit` — requires `video: url` |
+| Video extend | `wavespeed-ai/minimax-h3/video-extend` — requires `video: url` |
+
+These are good starting points. MiniMax H3 is the open-weights default: cheap, fast, and native stereo audio — the best place to start. When you need the highest quality, switch to `bytedance/seedance-2.5/*` (text-to-video, image-to-video, video-edit, video-extend). Browse alternatives with `wavespeed models <query>`.
+
+## Common recipes
+
+```bash
+# Edit an existing image — @path uploads the file and passes its URL (one step)
+wavespeed run bytedance/seedream-v5.0-pro/edit \
+  -p "replace the background with a sunlit kitchen" \
+  -i images='["@./input.jpg"]' --json
+
+# Image-to-video — same @ marker for single-URL fields
+wavespeed run wavespeed-ai/minimax-h3/image-to-video \
+  -p "subtle parallax, gentle wind" \
+  -i image=@./hero.jpg -i duration=5 --json
+
+# Or upload separately when you need the URL itself
+URL=$(wavespeed upload ./hero.jpg --json | jq -r .url)
+
+# Save outputs locally with a template
+wavespeed run ... -p "..." --download "./out/{index}.{ext}"
+```
+
+## Project config and aliases
+
+If `wavespeed.json` exists (created by `wavespeed init`):
+
+- **`defaultModel`** — lets `wavespeed run -p "…"` (no model arg) work.
+- **Aliases** — named shortcuts that bundle model + default inputs. Run `wavespeed aliases` to see what's defined. `wavespeed run <alias> -h` shows the resolved schema. CLI `-i k=v` overrides alias defaults.
+
+The CLI never modifies the user's prompt or inputs. The single exception is explicit: an `@path` value uploads that file and substitutes its hosted URL. Bare paths are never uploaded.
+
+## Auth
+
+`wavespeed status` shows whether the user is signed in. If not, ask them to run `wavespeed login` (opens https://wavespeed.ai/accesskey). **Never** ask the user to paste an API key into the chat — the CLI handles it.
+
+## Pitfalls
+
+- Local files: use `@./file.jpg` in `-i` values. Bare paths are NOT uploaded and the model will reject them.
+- Don't invent model IDs. Always confirm via `wavespeed models` or `wavespeed schema <id>` before running.
+- Use `--json` on every `run` so you can read `outputs[0]` programmatically.
+- `wavespeed delete` requires `--yes` when run non-interactively (that includes you).
+- Spend questions: `wavespeed usage` (totals, per-model) and `wavespeed billings` (per-charge records).