@acedatacloud/skills 2026.406.2 → 2026.418.0

package/README.md

@@ -70,10 +70,10 @@ export ACEDATACLOUD_API_TOKEN="your-token-here"
 
 ```bash
 # Install all skills (for any agentskills.io-compatible agent)
-npx skills add AceDataCloud/Skills --skill '*' --yes
+npx skills add acedatacloud/skills --skill '*' --yes
 
 # Install specific skills only
-npx skills add AceDataCloud/Skills --skill suno-music --skill midjourney-image --yes
+npx skills add acedatacloud/skills --skill suno-music --skill midjourney-image --yes
 ```
 
 The [`skills` CLI](https://github.com/vercel-labs/skills) auto-detects your agent and installs to the correct path.
@@ -86,10 +86,10 @@ The [`skills` CLI](https://github.com/vercel-labs/skills) auto-detects your agen
 
 ```bash
 # Install all skills for Claude Code
-npx skills add AceDataCloud/Skills --skill '*' -a claude-code --yes
+npx skills add acedatacloud/skills --skill '*' -a claude-code --yes
 
 # Install specific skills
-npx skills add AceDataCloud/Skills --skill suno-music -a claude-code --yes
+npx skills add acedatacloud/skills --skill suno-music -a claude-code --yes
 ```
 
 Skills are symlinked into `.claude/skills/` and auto-discovered by Claude Code.
@@ -97,7 +97,7 @@ Skills are symlinked into `.claude/skills/` and auto-discovered by Claude Code.
 **Option B: Plugin Marketplace**
 
 ```
-/plugin marketplace add AceDataCloud/Skills
+/plugin marketplace add acedatacloud/skills
 /plugin install acedatacloud-ai-media@acedatacloud-skills
 /plugin install acedatacloud-ai-tools@acedatacloud-skills
 ```
@@ -118,49 +118,49 @@ cp -r Skills/skills/* .claude/skills/
 ### GitHub Copilot
 
 ```bash
-npx skills add AceDataCloud/Skills --skill '*' -a github-copilot --yes
+npx skills add acedatacloud/skills --skill '*' -a github-copilot --yes
 ```
 
 ### Gemini CLI
 
 ```bash
-npx skills add AceDataCloud/Skills --skill '*' -a gemini-cli --yes
+npx skills add acedatacloud/skills --skill '*' -a gemini-cli --yes
 ```
 
 ### OpenAI Codex
 
 ```bash
-npx skills add AceDataCloud/Skills --skill '*' -a codex --yes
+npx skills add acedatacloud/skills --skill '*' -a codex --yes
 ```
 
 ### Cursor
 
 ```bash
-npx skills add AceDataCloud/Skills --skill '*' -a cursor --yes
+npx skills add acedatacloud/skills --skill '*' -a cursor --yes
 ```
 
 ### Roo Code
 
 ```bash
-npx skills add AceDataCloud/Skills --skill '*' -a roo --yes
+npx skills add acedatacloud/skills --skill '*' -a roo --yes
 ```
 
 ### Goose
 
 ```bash
-npx skills add AceDataCloud/Skills --skill '*' -a goose --yes
+npx skills add acedatacloud/skills --skill '*' -a goose --yes
 ```
 
 ### Windsurf
 
 ```bash
-npx skills add AceDataCloud/Skills --skill '*' -a windsurf --yes
+npx skills add acedatacloud/skills --skill '*' -a windsurf --yes
 ```
 
 ### Cline
 
 ```bash
-npx skills add AceDataCloud/Skills --skill '*' -a cline --yes
+npx skills add acedatacloud/skills --skill '*' -a cline --yes
 ```
 
 ### Other Agents
@@ -168,7 +168,7 @@ npx skills add AceDataCloud/Skills --skill '*' -a cline --yes
 The `skills` CLI supports 40+ agents. Use `npx skills add --help` to see all options, or install to the universal `.agents/skills/` path:
 
 ```bash
-npx skills add AceDataCloud/Skills --skill '*' --yes
+npx skills add acedatacloud/skills --skill '*' --yes
 ```
 
 ## Pairing Skills with MCP Servers

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@acedatacloud/skills",
-  "version": "2026.406.2",
+  "version": "2026.418.0",
   "description": "Agent Skills for AceDataCloud AI services — music, image, video generation, LLM chat, web search. Compatible with Claude Code, GitHub Copilot, Gemini CLI, OpenAI Codex, and 30+ AI coding agents.",
   "keywords": [
     "agent-skills",

package/skills/_shared/authentication.md

@@ -2,17 +2,29 @@
 
 All AceDataCloud APIs use Bearer token authentication.
 
+## Get Your Token
+
+1. Register at [platform.acedata.cloud](https://platform.acedata.cloud)
+2. Subscribe to a service (most include free quota)
+3. Go to your service's **Credentials** page and create an API token
+
 ## Setup
 
+Create a `.env` file in your project root:
+
 ```bash
-export ACEDATACLOUD_API_TOKEN="your-token-here"
+ACEDATACLOUD_API_TOKEN=your_token_here
 ```
 
-Get your token at [platform.acedata.cloud](https://platform.acedata.cloud):
+Then load it before making API calls:
 
-1. Register an account
-2. Browse and subscribe to a service (most include free quota)
-3. Create an API credential (token)
+```bash
+source .env
+```
+
+> **Agent usage:** If you're running skills through Claude Code or another AI agent, the agent will automatically `source .env` from the project root before calling any API.
+
+> **Important:** Add `.env` to your `.gitignore` — never commit tokens to version control.
 
 ## Usage
 
@@ -23,9 +35,14 @@ curl -X POST https://api.acedata.cloud/<endpoint> \
   -d '{ ... }'
 ```
 
-### Token Types
+## Token Types
+
+| Type | Scope | Use Case |
+|------|-------|----------|
+| **Service Token** | Single service | Default. Created per-subscription |
+| **Global Token** | All services | Create from the platform's global credentials page |
+
+## Gotchas
 
-| Type | Scope |
-|------|-------|
-| **Service Token** | Access to one subscribed service only |
-| **Global Token** | Access to all subscribed services |
+- Tokens are **service-scoped** by default — if you get a 401 on a different service, create a global token or a token for that specific service
+- Tokens do not expire, but can be revoked from the platform

package/skills/ai-chat/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Works as a drop-in replacement for the OpenAI SDK.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Works as a drop-in replacement for the OpenAI SDK.
 ---
 
 # AI Chat — Unified LLM Gateway

package/skills/face-transform/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md).
 ---
 
 # Face Transform

package/skills/fish-audio/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md).
 ---
 
 # Fish Audio — Voice & Audio Synthesis

package/skills/flux-image/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-flux-pro for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-flux-pro for tool-use.
 ---
 
 # Flux Image Generation

package/skills/google-search/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-serp for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-serp for tool-use.
 ---
 
 # Google Search (SERP)

package/skills/hailuo-video/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md).
 ---
 
 # Hailuo Video Generation

package/skills/kling-video/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md).
 ---
 
 # Kling Video Generation
@@ -20,7 +20,7 @@ Generate AI videos through AceDataCloud's Kuaishou Kling API.
 curl -X POST https://api.acedata.cloud/kling/videos \
   -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
   -H "Content-Type: application/json" \
-  -d '{"action": "text2video", "prompt": "a cat playing piano on a rooftop at sunset", "model": "kling-v2-5-turbo", "mode": "std", "duration": 5}'
+  -d '{"action": "text2video", "prompt": "a cat playing piano on a rooftop at sunset", "model": "kling-v3", "mode": "std", "duration": 5}'
 ```
 
 > **Async:** See [async task polling](../_shared/async-tasks.md). Poll via `POST /kling/tasks` with `{"task_id": "..."}`.
@@ -28,12 +28,15 @@ curl -X POST https://api.acedata.cloud/kling/videos \
 
 | Model | Quality | Best For |
 |-------|---------|----------|
-| `kling-v1` | Standard | Basic generation, lowest cost |
-| `kling-v1-6` | Improved | Better quality than v1 |
+| `kling-v3` | Latest | Best quality, flexible 3–15s duration, optional audio generation |
+| `kling-v3-omni` | Latest | Omni model with audio support, flexible 3–15s duration |
+| `kling-v2-6` | High | High-quality output with optional audio (pro mode) |
+| `kling-v2-5-turbo` | High + Fast | Best speed/quality trade-off |
 | `kling-v2-master` | High | High-quality output |
 | `kling-v2-1-master` | High | Improved v2 |
-| `kling-v2-5-turbo` | High + Fast | Best speed/quality trade-off (recommended) |
-| `kling-video-o1` | Premium | Highest quality |
+| `kling-v1-6` | Improved | Better quality than v1 |
+| `kling-v1` | Standard | Basic generation, lowest cost |
+| `kling-video-o1` | Premium | Highest quality (thinking model) |
 
 ## Quality Modes
 
@@ -51,7 +54,7 @@ POST /kling/videos
 {
   "action": "text2video",
   "prompt": "a futuristic city with flying cars",
-  "model": "kling-v2-5-turbo",
+  "model": "kling-v3",
   "mode": "std",
   "duration": 5,
   "aspect_ratio": "16:9"
@@ -69,7 +72,7 @@ POST /kling/videos
   "prompt": "the scene slowly comes alive with movement",
   "start_image_url": "https://example.com/scene.jpg",
   "end_image_url": "https://example.com/end-scene.jpg",
-  "model": "kling-v2-5-turbo",
+  "model": "kling-v3",
   "mode": "pro"
 }
 ```
@@ -107,7 +110,8 @@ POST /kling/motion
 | `action` | `"text2video"`, `"image2video"`, `"extend"` | Generation mode |
 | `model` | See models table | Model to use |
 | `mode` | `"std"`, `"pro"` | Quality mode |
-| `duration` | `5`, `10` | Duration in seconds |
+| `duration` | `5`, `10` (v3/v3-omni: `3`–`15`) | Duration in seconds |
+| `generate_audio` | `true`, `false` | Generate audio with video (v3, v3-omni, v2-6 pro only) |
 | `aspect_ratio` | `"16:9"`, `"9:16"`, `"1:1"` | Video aspect ratio |
 | `cfg_scale` | 0–1 | Prompt relevance strength |
 | `negative_prompt` | string | What to avoid in the video |
@@ -118,7 +122,8 @@ POST /kling/motion
 
 ## Gotchas
 
-- `duration` only supports `5` or `10` seconds
+- `duration` supports `5` or `10` seconds for most models; `kling-v3` and `kling-v3-omni` support flexible `3`–`15` seconds
+- `generate_audio` enables synchronized audio generation (supported by `kling-v3`, `kling-v3-omni`, and `kling-v2-6` in pro mode)
 - `end_image_url` is only for `image2video` action — it defines the last frame
 - Motion control (`/kling/motion`) is a separate endpoint from video generation
 - `pro` mode costs roughly 2x `std` mode but generates faster with better quality

package/skills/luma-video/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-luma for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-luma for tool-use.
 ---
 
 # Luma Video Generation

package/skills/midjourney-image/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-midjourney for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-midjourney for tool-use.
 ---
 
 # Midjourney Image Generation

package/skills/nano-banana-image/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-nano-banana for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-nano-banana for tool-use.
 ---
 
 # NanoBanana Image Generation

package/skills/producer-music/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md).
 ---
 
 # Producer Music Generation

package/skills/seedance-video/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-seedance for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-seedance for tool-use.
 ---
 
 # Seedance Video Generation

package/skills/seedream-image/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-seedream for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-seedream for tool-use.
 ---
 
 # Seedream Image Generation

package/skills/short-url/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-short-url for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-short-url for tool-use.
 ---
 
 # Short URL Service

package/skills/sora-video/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-sora for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-sora for tool-use.
 ---
 
 # Sora Video Generation

package/skills/suno-music/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-suno for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-suno for tool-use.
 ---
 
 # Suno Music Generation

package/skills/veo-video/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-veo for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-veo for tool-use.
 ---
 
 # Veo Video Generation

package/skills/wan-video/SKILL.md

@@ -5,7 +5,7 @@ license: Apache-2.0
 metadata:
   author: acedatacloud
   version: "1.0"
-compatibility: Requires ACEDATACLOUD_API_TOKEN environment variable. Optionally pair with mcp-wan for tool-use.
+compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (see _shared/authentication.md). Optionally pair with mcp-wan for tool-use.
 ---
 
 # Wan Video Generation