AceDataCloud Agent Skills

Agent Skills for AceDataCloud AI services — music, image, video generation, LLM chat, web search, and more.

Compatible with 30+ AI coding agents via the agentskills.io open standard: Claude Code, GitHub Copilot, Gemini CLI, OpenAI Codex, Cursor, Roo Code, Goose, and more.

Available Skills (30)

AI Music & Audio

| Skill | Description | |-------|-------------| | suno-music | Generate AI music, lyrics, covers, and vocal extraction with Suno | | producer-music | Generate music, covers, extend tracks, swap vocals with Producer | | fish-audio | Text-to-speech and voice synthesis with Fish Audio |

AI Image Generation

| Skill | Description | |-------|-------------| | midjourney-image | Generate, edit, blend, describe, and upscale images with Midjourney | | flux-image | Generate and edit images with Flux (Black Forest Labs) | | seedream-image | Generate and edit images with ByteDance Seedream | | nano-banana-image | Generate and edit images with Google Gemini (NanoBanana) |

AI Video Generation

| Skill | Description | |-------|-------------| | luma-video | Generate videos with Luma Dream Machine | | sora-video | Generate videos with OpenAI Sora | | veo-video | Generate videos with Google Veo (native audio) | | kling-video | Generate videos with Kuaishou Kling (motion control) | | hailuo-video | Generate videos with Hailuo / MiniMax | | seedance-video | Generate dance/motion videos with ByteDance Seedance |

AI Chat & Tools

| Skill | Description | |-------|-------------| | ai-chat | Unified LLM gateway — GPT, Claude, Gemini, Kimi, Grok (50+ models) | | google-search | Search the web, images, news, maps, places, and videos via Google | | face-transform | Face analysis, beautification, age/gender transform, swap, cartoon | | short-url | Create and manage short URLs | | onepage-pdf | Convert an HTML page into one tall single-page PDF — no pagination breaks (local, no token) | | acedatacloud-api | API usage guide — authentication, SDKs, error handling |

Connectors

These skills drive third-party connectors users wire up at auth.acedata.cloud/user/connections. Each declares the OAuth / BYOC connection it needs in connections: frontmatter; the aichat2 runtime injects the matching access token into the sandbox before the skill's Bash calls run.

| Skill | Description | Connection | |-------|-------------|------------| | github | GitHub issues, pull requests, repos, code search, and Actions via gh CLI | github | | gitlab | GitLab issues, MRs, projects, pipelines via the glab CLI | gitlab | | google-drive | List, search, and read Google Drive files via the Drive v3 REST API | google/drive | | google-gmail | Read, search, and triage Gmail messages via the Gmail v1 REST API | google/gmail | | google-calendar | Read calendar events, agenda, and free-busy windows via Calendar v3 | google/calendar | | google-tasks | List and inspect Google Tasks via the Tasks v1 REST API | google/tasks | | microsoft-onedrive | List and read OneDrive files via the Microsoft Graph API | microsoft/onedrive | | microsoft-outlook | Read Outlook mail, calendar events, and contacts via Microsoft Graph | microsoft/outlook | | notion | Read and search Notion pages, databases, and blocks | notion | | slack | Read Slack channels, messages, and user info via Web API | slack | | wechat-official-account | Manage WeChat MP — drafts, publishing, materials, user tags | wechat (BYOC) |

Prerequisites

Get your API token at platform.acedata.cloud:

1. Register an account
2. Browse and subscribe to a service (most have free quota)
3. Create an API credential (token)

export ACEDATACLOUD_API_TOKEN="your-token-here"

Quick Install

One command to install skills into your project — works with all agents:

# Install all skills (for any agentskills.io-compatible agent)
npx skills add acedatacloud/skills --skill '*' --yes

# Install specific skills only
npx skills add acedatacloud/skills --skill suno-music --skill midjourney-image --yes

The skills CLI auto-detects your agent and installs to the correct path.

Usage by Platform

Claude Code

Option A: skills CLI (recommended)

# Install all skills for Claude Code
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

Skills are symlinked into .claude/skills/ and auto-discovered by Claude Code.

Option B: Plugin Marketplace

/plugin marketplace add acedatacloud/skills
/plugin install acedatacloud-ai-media@acedatacloud-skills
/plugin install acedatacloud-ai-tools@acedatacloud-skills

Option C: npm package

npx @acedatacloud/skills install --target .claude/skills

Option D: Manual copy

git clone https://github.com/AceDataCloud/Skills.git
cp -r Skills/skills/* .claude/skills/

GitHub Copilot

npx skills add acedatacloud/skills --skill '*' -a github-copilot --yes

Gemini CLI

npx skills add acedatacloud/skills --skill '*' -a gemini-cli --yes

OpenAI Codex

npx skills add acedatacloud/skills --skill '*' -a codex --yes

Cursor

npx skills add acedatacloud/skills --skill '*' -a cursor --yes

Roo Code

npx skills add acedatacloud/skills --skill '*' -a roo --yes

Goose

npx skills add acedatacloud/skills --skill '*' -a goose --yes

Windsurf

npx skills add acedatacloud/skills --skill '*' -a windsurf --yes

Cline

npx skills add acedatacloud/skills --skill '*' -a cline --yes

Other Agents

The skills CLI supports 40+ agents. Use npx skills add --help to see all options, or install to the universal .agents/skills/ path:

npx skills add acedatacloud/skills --skill '*' --yes

Pairing Skills with MCP Servers

Skills provide knowledge (when to use, parameters, gotchas). MCP servers provide tools (executable functions the agent can call). Together they give the best experience.

| Skill | MCP Server | Install | Hosted Endpoint | |-------|-----------|---------|-----------------| | suno-music | mcp-suno | pip install mcp-suno | https://suno.mcp.acedata.cloud/mcp | | midjourney-image | mcp-midjourney | pip install mcp-midjourney | https://midjourney.mcp.acedata.cloud/mcp | | google-search | mcp-serp | pip install mcp-serp | https://serp.mcp.acedata.cloud/mcp | | flux-image | mcp-flux-pro | pip install mcp-flux-pro | https://flux.mcp.acedata.cloud/mcp | | luma-video | mcp-luma | pip install mcp-luma | https://luma.mcp.acedata.cloud/mcp | | sora-video | mcp-sora | pip install mcp-sora | https://sora.mcp.acedata.cloud/mcp | | veo-video | mcp-veo | pip install mcp-veo | https://veo.mcp.acedata.cloud/mcp | | seedream-image | mcp-seedream | pip install mcp-seedream | https://seedream.mcp.acedata.cloud/mcp | | seedance-video | mcp-seedance | pip install mcp-seedance | https://seedance.mcp.acedata.cloud/mcp | | nano-banana-image | mcp-nano-banana | pip install mcp-nano-banana | https://nano-banana.mcp.acedata.cloud/mcp | | short-url | mcp-shorturl | pip install mcp-shorturl | https://short-url.mcp.acedata.cloud/mcp | | wan-video | mcp-wan | pip install mcp-wan | https://wan.mcp.acedata.cloud/mcp |

Using hosted MCP endpoints (no local install needed):

{
  "mcpServers": {
    "suno": {
      "url": "https://suno.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
      }
    }
  }
}

Quick Example

Ask your AI agent:

"Generate a lo-fi hip hop track with rain sounds using Suno"

The agent will:

1. Read the suno-music skill to understand the API
2. Call the Suno MCP server (if configured) or guide you through the API call
3. Handle task polling until the music is ready
4. Return the audio URL

Contributing

We welcome contributions! To add a new skill:

1. Create a directory under skills/ matching the skill name
2. Add a SKILL.md following the Agent Skills specification
3. Use the template as a starting point
4. Reference shared files (../_shared/authentication.md, ../_shared/async-tasks.md, ../_shared/mcp-servers.md) instead of duplicating common sections
5. Submit a pull request — CI will validate your skill format

Note: .agents/skills/ and .github/skills/ are symlinks to skills/ — do not modify files via those paths.

License

Apache-2.0