New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Voooai

by LeoYeAI in LeoYeAI/openclaw-master-skills

Short drama & webtoon production, text-to-image, image-to-image, storyboard design, text-to-video, image-to-video, video edit, style transfer, batch generation, music & soundtrack.

MIT-0Auto-check passedMedia & Creative

Install Voooai

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill voooai -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills voooai --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/voooai .claude/skills/voooai && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
voooai
GitHub stars
2.2k
Token cost
~4.8k tokens
SKILL.md length
1,329 words
Files
10 (incl. scripts)
Skills in repo
1,235
Repo updated
First seen
Licence
MIT-0

At a glance

Short drama & webtoon production, text-to-image, image-to-image, storyboard design, text-to-video, image-to-video, video edit, style transfer, batch generation, music & soundtrack.

  • Works in 12 steps: Overview → Authentication → Scope and Restrictions → …
  • : users request any visual
  • SKILL.md covers 1. Overview, 2. Authentication, 3. Scope and Restrictions and 4. Scope Boundaries, plus 3 more sections
  • Runs Python scripts from its folder; calls python3; reaches a.com; needs VOOOAI_ACCESS_KEY and INVALID_ACCESS_KEY

What it does

Voooai is an agent skill from LeoYeAI/openclaw-master-skills. Short drama & webtoon production, text-to-image, image-to-image, storyboard design, text-to-video, image-to-video, video edit, style transfer, batch generation, music & soundtrack. Describe your creative needs → backend generates workflow → execute → poll status → download results. Upload reference files (images, videos, audio) → workflow uses them as input for generation. If a node fails → retry that node with adjusted parameters. Complex tasks (short dramas, full ads) may take 3-5 min. Your role: relay user…

Its SKILL.md is about 4.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts (for example `_meta.json`, `scripts/_common.py` and `scripts/check_capabilities.py`).

It sits in Media & Creative, covering AI video generation, Comics and storyboards and Music and audio generation. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT-0.

When your agent uses it

  • : users request any visual
  • Audio content creation

Example prompts

  • “/voooai”

Requirements

  • Python 3
  • A credential in VOOOAI_ACCESS_KEY

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. Overview
  2. Authentication
  3. Scope and Restrictions
  4. Scope Boundaries
  5. Available Scripts
  6. Usage Patterns
  7. Typical Workflows
  8. User Interaction Guidelines
  9. Failure Handling and Retry
  10. Output Formats
  11. Core Principles
  12. Polling Strategy

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 8 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • a.com

    Also links to:

    • voooai.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • VOOOAI_ACCESS_KEY
    • INVALID_ACCESS_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Voooai loads about 4.8k tokens when it runs. Until then it costs about 225 tokens; SKILL.md has 1,329 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~225
When it runs · the whole SKILL.md, loaded when a task matches
~4.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT-0 licence (© LeoYeAI). 1,329 words, ~4,821 tokens.

Download SKILL.mdSave it as .claude/skills/voooai/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
voooai
description
Short drama & webtoon production, text-to-image, image-to-image, storyboard design, text-to-video, image-to-video, video edit, style transfer, batch generation, music & soundtrack. Describe your creative needs → backend generates workflow → execute → poll status → download results. Upload reference files (images, videos, audio) → workflow uses them as input for generation. If a node fails → retry that node with adjusted parameters. Complex tasks (short dramas, full ads) may take 3-5 min. Your role: relay user requests verbatim to backend. Backend AI (Analyst + Expert + Reviewer) handles all creative decisions. Do NOT rewrite prompts, decompose tasks, or construct workflows yourself — just forward and retrieve. Requires VOOOAI_ACCESS_KEY (creative operations only, no billing/admin). Use when: users request any visual or audio content creation, generation, editing, or modification.
version
1.0.2
author
VoooAI Team
license
MIT-0
user-invocable
true

VoooAI - NL2Workflow Creative Platform

1. Overview

VoooAI is a multi-media creative platform with 70+ built-in AI skills. The Agent acts as a relay (搬运工) — forwarding user requests to VoooAI's backend, which handles all creative decisions via its multi-role AI system (Analyst + Expert + Reviewer).

Core Capabilities:

  • Image Generation: Text-to-image, image-to-image, style transfer, concept art, storyboards
  • Video Generation: Text-to-video, image-to-video, video editing, digital human, AI anchor
  • Music Generation: Full songs, instrumentals, background music, soundtracks
  • Workflow Orchestration: Multi-step automated pipelines (script → storyboard → video + music)
1.1 Who Should Use This Skill?
User TypeUse Cases
Content CreatorsMarketing videos, social media content, product showcases, promotional materials
DesignersDesign assets, style variants, visual concepts, mood boards
StudiosMulti-step creative pipelines (script → storyboard → video + music)
BusinessesAdvertising, e-commerce product videos, corporate training content
Game DevelopersGame art assets, character concept art, cutscene animations
EducatorsTutorial videos, course illustrations, animated demonstrations
One-Person CompaniesFull-stack content creation (posters, videos, music — all-in-one)
1.2 When NOT to Use This Skill

This skill is exclusively for creative workflow operations. The following are explicitly out of scope:

  • ❌ User account management (registration, login, profile changes)
  • ❌ Billing, subscription, or payment operations
  • ❌ Admin panel or system configuration
  • ❌ Analytics, statistics, or usage data queries
  • ❌ Homepage or dashboard features
  • ❌ Direct parameter tuning (let the backend AI system handle optimization)

For these operations, direct users to https://voooai.com

2. Authentication

VOOOAI_ACCESS_KEY
  • Source: User's VoooAI account page at https://voooai.com
  • Format: vooai_ prefix + 40 random alphanumeric characters (46 total)
  • Example: vooai_abc123def456ghi789jkl012mno345pqrs678
Scope (What the Key Allows)
  • ✅ Capability discovery (check_capabilities.py)
  • ✅ File upload (upload_file.py)
  • ✅ Workflow generation (generate_workflow.py)
  • ✅ Workflow execution (execute_workflow.py, execute_single_node.py)
  • ✅ Status query (get_status.py)
  • ✅ Result download (download_results.py)
Scope (What the Key DOES NOT Allow)
  • ❌ Billing / payment / subscription management
  • ❌ Admin / system administration
  • ❌ User account settings / profile changes
  • ❌ Analytics / statistics access
Storage
  • Environment variable: export VOOOAI_ACCESS_KEY="vooai_..."
  • Never hardcode in source code

3. Scope and Restrictions

Allowed Operations
  • Capability discovery, file upload, workflow generation/execution, status query, result download
Forbidden Operations (Explicit Deny List)

If user requests these, inform them to visit voooai.com directly:

  • ❌ Homepage / dashboard features
  • ❌ User registration / login / authentication
  • ❌ Subscription / payment / billing management
  • ❌ Admin panel / system administration
  • ❌ Analytics / statistics
  • ❌ Account settings / profile management

Content Moderation (Explicit Deny List)

  • ❌ Creating deepfakes or non-consensual facial/voice mimicry
  • ❌ Impersonating real individuals without explicit consent
  • ❌ Generating political disinformation or election interference content

Content Safety Note: Digital human and talking-head features are intended for legitimate creative use cases (marketing presenters, educational hosts, fictional characters). Users must label AI-generated content per applicable synthetic media regulations.

4. Scope Boundaries

This section provides a clear table-based definition of what this skill can and cannot do.

Supported Operations
OperationSupportedScriptExample
Capability discovery✅check_capabilities.pyCheck available skills and points balance
File upload✅upload_file.pyUpload reference image/video/audio (max 200MB)
Workflow generation✅generate_workflow.pyGenerate workflow from natural language description
Workflow execution✅execute_workflow.pyRun generated workflow
Single node execution✅execute_single_node.pyRetry specific failed node
Status query✅get_status.pyCheck execution progress
Result download✅download_results.pyDownload generated files to local
Forbidden Operations
OperationReason
User authentication / registrationOut of scope — handled by web frontend
Payment / billing / subscriptionOut of scope — user manages directly at voooai.com
Account settings / profileOut of scope — user manages directly
Analytics / usage statisticsOut of scope — not creative workflow
Admin panel / system configOut of scope — admin only
Homepage / dashboard featuresOut of scope — not workflow related
Direct API calls bypassing scriptsSecurity risk — use provided scripts only
Manual workflow JSON constructionQuality risk — use generate_workflow.py only
Deepfakes / non-consensual facial or voice mimicryContent safety — violates ethical guidelines
Impersonating real individuals without consentContent safety — privacy and legal concerns
Political disinformation / election interferenceContent safety — harmful content prohibition

5. Available Scripts

All scripts located at {baseDir}/scripts/. Required env: VOOOAI_ACCESS_KEY.

check_capabilities.py

Discover platform capabilities and points balance.

bash
python3 {baseDir}/scripts/check_capabilities.py
python3 {baseDir}/scripts/check_capabilities.py --summary
upload_file.py

Upload image/video/audio file (max 200MB).

bash
python3 {baseDir}/scripts/upload_file.py /path/to/file.png
python3 {baseDir}/scripts/upload_file.py /path/to/video.mp4
  • Supported: jpg, png, webp, gif, mp4, mov, avi, mkv, webm, mp3, wav, flac, m4a
generate_workflow.py

Generate workflow from natural language description.

bash
python3 {baseDir}/scripts/generate_workflow.py "生成一个咖啡产品宣传视频"
python3 {baseDir}/scripts/generate_workflow.py "基于这张图生成视频" --reference-urls https://example.com/ref.jpg
python3 {baseDir}/scripts/generate_workflow.py "生成分镜图" --skill-id storyboard-basic
python3 {baseDir}/scripts/generate_workflow.py "测试描述" --analyze-only  # analysis only
execute_workflow.py

Execute a generated workflow.

bash
python3 {baseDir}/scripts/execute_workflow.py '{"nodes": [...], "connections": [...]}'
python3 {baseDir}/scripts/execute_workflow.py /path/to/workflow.json
cat workflow.json | python3 {baseDir}/scripts/execute_workflow.py --from-stdin
python3 {baseDir}/scripts/execute_workflow.py workflow.json --set-param node_1.prompt="新提示词"
execute_single_node.py

Execute/retry a single node (for debugging or partial retry).

bash
python3 {baseDir}/scripts/execute_single_node.py workflow.json --node-id node_1
cat workflow.json | python3 {baseDir}/scripts/execute_single_node.py --from-stdin --node-id node_2
python3 {baseDir}/scripts/execute_single_node.py workflow.json --node-id node_1 --set-param node_1.prompt="修改后的提示词"
get_status.py

Query execution status.

bash
python3 {baseDir}/scripts/get_status.py exec_abc123                            # single query
python3 {baseDir}/scripts/get_status.py exec_abc123 --poll                     # poll until complete
python3 {baseDir}/scripts/get_status.py exec_abc123 --poll --timeout 600       # custom timeout
download_results.py

Download execution results to local.

bash
python3 {baseDir}/scripts/download_results.py exec_abc123
python3 {baseDir}/scripts/download_results.py exec_abc123 --output-dir ~/Downloads/project
python3 {baseDir}/scripts/download_results.py exec_abc123 --prefix "storyboard"
python3 {baseDir}/scripts/download_results.py exec_abc123 --no-download        # list URLs only
python3 {baseDir}/scripts/download_results.py --urls https://a.com/1.png       # direct URL download

6. Usage Patterns

This section describes common trigger patterns to help the Agent understand when and how to invoke VoooAI.

Pattern 1: Direct Media Generation

User expressions:

  • "Generate an image of a sunset over mountains"
  • "画一只戴眼镜的猫"
  • "做个海报宣传我的产品"
  • "Create a video of a dancing robot"
  • "帮我做首轻松的背景音乐"

Execution flow:

check_capabilities → generate_workflow → execute_workflow → get_status (poll) → download_results
Pattern 2: Reference-Based Creation

User expressions:

  • "Based on this image, generate a video"
  • "把这张图变成动画"
  • "用这首歌做个MV"
  • "Convert this sketch to a realistic image"
  • "参考这个风格做一组产品图"

Execution flow:

upload_file → generate_workflow (with --reference-urls) → execute_workflow → get_status (poll) → download_results
Pattern 3: Complex Multi-Step Workflows

User expressions:

  • "Create a short drama about a detective"
  • "帮我做个产品广告，从脚本到成片"
  • "一句话生成短剧"
  • "Make a complete promotional video with storyboard and music"
  • "从剧本到分镜到视频帮我全流程做出来"

Execution flow:

generate_workflow (backend handles decomposition) → execute_workflow → get_status (poll, may take 3-5+ min) → download_results
Pattern 4: Failure Recovery & Retry

User expressions:

  • "Retry with different parameters"
  • "这个节点重新执行一下"
  • "把提示词改一下再试"
  • "换个风格重新生成"

Execution flow:

get_status (identify failed node) → execute_single_node (with --set-param if needed) → get_status (poll) → download_results
Pattern 5: Exploration & Discovery

User expressions:

  • "What can you generate?"
  • "你能做什么？"
  • "有哪些创作能力？"
  • "Show me available AI skills"
  • "我还有多少积分？"

Execution flow:

check_capabilities → present results to user
Show full SKILL.md (530 more words)Show less

7. Typical Workflows

Scenario 1: Basic Image/Video Generation
bash
# 1. Check capabilities and points
python3 {baseDir}/scripts/check_capabilities.py --summary

# 2. Generate workflow (user confirms points_cost before proceeding)
python3 {baseDir}/scripts/generate_workflow.py "一个宇航员在月球上弹吉他"
# → Review estimated_points, ask user to confirm

# 3. Execute workflow
python3 {baseDir}/scripts/execute_workflow.py '<template_data_json>'

# 4. Poll status
python3 {baseDir}/scripts/get_status.py EXEC_ID --poll

# 5. Download results
python3 {baseDir}/scripts/download_results.py EXEC_ID --output-dir ./output
Scenario 2: With Reference Media (URL)
bash
python3 {baseDir}/scripts/generate_workflow.py "根据这张图生成视频" \
  --reference-urls https://example.com/reference.jpg
# Then execute, poll, download as above
Scenario 3: With Local File Upload
bash
# 1. Upload local file first
python3 {baseDir}/scripts/upload_file.py /path/to/reference.png
# → Returns file_url

# 2. Generate workflow with uploaded URL
python3 {baseDir}/scripts/generate_workflow.py "基于这张图生成视频" \
  --reference-urls <file_url_from_upload>
# Then execute, poll, download as above
Scenario 4: Failed Node Retry
bash
# 1. Check which node failed
python3 {baseDir}/scripts/get_status.py EXEC_ID
# → Identify failed node_id from node_statuses

# 2. Retry single node (optionally adjust params)
python3 {baseDir}/scripts/execute_single_node.py workflow.json \
  --node-id failed_node_id \
  --set-param failed_node_id.some_param="adjusted_value"

# 3. Poll new execution
python3 {baseDir}/scripts/get_status.py NEW_EXEC_ID --poll
Scenario 5: Multi-Step Creative Pipeline (Short Drama / Product Ad)
bash
# Complex workflow: script → storyboard → video + music (all handled by backend)
# Example: "帮我做个咖啡产品广告，从脚本到成片"

# 1. Check capabilities and points (complex workflows cost more)
python3 {baseDir}/scripts/check_capabilities.py --summary

# 2. Generate multi-step workflow (backend auto-decomposes)
python3 {baseDir}/scripts/generate_workflow.py "制作一个30秒的咖啡产品广告，包含脚本、分镜、视频和背景音乐"
# → Backend returns multi-node workflow (script → storyboard → video → music → composite)
# → Review estimated_points (typically 80-200+ for complex pipelines), ask user to confirm

# 3. Execute full pipeline
python3 {baseDir}/scripts/execute_workflow.py '<template_data_json>'

# 4. Poll status (complex workflows take 3-5+ minutes)
python3 {baseDir}/scripts/get_status.py EXEC_ID --poll --timeout 600

# 5. Download all outputs (storyboard images, video clips, music, final composite)
python3 {baseDir}/scripts/download_results.py EXEC_ID --output-dir ./output/product_ad

8. User Interaction Guidelines

Points Confirmation (CRITICAL)

When generate_workflow.py returns points_warning or estimated_points:

  1. MUST show estimated cost to user before execution
  2. MUST wait for user confirmation
  3. NEVER auto-execute when points_warning exists

Example interaction:

Agent: "This workflow will cost approximately 45 points. You have 50 points available. Proceed? (yes/no)"
User: "yes"
Agent: [Then execute]
Multiple Options

When backend returns multiple plans or options:

  • Present all options to user with clear descriptions
  • Let user choose, do not auto-select
Ambiguous Parameters

When user description is vague:

  • Ask clarifying questions about key parameters (duration, style, resolution)
  • Do not guess or fill in creative details yourself
Post-Failure Decisions

When execution fails:

  • Present failure reason clearly
  • Offer options: retry, adjust parameters, change engine, or abort
  • Let user decide next action
Core Principle

Agent MUST NOT make any points-consuming decision on behalf of the user.

9. Failure Handling and Retry

Diagnosis Steps
  1. Run get_status.py EXEC_ID to get detailed error info
  2. Check failed_nodes list and error_message
  3. Review node_statuses for per-node status
Retry Strategies
StrategyWhen to UseCommand
Single-node retryOne node failed, others succeededexecute_single_node.py --node-id <failed_node>
Parameter adjustmentEngine rejected paramsAdd --set-param to modify
Full retryMultiple nodes failed or workflow errorRe-run execute_workflow.py
Common Failure Scenarios
Error CodeCauseResolution
INSUFFICIENT_POINTSNot enough creditsUser adds credits at voooai.com/subscription
ENGINE_TIMEOUTEngine took too longRetry, or try different engine
INVALID_PARAMSBad parametersAdjust params with --set-param
CONTENT_BLOCKEDContent safety filterModify description to comply with guidelines
ENGINE_UNAVAILABLEEngine temporarily downWait and retry, or use alternative engine
Known Limitations
  • Status synchronization may lag — poll with patience
  • Complex workflows (short dramas) may take 3-5+ minutes
  • After 5-minute timeout, tell user to check results at voooai.com

10. Output Formats

check_capabilities.py: {success, points_balance, points_warning, available_engines, available_skills}

generate_workflow.py: {success, template_data, explanation, metadata: {node_count, engine_nodes, estimated_points}, points_warning}

execute_workflow.py: {success, execution_id, status, message}

get_status.py: {success, execution_id, status, progress, result_urls[]}
Status values: pending | running | completed | failed

download_results.py: {success, output_dir, downloaded_files[], total_count}

11. Core Principles

Agent is a Relay (搬运工)
  • Forward user descriptions verbatim to the API
  • NEVER rewrite, expand, embellish, or translate user prompts
  • NEVER decompose tasks yourself (send "make 5 episodes" as ONE request)
  • NEVER construct workflow JSON manually — always use generate_workflow.py
Trust the Backend

VoooAI's PlannerAgent (Analyst + Expert + Reviewer) handles:

  • Task decomposition and planning
  • Engine/model selection
  • Prompt engineering and optimization
  • Workflow structure design
Points Awareness
  • ALWAYS check points_warning before execution
  • ALWAYS inform user of estimated cost
  • ALWAYS get user confirmation for costly operations
Scope Awareness
  • ONLY operate workflow-related features
  • NEVER attempt homepage, billing, admin, or account operations
  • If user requests out-of-scope operation → direct them to voooai.com

12. Polling Strategy

  • Interval: 10 seconds (do not poll more frequently)
  • Timeout: 300 seconds (5 minutes default)
  • Completion: status: "completed" → results in outputs
  • Failure: status: "failed" → check error_message
  • Post-timeout: Tell user to check at https://voooai.com

13. Error Reference

HTTP Codes: 400 (bad request) | 401 (unauthorized) | 403 (forbidden) | 429 (rate limit) | 500 (server error)

Error Codes:

  • INVALID_ACCESS_KEY — Key must start with vooai_
  • INSUFFICIENT_POINTS — Add credits at voooai.com/subscription
  • MEMBERSHIP_REQUIRED — Engine requires higher tier
  • RATE_LIMIT_EXCEEDED — Wait and retry
  • ENGINE_UNAVAILABLE — Try alternative engine

Website: https://voooai.com | Support: support@voooai.com

© LeoYeAI, MIT-0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (scripts) in skills/voooai of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • _meta.json
  • scripts/_common.py
  • scripts/check_capabilities.py
  • scripts/download_results.py
  • scripts/execute_single_node.py
  • scripts/execute_workflow.py
  • scripts/generate_workflow.py
  • scripts/get_status.py
  • scripts/upload_file.py

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Voooai next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Voooai compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Voooai this skillLeoYeAI/openclaw-master-skills2.2k—~4.8kAutomated safety check: PassMIT-0
Motion Graphics Music Videomakevoid/motion-graphics-music-video-skill143—~3.3kAutomated safety check: PassMIT
Music VideoNoizAI/skills526—~1.5kAutomated safety check: PassNone
WorkrallyTencent/workrally166—~3.7kAutomated safety check: PassMIT-0
RunninghubHM-RunningHub/OpenClaw_RH_Skills142—~1.6kAutomated safety check: PassApache-2.0
Character Design with genmediafal-ai-community/skills251—~1.3kAutomated safety check: PassNone

Similar skills

  • Motion Graphics Music Video

    makevoid/motion-graphics-music-video-skill

    Create and revise animated character music videos from a supplied song and creative prompt, with researched storyboards, Fal character and video generation, p5 motion graphics, audio editing, and…

    143 GitHub stars~3.3k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed

  • Music Video

    NoizAI/skills

    Build a music video from an existing song and lyrics, either as p5.js/p5.brush animation or by assembling local images and clips.

    526 GitHub stars~1.5k tokensUpdated 12 days ago
    Media & CreativeAuto-check passed

  • Workrally

    Tencent/workrally

    WorkRally CLI (workrally) — 面向 AI Agent 的 AIGC 漫剧视频创作全流程工具集。支持 AI 生图、AI 生视频、视频提示词优化、画布生音频/音乐、混元 3D 模型生成、AI 生音频、项目/剧集/场次/分镜的完整 CRUD、资产库、媒资管理、无限画布、文件上传下载等。Use when user asks to generate images…

    166 GitHub stars~3.7k tokensUpdated 10 days ago
    Media & CreativeAuto-check passed

  • Runninghub

    HM-RunningHub/OpenClaw_RH_Skills

    Generate images, videos, audio, and 3D models via RunningHub API (420 endpoints) and run any RunningHub AI Application (custom ComfyUI workflow) by webappId.

    142 GitHub stars~1.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

  • Character Design with genmedia

    fal-ai-community/skills

    Builds consistent characters, reference and expression sheets, outfit variations and character-to-video shots with the genmedia CLI while keeping identity stable.

    251 GitHub stars~1.3k tokensUpdated 11 days ago
    Media & CreativeAuto-check passed

  • Professional Media Prompts

    agentscope-ai/QwenPaw

    Compiles production-grade prompts for character identity boards, cinematic storyboards and reference-to-video generation, keeping characters and shots consistent.

    36k GitHub stars~2k tokensUpdated today
    Media & CreativeAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,235 skills in this repo

  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes

  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed

  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed

  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed

  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes

  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Voooai

What does Voooai do?

Short drama & webtoon production, text-to-image, image-to-image, storyboard design, text-to-video, image-to-video, video edit, style transfer, batch generation, music & soundtrack. Voooai is an agent skill from LeoYeAI/openclaw-master-skills. Short drama & webtoon production, text-to-image, image-to-image, storyboard design, text-to-video, image-to-video, video edit, style transfer, batch generation, music & soundtrack.

When should I use Voooai?

Voooai fits situations like: : users request any visual; audio content creation.

How do I install Voooai in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill voooai -a claude-code`. Or copy the skill folder (skills/voooai in LeoYeAI/openclaw-master-skills) into .claude/skills/voooai in your project. Claude Code loads it when a task matches its description.

How do I install Voooai in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill voooai -a codex`. Or copy the skill folder (skills/voooai in LeoYeAI/openclaw-master-skills) into .agents/skills/voooai in your project. Codex loads it when a task matches its description.

Can I use Voooai in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill voooai -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/voooai, .gemini/skills/voooai, .github/skills/voooai and .opencode/skills/voooai in your project.

What does Voooai need to run?

Going by SKILL.md and its folder, Voooai needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named VOOOAI_ACCESS_KEY and INVALID_ACCESS_KEY. Our summary lists: Python 3; A credential in VOOOAI_ACCESS_KEY.

Does Voooai access the network?

SKILL.md names 2 domains. In commands or code: a.com; the agent is likely to contact it when it follows the instructions. As links in the text: voooai.com. This is read from the text; nothing was executed.

Is Voooai safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Voooai use?

Voooai is published under the MIT-0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Voooai use?

About 4.8k tokens (SKILL.md is roughly 19k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Voooai?

Skills that share tags, products or a category with Voooai: Motion Graphics Music Video (makevoid/motion-graphics-music-video-skill, 143 stars), Music Video (NoizAI/skills, 526 stars), Workrally (Tencent/workrally, 166 stars) and Runninghub (HM-RunningHub/OpenClaw_RH_Skills, 142 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Voooai?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.