Generate AI videos and images using Alibaba's Wan 2.6 and Wan 2.5 — featuring text-to-video, image-to-video, video-to-video, text-to-image, and image editing with up to 1080p resolution, 15-second…

MITAuto-check passedMedia & Creative

Install Wan

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

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

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills wan --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/alibaba-wan .claude/skills/wan && 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
wan
GitHub stars
2.2k
Token cost
~4.5k tokens
SKILL.md length
1,353 words
Files
4 (incl. scripts)
Skills in repo
972
Repo updated
First seen
Licence
MIT

At a glance

Generate AI videos and images using Alibaba's Wan 2.6 and Wan 2.5 — featuring text-to-video, image-to-video, video-to-video, text-to-image, and image editing with up to 1080p resolution, 15-second…

  • Works in 3 steps: Sign up at https://www.atlascloud.ai → Console → API Keys → Create new key → Set env: export…
  • The user wants to generate AI videos
  • SKILL.md covers Key Capabilities, Setup, Script Usage and Pricing, plus 3 more sections
  • Runs Python scripts from its folder; calls curl and python; reaches api.atlascloud.ai; needs ATLASCLOUD_API_KEY

What it does

Wan is an agent skill from LeoYeAI/openclaw-master-skills. Generate AI videos and images using Alibaba's Wan 2.6 and Wan 2.5 — featuring text-to-video, image-to-video, video-to-video, text-to-image, and image editing with up to 1080p resolution, 15-second duration, multi/single camera shot types, audio-guided generation, and prompt expansion. Supports 18 model variants across 2 generations. Available via Atlas Cloud API at up to 30% off standard pricing. Use this skill whenever the user wants to generate AI videos, create video clips, animate images, edit videos…

Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `_meta.json`, `scripts/generate_image.py` and `scripts/generate_video.py`).

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

When your agent uses it

  • The user wants to generate AI videos
  • Create video clips
  • Generate images
  • Users ask to create product demos

Example prompts

  • “/wan”

Requirements

  • Python 3
  • A credential in ATLASCLOUD_API_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Sign up at https://www.atlascloud.ai
  2. Console → API Keys → Create new key
  3. Set env: export ATLASCLOUD_API_KEY="your-key"

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

    Shell commands in SKILL.md call:

    • curl
    • python

    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:

    • api.atlascloud.ai

    Also links to:

    • atlascloud.ai
    • fal.ai

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

  • Credentials

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

    • ATLASCLOUD_API_KEY

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

Context cost

Wan loads about 4.5k tokens when it runs. Until then it costs about 212 tokens; SKILL.md has 1,353 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~212
When it runs · the whole SKILL.md, loaded when a task matches
~4.5k

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 licence (© LeoYeAI). 1,353 words, ~4,514 tokens.

Download SKILL.mdSave it as .claude/skills/wan/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
wan
description
Generate AI videos and images using Alibaba's Wan 2.6 and Wan 2.5 — featuring text-to-video, image-to-video, video-to-video, text-to-image, and image editing with up to 1080p resolution, 15-second duration, multi/single camera shot types, audio-guided generation, and prompt expansion. Supports 18 model variants across 2 generations. Available via Atlas Cloud API at up to 30% off standard pricing. Use this skill whenever the user wants to generate AI videos, create video clips, animate images, edit videos, generate images, edit photos, or mentions Wan, Alibaba video, Tongyi video, Wanx, or Wan 2.6/2.5. Also trigger when users ask to create product demos, marketing videos, social media reels, animated scenes, cinematic clips, video-to-video transfers, character-consistent video edits, multi-camera shots, or any visual content using AI.
source
https://github.com/AtlasCloudAI/nano-banana-2-skill
homepage
https://github.com/AtlasCloudAI/nano-banana-2-skill

Wan 2.6 & 2.5 — AI Video & Image Generation by Alibaba

Generate AI videos and images using Alibaba's Wan 2.6 and Wan 2.5 — featuring text-to-video, image-to-video, video-to-video, text-to-image, and image editing with up to 1080p resolution, 15-second duration, multi/single camera modes, audio-guided generation, and built-in prompt expansion.

Wan 2.6 is the latest flagship model with cinematic motion quality, multi-camera shot types, audio URL input for guided generation, and video-to-video transfer with character-level prompt control. Wan 2.5 offers a cost-effective alternative with 480p support and Flash variants for rapid prototyping.

Data usage note: This skill sends text prompts, image URLs, audio URLs, and video files to the Atlas Cloud API (api.atlascloud.ai) for generation. No data is stored locally beyond the downloaded output files. API usage incurs charges based on resolution, duration, and model selected.


Key Capabilities

  • Text-to-Video — Generate video clips from text descriptions with optional audio (2.6 / 2.5)
  • Image-to-Video — Animate still images into dynamic video (2.6 / 2.5)
  • Video-to-Video — Transfer style or replace characters in existing videos using characterX prompt notation (2.6)
  • Text-to-Image — Generate images from text descriptions, 27 preset sizes (2.6)
  • Image Editing — Edit images with prompt-based instructions, up to 4 reference images (2.6)
  • Audio-Guided Generation — Provide an audio URL to guide video generation with synchronized sound (2.6)
  • Multi/Single Camera — multi_camera for dynamic shots, single_camera for stable framing (2.6)
  • Prompt Expansion — Built-in prompt optimization for better results
  • Up to 1080p — Resolutions: 480p, 720p, 1080p
  • Up to 15s — Duration: 5/10/15 seconds (2.6), 5/10 seconds (2.5)
  • Flash Variants — Fast, budget-friendly generation for drafts (2.6 I2V Flash, 2.5 Fast)

Setup

  1. Sign up at https://www.atlascloud.ai
  2. Console → API Keys → Create new key
  3. Set env: export ATLASCLOUD_API_KEY="your-key"

The API key is tied to your Atlas Cloud account and its pay-as-you-go balance. All usage is billed to this account. Atlas Cloud does not currently support scoped keys — the key grants access to all models available on your account.


Script Usage

This skill includes Python scripts for both video and image generation. Zero external dependencies required.

List available models
bash
python scripts/generate_video.py list-models
python scripts/generate_image.py list-models
Generate a video
bash
python scripts/generate_video.py generate \
  --model "alibaba/wan-2.6/text-to-video" \
  --prompt "Your prompt here" \
  --output ./output \
  duration=5
Generate an image
bash
python scripts/generate_image.py generate \
  --model "alibaba/wan-2.6/text-to-image" \
  --prompt "Your prompt here" \
  --output ./output
Image-to-video
bash
python scripts/generate_video.py generate \
  --model "alibaba/wan-2.6/image-to-video" \
  --image "https://example.com/photo.jpg" \
  --prompt "Animate this scene" \
  --output ./output \
  resolution=1080p duration=5
Upload a local file
bash
python scripts/generate_video.py upload ./local-file.jpg

Run python scripts/generate_video.py generate --help or python scripts/generate_image.py generate --help for all options. Extra model params can be passed as key=value.


Pricing

Wan 2.6 — Video Models (per second, by resolution)

All video prices are per second of video generated. Atlas Cloud pricing varies by resolution.

Text-to-Video & Video-to-Video
Resolutionfal.aiAtlas CloudSavings
480p-$0.04/s-
720p$0.10/s$0.08/s20% off
1080p$0.15/s$0.12/s20% off
Image-to-Video
Resolutionfal.aiAtlas CloudSavings
720p$0.10/s$0.10/s-
1080p$0.15/s$0.15/s-
Image-to-Video Flash
ResolutionAtlas Cloud
All$0.018/s
Wan 2.6 — Image Models (per image)
ModelOriginalAtlas CloudSavings
Text-to-Image$0.03$0.02130% off
Image Edit$0.035$0.02140% off
Wan 2.5 — Video Models (per second, flat rate)
ModelAtlas CloudDuration
Text-to-Video$0.035/s5/10 seconds
Image-to-Video$0.035/s5/10 seconds

fal.ai pricing sourced from fal.ai/models/wan.


Available Models

Wan 2.6 Video
Model IDTypeResolutionDuration
alibaba/wan-2.6/text-to-videoText-to-Video480p–1080p5/10/15s
alibaba/wan-2.6/image-to-videoImage-to-Video720p–1080p5/10/15s
alibaba/wan-2.6/image-to-video-flashImage-to-Video (Fast)720p–1080p5/10/15s
alibaba/wan-2.6/video-to-videoVideo-to-Video480p–1080p5/10s
Wan 2.6 Image
Model IDTypeMax Size
alibaba/wan-2.6/text-to-imageText-to-Image2184×936
alibaba/wan-2.6/image-editImage Editing24 presets
Wan 2.5 Video
Model IDTypeResolutionDuration
alibaba/wan-2.5/text-to-videoText-to-Video480p–1080p5/10s
alibaba/wan-2.5/image-to-videoImage-to-Video480p–1080p5/10s

Parameters

Wan 2.6 — Text-to-Video
ParameterTypeRequiredDefaultDescription
promptstringYes-Video description
negative_promptstringNo-What to exclude from the video
sizestringNo1280*720Output size (see Size Options below)
durationintegerNo55, 10, or 15 seconds
shot_typestringNo-multi_camera for dynamic shots, single_camera for stable framing
audiostringNo-Audio URL to guide generation with synchronized sound
generate_audiobooleanNofalseGenerate synchronized audio
enable_prompt_expansionbooleanNofalseExpand prompt for better results
seedintegerNorandomFor reproducible results
Wan 2.6 — Image-to-Video

Same as text-to-video (without size), plus:

ParameterTypeRequiredDefaultDescription
imagestringYes-Source image URL
resolutionstringNo720p720p, 1080p
Wan 2.6 — Video-to-Video
ParameterTypeRequiredDefaultDescription
promptstringYes-Video description (use character1, character2 to reference characters in video)
negative_promptstringNo-What to exclude
videosarrayYes-Source video URLs (max 100MB each, 2-30s duration)
sizestringNo1280*720Output size
durationintegerNo55 or 10 seconds
shot_typestringNo-multi_camera or single_camera
enable_prompt_expansionbooleanNofalseExpand prompt for better results
seedintegerNorandomFor reproducible results
Wan 2.6 — Text-to-Image
ParameterTypeRequiredDefaultDescription
promptstringYes-Image description
negative_promptstringNo-What to exclude
sizestringNo1024*1024Output size (27 presets, see below)
enable_prompt_expansionbooleanNofalseExpand prompt
enable_sync_modebooleanNofalseWait for result synchronously
enable_base64_outputbooleanNofalseReturn Base64 instead of URL
seedintegerNorandomFor reproducible results
Wan 2.6 — Image Edit

Same as text-to-image, plus:

ParameterTypeRequiredDefaultDescription
imagesarrayYes-Images to edit (max 4, 384-5000px per side)
Show full SKILL.md (552 more words)Show less
Wan 2.5 — Text-to-Video
ParameterTypeRequiredDefaultDescription
promptstringYes-Video description
negative_promptstringNo-What to exclude
sizestringNo1280*720Output size (13 presets, including 480p)
durationintegerNo55 or 10 seconds
audiostringNo-Audio URL for guided generation
generate_audiobooleanNofalseGenerate synchronized audio
enable_prompt_expansionbooleanNofalseExpand prompt
seedintegerNorandomFor reproducible results
Wan 2.5 — Image-to-Video

Same as Wan 2.5 text-to-video (without size), plus:

ParameterTypeRequiredDefaultDescription
imagestringYes-Source image URL
resolutionstringNo720p480p, 720p, 1080p
Video Size Options (Wan 2.6)

T2V / V2V (10 presets): 1280*720, 720*1280, 960*960, 1920*1080, 1080*1920, 1280*960, 960*1280, 1920*816, 816*1920, 1280*544

Image Size Options (Wan 2.6 — 27 presets): 1024*1024, 1280*720, 720*1280, 1280*960, 960*1280, 1536*1024, 1024*1536, 1280*1280, 1536*1536, 2048*1024, 1024*2048, 1536*1280, 1280*1536, 1680*720, 720*1680, 2016*864, 864*2016, 1536*864, 864*1536, 2184*936, 936*2184, 1400*1050, 1050*1400, 1680*1050, 1050*1680, 1176*1176, 1560*1560


Workflow: Submit → Poll → Download

Text-to-Video Example (Wan 2.6)
bash
# Step 1: Submit
curl -s -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/wan-2.6/text-to-video",
    "prompt": "A drone shot flying over ancient ruins at golden hour, camera slowly descending toward a central courtyard",
    "size": "1920*1080",
    "duration": 10,
    "shot_type": "multi_camera",
    "generate_audio": true,
    "enable_prompt_expansion": true
  }'
# Returns: { "code": 200, "data": { "id": "prediction-id" } }

# Step 2: Poll (every 5 seconds until completed)
curl -s "https://api.atlascloud.ai/api/v1/model/prediction/{prediction-id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"
# Returns: { "code": 200, "data": { "status": "completed", "outputs": ["https://...video-url..."] } }

# Step 3: Download
curl -o output.mp4 "VIDEO_URL_FROM_OUTPUTS"
Image-to-Video Example (Wan 2.6)
bash
curl -s -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/wan-2.6/image-to-video",
    "image": "https://example.com/landscape.jpg",
    "prompt": "The camera slowly zooms in as clouds drift across the sky and leaves rustle in the wind",
    "resolution": "1080p",
    "duration": 5,
    "generate_audio": true
  }'
Video-to-Video Example (Wan 2.6)
bash
curl -s -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/wan-2.6/video-to-video",
    "videos": ["https://example.com/original-video.mp4"],
    "prompt": "Transform character1 into a cartoon anime character, keep the background unchanged",
    "size": "1280*720",
    "duration": 5,
    "shot_type": "single_camera"
  }'
Audio-Guided Generation Example (Wan 2.6)
bash
curl -s -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/wan-2.6/text-to-video",
    "prompt": "A jazz band performing on stage, musicians playing saxophone and piano",
    "audio": "https://example.com/jazz-music.mp3",
    "size": "1920*1080",
    "duration": 10
  }'
Text-to-Image Example (Wan 2.6)
bash
curl -s -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/wan-2.6/text-to-image",
    "prompt": "A cyberpunk cityscape at night, neon signs reflected in rain puddles, photorealistic",
    "size": "1680*720",
    "enable_prompt_expansion": true
  }'
# Returns: { "code": 200, "data": { "id": "prediction-id" } }
Image Editing Example (Wan 2.6)
bash
curl -s -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/wan-2.6/image-edit",
    "prompt": "Change the background to a sunset beach scene, keep the person unchanged",
    "images": ["https://example.com/photo.jpg"],
    "size": "1280*720"
  }'
Image-to-Video Flash Example (Wan 2.6)
bash
curl -s -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/wan-2.6/image-to-video-flash",
    "image": "https://example.com/portrait.jpg",
    "prompt": "The person slowly turns and smiles",
    "resolution": "720p",
    "duration": 5
  }'
Polling Logic
  • processing / starting / running → wait 5s, retry (typically takes ~30-120s for video, ~5-10s for image)
  • completed / succeeded → done, get URL from data.outputs[]
  • failed → error, read data.error
Atlas Cloud MCP Tools (if available)

If the Atlas Cloud MCP server is configured, use built-in tools:

atlas_generate_video(model="alibaba/wan-2.6/text-to-video", params={...})
atlas_generate_image(model="alibaba/wan-2.6/text-to-image", params={...})
atlas_get_prediction(prediction_id="...")

Implementation Guide

  1. Determine task type:

    • Text-to-video: user describes a scene/action in text → 2.6 T2V or 2.5 T2V
    • Image-to-video: user provides an image to animate → 2.6 I2V or 2.6 I2V Flash (budget)
    • Video-to-video: user wants to transform an existing video → 2.6 V2V
    • Text-to-image: user wants to generate an image → 2.6 T2I
    • Image editing: user wants to modify existing images → 2.6 Image Edit
  2. Choose model version:

    • Wan 2.6 (recommended): Latest generation, best quality, multi-camera, audio-guided, V2V
    • Wan 2.6 Flash: Budget I2V at $0.018/s — ideal for drafts
    • Wan 2.5: Cost-effective at $0.035/s flat rate, supports 480p
  3. Extract parameters:

    • Prompt: describe scene, action, camera movement
    • Negative prompt: exclude undesired elements ("blurry, distorted, watermark")
    • Resolution: 480p for drafts, 720p default, 1080p for final output
    • Duration: 5s default, up to 15s for 2.6, up to 10s for 2.5
    • Shot type (2.6 only): multi_camera for dynamic shots, single_camera for stable framing
    • Audio: provide URL for audio-guided generation, or set generate_audio: true
    • Prompt expansion: set enable_prompt_expansion: true for auto-optimized prompts
  4. Execute: POST to generateVideo/generateImage API → poll result → download

  5. Present result: show file path, offer to play/open

Prompt Tips

  • Scene + Action: "A samurai draws his sword in a bamboo forest at dawn, mist rising from the ground"
  • Camera direction: "Camera slowly dollies forward...", "Aerial tracking shot of...", "First-person POV walking through..."
  • Multi-camera: Use shot_type: "multi_camera" with prompts like "Cut between close-up and wide shot..."
  • V2V character control: Reference characters as character1, character2 — e.g., "Transform character1 into an anime character"
  • Audio-guided: Provide an audio URL to sync video with music, dialogue, or sound effects
  • Negative prompts: "blurry, low quality, distorted faces, watermark, text overlay"

Model Comparison

FeatureWan 2.6Wan 2.5
Video T2V Price (720p)$0.08/s$0.035/s
Video I2V Price (720p)$0.10/s$0.035/s
Max Resolution1080p1080p
Max Duration15s10s
Shot Type ControlYesNo
Audio-GuidedYesYes
Video-to-VideoYesNo
Text-to-ImageYes ($0.021)No
Image EditingYes ($0.021)No
Flash/Fast VariantsI2V Flash ($0.018/s)Yes
Prompt ExpansionYesYes

© LeoYeAI, MIT. 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 3 other files (scripts) in skills/alibaba-wan of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • _meta.json
  • scripts/generate_image.py
  • scripts/generate_video.py

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Wan 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.

Wan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wan this skillLeoYeAI/openclaw-master-skills2.2k—~4.5kAutomated safety check: PassMIT
Media Genclacky-ai/openclacky1.2k—~7.3kAutomated safety check: PassMIT
Qianwen Video GenerationQianWen-AI/qianwen-ai104—~5kAutomated safety check: NotesApache-2.0
Mulerouteraiskillstore/marketplace4301 repos~714Automated safety check: NotesNone
Runcomfy CLIaiskillstore/marketplace4301 repos~3.5kAutomated safety check: PassMIT
Atlas Cloudcalesthio/OpenMontage65k—~1.2kAutomated safety check: PassAGPL-3.0

Similar skills

  • Media Gen

    clacky-ai/openclacky

    Generate or edit images, videos, or audio in the current task.

    1.2k GitHub stars~7.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Qianwen Video Generation

    QianWen-AI/qianwen-ai

    Generate videos using Wan and HappyHorse models. An agent skill from QianWen-AI/qianwen-ai.

    104 GitHub stars~5k tokensUpdated 17 days ago
    Media & CreativeAuto-check: notes
  • Mulerouter

    aiskillstore/marketplace

    Generates images and videos using MuleRouter or MuleRun multimodal APIs.

    430 GitHub starsUsed in 1 repo~714 tokens
    Media & CreativeAuto-check: notes
  • Runcomfy CLI

    aiskillstore/marketplace

    Run any model on RunComfy from the command line. An agent skill from aiskillstore/marketplace.

    430 GitHub starsUsed in 1 repo~3.5k tokens
    Media & CreativeAuto-check passed
  • Atlas Cloud

    calesthio/OpenMontage

    Generate or edit images and videos through the Atlas Cloud gateway.

    65k GitHub stars~1.2k tokensUpdated 5 days ago
    Media & CreativeAuto-check passed
  • Beatdesign Workspace

    BeatAPI/BeatDesign

    操作本地 BeatDesign 项目中的 Canvas、Assets、生成任务、视频时间线和字幕;在用户要求创作、整理、检查或剪辑媒体时使用。

    114 GitHub starsUsed in 1 repo~632 tokens
    Media & CreativeAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 972 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

Questions about Wan

What does Wan do?

Generate AI videos and images using Alibaba's Wan 2.6 and Wan 2.5 — featuring text-to-video, image-to-video, video-to-video, text-to-image, and image editing with up to 1080p resolution, 15-second…. Wan is an agent skill from LeoYeAI/openclaw-master-skills.5 — featuring text-to-video, image-to-video, video-to-video, text-to-image, and image editing with up to 1080p resolution, 15-second duration, multi/single camera shot types, audio-guided generation, and prompt expansion.

When should I use Wan?

Wan fits situations like: the user wants to generate AI videos; create video clips; generate images; users ask to create product demos.

How do I install Wan in Claude Code?

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

How do I install Wan in Codex?

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

Can I use Wan 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 wan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wan, .gemini/skills/wan, .github/skills/wan and .opencode/skills/wan in your project.

What does Wan need to run?

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

Does Wan access the network?

SKILL.md names 3 domains. In commands or code: api.atlascloud.ai; the agent is likely to contact it when it follows the instructions. As links in the text: atlascloud.ai and fal.ai. This is read from the text; nothing was executed.

Is Wan 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 Wan use?

Wan is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Wan use?

About 4.5k tokens (SKILL.md is roughly 18k 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 Wan?

Skills that share tags, products or a category with Wan: Media Gen (clacky-ai/openclacky, 1.2k stars), Qianwen Video Generation (QianWen-AI/qianwen-ai, 104 stars), Mulerouter (aiskillstore/marketplace, 430 stars) and Runcomfy CLI (aiskillstore/marketplace, 430 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wan?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,159 GitHub stars. The repository holds 972 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.