AIVideoMaker API Executor
Purpose
Provide a production-ready execution workflow for AIVideoMaker API v1:
- - Create generation task
- Poll task status safely
- Fetch task details
- Cancel submitted task
When To Use
- - User asks to call
aivideomaker.ai API directly - User wants a scriptable generation workflow
- User needs robust retry/429 handling for task queries
Required Environment
- -
AIVIDEO_API_KEY (required) Get an API Key from https://aivideomaker.ai . - INLINECODE2 (optional, default
30000) - Request timeout in milliseconds - INLINECODE4 (optional, default
3) - Max retries for idempotent read requests
Supported Actions
- 1. INLINECODE6
- INLINECODE7
- INLINECODE8
- INLINECODE9
Model Whitelist
- - INLINECODE10
- INLINECODE11
- INLINECODE12
- INLINECODE13
- INLINECODE14
Image Input Policy
- - This skill accepts both public image URLs and
data:image/...;base64,... for i2v, lv, and i2v_v3. - Prefer
data:image/...;base64,... for reliability in OpenClaw environments.
Standard Workflow
- 1. Validate model and payload by contract.
- Call
createGeneration. - Poll
getStatus with backoff until terminal status. - If
COMPLETED, call getTask and return output. - If
FAILED, return failure with actionable next steps.
Error Policy
- - Normalize all responses to:
-
ok,
status,
taskId,
data,
errorCode,
errorMessage,
retryAfter
- - Map API/runtime errors into stable error codes:
-
INVALID_MODEL
-
INVALID_PAYLOAD
-
AUTH_FAILED
-
RATE_LIMITED
-
INSUFFICIENT_CREDITS
-
TASK_NOT_FOUND
-
NETWORK_ERROR
- INLINECODE39
Execution Commands
-
node scripts/run-workflow.mjs --model <model> --payload '<json_payload>'
-
node scripts/run-workflow.mjs --action getStatus --taskId <task_id>
-
node scripts/run-workflow.mjs --action getTask --taskId <task_id>
- INLINECODE43
Security
This skill only performs the following actions:
- - Calls the AIVideoMaker API with user-provided parameters
- Validates input payloads against a defined contract
- Reads only payload passed via INLINECODE44
- Does not read arbitrary host files, credentials, or sensitive system information
- Does not execute arbitrary code or shell commands
All network requests are made to https://aivideomaker.ai (or an optional custom base URL configured via client options) and include only the API key for authentication.
Security Best Practices:
- - Never hardcode API keys in source code, configuration files, or skill archives
- Always pass the
AIVIDEO_API_KEY as an environment variable - Use secret management tools or platform-specific credential storage
- Regularly rotate API keys and monitor usage
Additional Resources
AIVideoMaker API 执行器
目的
为AIVideoMaker API v1提供生产就绪的执行工作流：
- - 创建生成任务
- 安全轮询任务状态
- 获取任务详情
- 取消已提交的任务
使用场景
- - 用户要求直接调用aivideomaker.ai API
- 用户需要可脚本化的生成工作流
- 用户需要针对任务查询的稳健重试/429处理
所需环境
- - AIVIDEOAPIKEY（必需）从https://aivideomaker.ai获取API密钥。
- AIVIDEOTIMEOUTMS（可选，默认30000）- 请求超时时间（毫秒）
- AIVIDEOMAX_RETRIES（可选，默认3）- 幂等读取请求的最大重试次数
支持的操作
- 1. createGeneration
- getTask
- getStatus
- cancelTask
模型白名单
图像输入策略
- - 本技能接受公共图像URL和data:image/...;base64,...格式用于i2v、lv和i2v_v3。
- 在OpenClaw环境中优先使用data:image/...;base64,...以确保可靠性。
标准工作流
- 1. 根据契约验证模型和负载。
- 调用createGeneration。
- 使用退避策略轮询getStatus直至终端状态。
- 如果状态为COMPLETED，调用getTask并返回输出。
- 如果状态为FAILED，返回失败信息及可操作的后续步骤。
错误策略
- ok、status、taskId、data、errorCode、errorMessage、retryAfter
- INVALID_MODEL
- INVALID_PAYLOAD
- AUTH_FAILED
- RATE_LIMITED
- INSUFFICIENT_CREDITS
- TASK
NOTFOUND
- NETWORK_ERROR
- UNKNOWN_ERROR
执行命令
- node scripts/run-workflow.mjs --model
--payload
- node scripts/run-workflow.mjs --action getStatus --taskId
- node scripts/run-workflow.mjs --action getTask --taskId
- node scripts/run-workflow.mjs --action cancelTask --taskId
安全性
本技能仅执行以下操作：
- - 使用用户提供的参数调用AIVideoMaker API
- 根据定义的契约验证输入负载
- 仅读取通过--payload传递的负载
- 不读取任意主机文件、凭据或敏感系统信息
- 不执行任意代码或shell命令
所有网络请求均发送至https://aivideomaker.ai（或通过客户端配置的可选自定义基础URL），且仅包含用于身份验证的API密钥。
安全最佳实践：
- - 切勿在源代码、配置文件或技能存档中硬编码API密钥
- 始终将AIVIDEOAPIKEY作为环境变量传递
- 使用密钥管理工具或平台特定的凭据存储
- 定期轮换API密钥并监控使用情况
附加资源
