← 返回 Skills 市场
husu

AIVideomaker

作者 husu · GitHub ↗ · v1.0.14 · MIT-0
cross-platform ⚠ suspicious
283
总下载
1
收藏
0
当前安装
15
版本数
在 OpenClaw 中安装
/install ai-video-maker
功能描述
Executes AIVideoMaker API workflows for text-to-video and image-to-video generation, including task creation, status polling, task details retrieval, and can...
使用说明 (SKILL.md)

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 .
  • AIVIDEO_TIMEOUT_MS (optional, default 30000) - Request timeout in milliseconds
  • AIVIDEO_MAX_RETRIES (optional, default 3) - Max retries for idempotent read requests

Supported Actions

  1. createGeneration
  2. getTask
  3. getStatus
  4. cancelTask

Model Whitelist

  • t2v
  • i2v
  • lv
  • t2v_v3
  • i2v_v3

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.
  2. Call createGeneration.
  3. Poll getStatus with backoff until terminal status.
  4. If COMPLETED, call getTask and return output.
  5. 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
    • UNKNOWN_ERROR

Execution Commands

  • Run full workflow:
    • node scripts/run-workflow.mjs --model \x3Cmodel> --payload '\x3Cjson_payload>'
  • Query status:
    • node scripts/run-workflow.mjs --action getStatus --taskId \x3Ctask_id>
  • Query task details:
    • node scripts/run-workflow.mjs --action getTask --taskId \x3Ctask_id>
  • Cancel task:
    • node scripts/run-workflow.mjs --action cancelTask --taskId \x3Ctask_id>

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 --payload
  • 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. The API key is sent as an HTTP header named key (as required by the AIVideoMaker API). While HTTPS encrypts the transmission, intermediaries may log the key header. Users should be aware of privacy implications when sending image data and API keys to upstream services.

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

安全使用建议
This skill appears to do exactly what it says: call aivideomaker.ai to create and monitor video-generation tasks and it only needs your AIVIDEO_API_KEY. Before installing, consider: (1) Only provide an API key with the minimum necessary privileges; rotate keys regularly and do not hardcode them. (2) The API key is sent in an HTTP header named "key" — intermediaries or logs could record that header, so avoid sending highly sensitive keys through environments where network egress is monitored. (3) The skill will upload image data (including base64 data URIs) to the upstream service — do not send images you are not comfortable sharing. (4) The code uses web fetch/AbortController behavior common to newer Node versions; ensure your runtime provides fetch (Node >=18) or the agent environment supplies an HTTP fetch implementation. (5) If you need stricter guarantees, run the scripts in an isolated environment and monitor network calls or use a short-lived/revocable API key.
功能分析
Type: OpenClaw Skill Name: ai-video-maker Version: 1.0.14 The skill bundle is a legitimate API executor for the AIVideoMaker service, providing a structured workflow for video generation. The implementation in `scripts/aivideo-client.mjs` and `scripts/run-workflow.mjs` follows security best practices, such as sanitizing logs to prevent API key leakage and validating input payloads against a strict contract (`scripts/contract.mjs`). There is no evidence of data exfiltration, unauthorized system access, or malicious prompt injection; all network activity is confined to the stated service domain (aivideomaker.ai).
能力评估
✓ Purpose & Capability
Name/description, required env var (AIVIDEO_API_KEY), and declared binary (node) align with the included client and workflow scripts that call https://aivideomaker.ai endpoints. No unrelated credentials, binaries, or config paths are requested.
✓ Instruction Scope
SKILL.md and the scripts limit actions to creating tasks, polling status, fetching task details, and cancelling tasks. The code reads only process.env.AIVIDEO_API_KEY, CLI args (including the --payload JSON), and does not access arbitrary host files or other system credentials.
✓ Install Mechanism
No install spec is provided (instruction-only at registry level); the package includes Node scripts only. Nothing is downloaded from untrusted URLs and no extract/install steps are declared.
✓ Credentials
Only AIVIDEO_API_KEY is required (with optional AIVIDEO_TIMEOUT_MS and AIVIDEO_MAX_RETRIES). These variables are proportionate and justified by the API client behavior. The primary credential is declared correctly.
✓ Persistence & Privilege
Skill is not force-included (always:false). It does not modify other skills or system-wide settings and only performs network calls to the documented API endpoints.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install ai-video-maker
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /ai-video-maker 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.14
- Added top-level requires, binaries, and primaryCredential fields for clearer environment and dependency specification. - Updated security documentation to clarify that the API key is sent as an HTTP header named key, noting potential privacy implications. - Enhanced security warning about intermediaries possibly logging the key header and handling of user image data. - No feature changes or new functionality—documentation and metadata improvements only.
v1.0.13
- Removed sample and smoke test files: examples/t2v-input.json, scripts/smoke-test.mjs. - Updated documentation to remove references to the smoke test script and example input files. - Updated image input policy and recommended passing payloads directly via the command line for workflow execution.
v1.0.12
- Updated to version 1.0.12. - Changed metadata: replaced "credentials" with "primaryCredential" for environment variable configuration. - No changes to core functionality or command usage.
v1.0.11
- Added required "node" binary and "AIVIDEO_API_KEY" as the primary credential in skill metadata. - No changes to core logic or supported actions. - Security and usage remain unchanged.
v1.0.10
- Added a .gitignore file to the project. - Updated documentation to include a "Security Best Practices" section with recommendations for API key management. - No changes to the skill logic or API workflows.
v1.0.9
ai-video-maker 1.0.9 - Added .claude/settings.local.json and clawhub.manifest.json files. - Updated environment variable docs: clarified purpose for optional variables, especially SMOKE_TASK_ID for testing. - Enhanced security documentation, outlining exactly what actions the skill performs and limiting host/file access. - Updated resource links to new locations under references/. - No changes to API behavior.
v1.0.8
- Removed the file clawhub.manifest.json from the project. - No changes to functionality or documentation beyond file removal. - Version updated to 1.0.8.
v1.0.7
- Added new metadata field to declare required environment variables for improved integration and validation. - Incremented version to 1.0.7.
v1.0.6
- Added skill version 1.0.6 to metadata. - Declared version field in SKILL.md. - No changes to functionality or API; change is metadata-only.
v1.0.5
- No user-facing changes in this release. - No file changes detected. - All features and documentation remain unchanged from the previous version.
v1.0.4
- Enhanced documentation for required and optional environment variables; added requirements metadata for easier setup. - Clarified purpose and usage scenarios, detailing when to use the skill for API workflows. - Updated and simplified error policy and normalized response fields. - Improved descriptions of supported actions and workflow steps. - Added explicit mention of primary credential (AIVIDEO_API_KEY) and improved structure for quick reference.
v1.0.3
Version 1.0.3 of ai-video-maker - No changes detected in any files. - No updates to functionality, documentation, or dependencies.
v1.0.2
- Major documentation restructure for clarity and quick reference, including a new Security Notes section. - Added two new reference files: api-reference.md and examples.md, replacing the previous single examples.md and reference.md. - All resource links now point to updated file locations under the references/ directory. - Minor edits to command explanations and field names for consistency and accuracy. - Environment and error handling details now more concise and standardized. - Removed legacy checklist and consolidated workflow instructions for easier usage.
v1.0.1
- Added instruction to obtain an API key from https://aivideomaker.ai in the environment setup. - No functional or workflow changes; documentation is now clearer on acquiring required credentials.
v1.0.0
- Initial release of ai-video-maker API Executor skill. - Supports automated workflows for video generation tasks: create, monitor, retrieve details, and cancel. - Provides robust error handling and unified response formats across all actions. - Enables direct and scriptable video generation via AIVideoMaker API for text-to-video and image-to-video models. - Includes support for retry logic, rate-limit handling, and task management commands.
元数据
Slug ai-video-maker
版本 1.0.14
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 15
常见问题

AIVideomaker 是什么？

Executes AIVideoMaker API workflows for text-to-video and image-to-video generation, including task creation, status polling, task details retrieval, and can... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 283 次。

如何安装 AIVideomaker？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-video-maker」即可一键安装，无需额外配置。

AIVideomaker 是免费的吗？

是的，AIVideomaker 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

AIVideomaker 支持哪些平台？

AIVideomaker 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 AIVideomaker？

由 husu（@husu）开发并维护，当前版本 v1.0.14。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论