← 返回 Skills 市场
WodeApp AI Engine
作者
diankourenxia
· GitHub ↗
· v1.0.18
· MIT-0
571
总下载
1
收藏
0
当前安装
19
版本数
在 OpenClaw 中安装
/install wodeapp-ai
功能描述
One API Key (WODEAPP_API_KEY) unlocks the full multi-modal stack on this account: text, vision, audio, and video — unified credits, no per-provider keys. Sta...
安全使用建议
This skill appears internally consistent, but take normal precautions: only provide a WODEAPP_API_KEY you intend to trust with prompt/media forwarding and billing; avoid uploading sensitive/confidential files (uploads are stored on WodeApp CDN and URLs may be semi-public); review WodeApp's privacy/ToS (it states prompts may be forwarded to upstream providers and claims not to persist raw prompts — verify with provider if this is critical); create scoped/limited API keys if possible and rotate/revoke keys after testing; and test with non-sensitive data before production use.
功能分析
Type: OpenClaw Skill
Name: wodeapp-ai
Version: 1.0.18
The wodeapp-ai skill bundle provides a comprehensive AI orchestration platform but includes high-risk capabilities such as broad integration with enterprise messaging systems (Feishu, DingTalk, WeCom) and file uploads to a semi-public CDN (wodeapp-ai-skill.json). While these features are consistent with the stated goal of providing a unified AI execution engine, they constitute a significant permission set. Furthermore, SKILL.md contains extensive instructions designed to steer the AI agent's logic and decision-making, which serves as a large prompt-injection surface, although no explicitly malicious intent was identified.
能力标签
能力评估
Purpose & Capability
Name/description (multi-modal execution engine) matches the declared capabilities and the tools/endpoints in SKILL.md and wodeapp-ai-skill.json. Requiring only WODEAPP_API_KEY is proportionate for a single-integrator gateway.
Instruction Scope
SKILL.md instructs the agent to call platform REST/MCP endpoints, create/list/publish projects, and upload files. It explicitly states it does not read local files or other environment variables. No steps request unrelated system artifacts or hidden exfiltration.
Install Mechanism
No install spec and no code files — instruction-only skill. Low risk because nothing is written to disk or downloaded as part of installation.
Credentials
Only one required env var (WODEAPP_API_KEY) is declared and used as the primary credential. That aligns with the skill's single-key design. No unrelated secrets or config paths are requested.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent system presence or modify other skills. Autonomous invocation is allowed by default (platform behaviour) but not combined with other red flags here.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install wodeapp-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/wodeapp-ai触发 - 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
v1.0.18
Version 1.0.18
- Improved and expanded SKILL.md documentation for clarity and depth.
- Updated description and guidance for key features including visual workflows, multi-modal support, and template-based project creation.
- Refined terminology and examples for both international and China-based users.
- Increased reported supported models from 343+ to 400+.
- Added capabilities such as zero-code workflow, storyboard/multi-engine video, workflow model override, workflow-history sync, and asset library.
- No code changes or new files in this release; documentation update only.
v1.0.17
v1.0.17 Changelog
- Updated documentation to reflect new auto-publish workflow: projects and pages are now automatically published upon creation or change, eliminating the need for separate publish actions.
- Added and emphasized verification steps after each modification, instructing to check publishedVersion and page content via get_project/get_page.
- Revised Agent Recipes and examples throughout to align with automatic publishing and required verification after edits.
- Clarified tool usage for project/page creation, publishing, and verification flows.
- No code changes; documentation/guidance improvements only.
v1.0.16
- Changed requirements section to new YAML format using "requires: env" instead of "requirements".
- No changes to code or implementation; metadata updated only.
- Capability and feature set remain unchanged.
v1.0.15
**Changelog for wodeapp-ai 1.0.15**
- All project-related tool responses (`list_projects`, `get_project`, `create_project`, `publish_project`) now include a `url` field. Agents should provide this URL directly to users.
- Added guidance for deciding when to create a new project vs. adding a page to an existing project, encouraging smarter project organization.
- Documentation updated to promote always showing project URLs to users and improved suggestions for project/page management.
- No code changes; documentation only.
v1.0.14
wodeapp-ai 1.0.14
- Expanded workflow orchestration to support 22 step types (was 19).
- Added detailed "Agent Recipes" section with step-by-step usage examples for common agent tasks, in both English and Chinese.
- Included quick reference tips for building projects, pages, and workflows, clarifying usage of main tools and APIs.
- Added demo REST API invocations for key workflows.
- Improved documentation for multi-page apps and project management.
- No changes to file content or code; documentation update only.
v1.0.13
wodeapp-ai 1.0.13
- Updated architecture documentation to clarify cost savings (now stated as 20–30%) and positioning vs. direct provider keys.
- Expanded setup instructions, now mentioning MCP config requirements for specific clients and offering a no-MCP web alternative.
- Added new production template: user-management (用户管理).
- Increased number of page builder UI components from 60+ to 75+, with new block/section categories.
- Improved and clarified various descriptions throughout documentation for easier onboarding and comparison.
v1.0.12
- Added support for digital human avatar generation and related workflow capabilities.
- Introduced project-scoped MCP protocol for advanced digital human and video generation scenarios.
- Expanded capabilities list with `digital-human-avatar` and `project-scoped-mcp`.
- Updated description to highlight digital avatar/video generation and project-scoped MCP.
- No file or code changes detected; updates are documentation and capability clarifications.
v1.0.11
- License updated from Commercial to MIT-0 for improved openness.
- Minor metadata adjustments: added requirements and primaryCredential fields.
- Version bump from 2.2 to 2.3.
- No changes to features, capabilities, or usage instructions.
v1.0.10
- Updated version to 2.2 and clarified that only a single API key (WODEAPP_API_KEY) is needed—no additional platform credentials required.
- Improved description to emphasize simplified setup and key requirement.
- Updated trigger scenario documentation to reflect that server-side video features now use just the main API key.
- No functional or code changes included in this release.
v1.0.9
No file changes detected; only documentation updates.
- Updated documentation with new architecture overview, clearer feature mapping, and detailed trigger scenarios for each tool.
- Added comprehensive lists of intent patterns, production-ready templates (with template IDs), and available page builder UI components.
- Improved guidance for agent developers, including parameter design principles and instant-deploy workflows.
- Streamlined descriptions and terminology to better communicate WodeApp’s unified AI execution and orchestration capabilities.
v1.0.8
- Added metadata fields: homepage, author, requiredEnv (WODEAPP_API_KEY) to SKILL.md.
- No functional changes to the skill code or user-facing features.
v1.0.7
- Major documentation overhaul: streamlined all sections for clarity and brevity
- Simplified feature overviews and capability descriptions
- Combined and condensed English/Chinese guidance for easier reading
- Improved API usage examples and setup instructions
- Updated security, endpoints, and MCP tool documentation for easier onboarding
- No code or functional changes; documentation only
v1.0.6
- Added headless Workflow API for programmatic workflow discovery and execution via REST.
- Documentation now includes usage examples for the new Workflow API endpoints.
- Updated description to mention "headless workflow API."
- Updated suggested endpoint domain from `*.wodeapp.com` to `*.wodeapp.ai` for zero-deploy.
v1.0.5
No changes detected in this version (1.0.5).
- No file changes were made.
- Documentation and core functionality remain unchanged.
v1.0.4
- Version bump to 1.0.4 with no file changes detected.
- No updates to features, documentation, or configuration.
v1.0.3
- Added a security best practices section with guidance on API key storage, scoping, revocation, data policy, and rate limiting.
- Updated MCP client configuration examples to recommend using environment variables for API keys, with explicit security warnings.
- Clarified that API keys should never be hardcoded in config files.
- No changes to skill features or endpoints; documentation improvements only.
v1.0.2
- Removed the English documentation file `SKILL.en.md`.
- Combined English and Chinese instructions into a single, concise bilingual `SKILL.md`.
- Updated capability and feature descriptions for clarity and brevity.
- Improved quick start instructions and endpoint references.
- Ensured all details now appear in both English and Chinese within one unified file.
v1.0.1
- Major documentation update: SKILL.md completely rewritten and expanded for clarity.
- Added new SKILL.en.md file (English documentation).
- SDK reference (wodeapp-sdk.mjs) removed; Node.js 示例与 SDK细节不再包含于主文档。
- 明确突出全新支持的视频生成（豆包 Seedance、可灵 AI）及可视化工作流能力。
- 详细说明统一积分池、极致省 Token、免部署免运维等核心优势。
- 操作指导、API示例与环境准备流程更精简、更详细，并整理关键端点和限流策略。
- 关键词与内容结构优化，便于多模型、多能力场景下更易查阅与上手。
v1.0.0
WodeApp AI 1.0.0
EN:One skill, 343+ AI models — text generation, image creation, structured JSON, TTS, video, and no-code page building. MCP-native, plug and play.
CN:- 提供文本、图片、JSON 结构化、语音合成、视频生成、页面构建等全套 AI 能力
- 支持通过 MCP Server、Node.js SDK、REST API 三种方式接入
- 内置 9 个 MCP Tools，涵盖项目管理与 AI 功能
- 文档详细包含端点地址、安全限制、文件清单和环境变量配置
元数据
常见问题
WodeApp AI Engine 是什么？
One API Key (WODEAPP_API_KEY) unlocks the full multi-modal stack on this account: text, vision, audio, and video — unified credits, no per-provider keys. Sta... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 571 次。
如何安装 WodeApp AI Engine？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install wodeapp-ai」即可一键安装，无需额外配置。
WodeApp AI Engine 是免费的吗？
是的，WodeApp AI Engine 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
WodeApp AI Engine 支持哪些平台？
WodeApp AI Engine 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 WodeApp AI Engine？
由 diankourenxia（@diankourenxia）开发并维护，当前版本 v1.0.18。
推荐 Skills