← 返回 Skills 市场
659
总下载
1
收藏
5
当前安装
4
版本数
在 OpenClaw 中安装
/install translate-image
功能描述
Translate text in images, extract text via OCR, and remove text using TranslateImage AI. Use when user says 'translate image', 'OCR image', 'extract text fro...
安全使用建议
This skill appears to do what it claims (send images to translateimage.io for OCR/translation/inpainting). Before installing: 1) Verify the publisher and the translateimage.io domain (no homepage/source was provided here). 2) Be aware it requires TRANSLATEIMAGE_API_KEY and expects curl and python3 — the package metadata omitted those, so confirm the platform will prompt for the API key. 3) Any image you process is uploaded to an external service — do not send sensitive or private images unless you trust the service and its privacy policy. 4) The skill may download user-provided image URLs (follow SKILL.md guidance: only fetch URLs the user explicitly supplies); avoid giving internal or sensitive URLs to prevent SSRF/data-leakage risks. If you rely on this skill, prefer obtaining the API key from the official site and verifying the publisher identity first.
功能分析
Type: OpenClaw Skill
Name: translate-image
Version: 1.0.3
The skill provides image translation, OCR, and text removal capabilities by interfacing with the translateimage.io REST API. It uses standard system utilities like curl for network requests and python3 for safe JSON parsing and base64 decoding. The logic is transparently documented in SKILL.md, aligns with the stated purpose, and includes appropriate security warnings regarding the handling of untrusted URLs.
能力评估
Purpose & Capability
The name and description match the instructions: the skill sends images to https://translateimage.io for translate/OCR/remove-text operations and expects an API key. However, registry-level metadata reported earlier (no required env or binaries) contradicts the SKILL.md, which declares TRANSLATEIMAGE_API_KEY and requires curl and python3. That mismatch is a coherence problem in the package metadata.
Instruction Scope
SKILL.md stays within the stated purpose: it documents POST endpoints, required form fields, and example curl/python snippets for decoding base64 images. It only instructs fetching images that the user explicitly provides and uses /tmp for temporary files. It does not instruct reading unrelated files or other environment variables.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk by the skill package itself. That lowers installation risk.
Credentials
The single required secret (TRANSLATEIMAGE_API_KEY) is appropriate for a third‑party REST API integration. The concern is the inconsistency between SKILL.md (which requires the env var) and the registry summary (which listed no required env vars). If the platform doesn't surface this requirement to you, the skill may fail or silently attempt to use an unset variable.
Persistence & Privilege
The skill is not always-enabled, is user-invocable, does not request persistent system privileges, and does not modify other skills' configs. Autonomous invocation is allowed (platform default) but not combined with other worrying privileges.
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 translate-image - 安装完成后，直接呼叫该 Skill 的名称或使用
/translate-image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
v1.0.3
- Updated skill name to "translate-image" and revised metadata for consistency and clarity.
- Removed legacy files: README.md, package.json, and scripts/validate.js.
- Added metadata.json for standardized skill metadata.
- Improved and clarified the description and usage instructions, including typical user intent phrases.
- No changes to core API endpoints or functionality.
v1.0.2
No significant changes detected in this version.
- No file changes were made between versions 1.0.0 and 1.0.2.
- Documentation, functionality, and usage remain the same.
v1.0.1
- Switched from Node-based MCP server to direct REST API usage via curl for all TranslateImage functionality.
- Updated setup instructions to require only an API key and curl; Node.js installation is no longer needed.
- All tool usage is now via HTTP endpoints—bash and curl examples provided for every feature.
- Clarified image input methods (local file/URL) and base64 result handling.
- Revised Shopify image translation integration instructions to use the TranslateImage REST API.
- Added endpoint scope documentation and improved error handling notes.
v1.0.0
- Initial release of the TranslateImage skill.
- Translate text in images, extract OCR, and remove text with AI inpainting.
- High-quality image-to-text extraction with optional translation using Gemini AI.
- Shopify tools for translating product images at scale, including batch operations and store stats.
- Supports multiple image formats, language models, and font options.
- Requires TRANSLATEIMAGE_API_KEY and optional Shopify credentials for store features.
元数据
常见问题
Translate Image 是什么？
Translate text in images, extract text via OCR, and remove text using TranslateImage AI. Use when user says 'translate image', 'OCR image', 'extract text fro... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 659 次。
如何安装 Translate Image？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install translate-image」即可一键安装，无需额外配置。
Translate Image 是免费的吗？
是的，Translate Image 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Translate Image 支持哪些平台？
Translate Image 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 Translate Image？
由 cottom（@cottom）开发并维护，当前版本 v1.0.3。
推荐 Skills