メニュー
Use this skill when text needs to be extracted from images, including short verification codes and multi-line document screenshots.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use this skill when Word, PPT, or PDF files need to be normalized into images before OCR, multimodal understanding, or preview rendering.
Use this skill when the user needs text-to-image or image-guided image generation, such as posters, illustrations, style changes, or creative visual drafts.
Use this skill when Markdown content must be rendered into HTML or image output for chat previews, long replies, or rich document screenshots.
Use this skill when the project needs to generate QR codes from text or decode QR codes from images.
| name | ocr |
| description | Use this skill when text needs to be extracted from images, including short verification codes and multi-line document screenshots. |
Use this skill when image text should be recognized instead of being sent directly to an LLM.
src.core.skills.ocr_skill.read_code(...) for验证码或单行短文本。src.core.skills.ocr_skill.read_lines(...) for multi-line text detection and recognition.src.core.skills.ocr_skill.read_text(...) when you want one combined text result with automatic fallback.resources/models/ocr/.