文档处理
image-analyzer
Inspect supplied images with available vision tools for OCR, visual description, object inspection, layout review, comparison, and structured extraction.
Rylaispirit · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add Rylaispirit/rylai-codex-hermes-skills --skill image-analyzer技能说明
name: image-analyzer description: Inspect supplied images with available vision tools for OCR, visual description, object inspection, layout review, comparison, and structured extraction. metadata: maintainer: Rylai adapted_by: Rylai edition: Codex-Hermes-Claude edition_version: 1.1.0 provenance: clean-room-original hermes: category: media claude: category: media
Rylai Codex-Hermes-Claude Edition | Original portable workflow by Rylai
Image Analyzer
Analyze the supplied image itself before making claims.
Workflow
- Resolve the exact local file, attachment, or user-approved URL.
- Inspect the original resolution when small text, fine detail, or cropping matters.
- Match the analysis to the request: description, OCR, layout, objects, comparison, or extraction.
- Separate direct observations from interpretation and uncertainty.
- Preserve reading order for OCR and mark unreadable regions instead of guessing.
- For structured extraction, define the schema first and use
nullfor unavailable fields. - When comparing images, use the same checklist for every image.
- Return concise evidence and note any resolution or visibility limits.
Runtime Routes
- Use the image viewer or native vision capability available in Codex, Hermes, or Claude.
- Use an external OCR or vision service only when the user approves it and the required credentials are already configured.
Safety
- Do not infer sensitive identity, health, ethnicity, or exact location without reliable evidence and a legitimate user request.
- Do not claim that an object, logo, person, or place is certain when the image only supports a tentative match.
- Never upload a private image to an external service without user approval.