#
ENJA

deepseekimg

wdwxw/deepseekimg

Enables text-only models like DeepSeek in Claude Code to process local images by bridging to a local Ollama vision model.

14 5No licenseUpdated 2026-07-10
View on GitHubOpen source file

Overview

This skill acts as a middleware bridge allowing text-based AI models within Claude Code to interpret local image files. By utilizing a companion Node.js script, it encodes images in base64 format and queries a local Ollama vision model (such as gemma4:e2b) based on the user's specific prompt or question, ensuring targeted answers rather than generic image captions.

Capabilities

  • ▸Local image path processing
  • ▸Base64 image encoding for API transmission
  • ▸Integration with local Ollama vision models
  • ▸Question-driven visual analysis and OCR
  • ▸Configurable model parameters including thinking mode and API endpoints

Best for

Answering specific questions about a local image such as counting people or identifying objects., Performing OCR to extract text from screenshots or documents., Identifying products or analyzing visual styles from image paths., Generating general scene descriptions when no specific query is provided.

Works with

Claude Code
Evoa Score breakdown= Σ (score × weight)
62
Task usefulness20%88 → +17.6

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%85 → +12.8

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%85 → +12.8

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%28 → +3.4

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%100 → +15.0

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%70 → +7.0

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%35 → +2.8

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%25 → +1.3

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total72.5 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →

Security considerations

Communicates with a local Ollama server running on localhost. No external cloud transmission occurs unless configured otherwise via environment variables.

Categories

CodingAI EngineeringAutomationProductivity

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.