mrdulasolutions/visionclaude/vision-describe
Claude Code and agent skill by mrdulasolutions/visionclaude
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Detailed scene analysis and object identification
Install
npx vskill@latest install mrdulasolutions/visionclaude/vision-describeSKILL.md
Vision Describe
When the user asks you to describe what you see, provide a thorough analysis:
- Primary subject: What is the main focus of the image?
- Environment: Indoor/outdoor, lighting, setting
- Text: Read ANY visible text exactly (signs, screens, labels, packaging)
- Objects: List notable objects with specific details (brand, color, size, condition)
- Activity: What is happening in the scene?
- Notable details: Anything unusual, interesting, or potentially useful
Be specific — say "red Nike Air Max 90" not "sneakers". Say "Samsung Galaxy S24 showing a weather app" not "a phone with an app open".
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingClaudeVision/server/skills/vision-describe/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/mrdulasolutions/visionclaude/vision-describe)