dsh-vision-skill
Multimodal vision perception and UI grounding skill plugin for DeepSeek Harness.
Install
$ dsh plugin --profile web add github:DDDFXYqiming/dsh-vision-skillPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Deep multi-mode image analysis across code, errors, tables, and evidence modes
- UI element grounding and bounding box localization
- Full-page UI interactable element detection and numbering
- Overlapping long screenshot slicing with local Tesseract-first OCR and VLM fallback
- Local dominant color extraction without external API calls
- Clipboard and paste ingestion directly into workspace paths
- Multi-provider VLM failover handling rate limits and timeouts
Useful For
- Enabling vision understanding for text-only primary LLMs inside DeepSeek Harness
- Automated UI element localization and bounding box detection for agent workflows
- Extracting structured text and data from full-page and long scrolling screenshots
- Analyzing software bug screenshots and terminal error images from clipboard
Who It Fits
- DeepSeek Harness developers building multimodal or web automation agents
- Users needing image inspection, OCR, and GUI element grounding without switching primary LLMs
Documented Limitations
- Local OCR features require local Tesseract binary installation and language pack setup
- External VLM analysis requires configured OpenAI-compatible vision model API endpoints and credentials
- Requires Node.js >= 22.19 runtime environment
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 6 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- DDDFXYqiming/dsh-vision-skill
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- ad4d35f · 2026-10-19
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 2GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-15
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Full office suite integration for DeepSeek Harness supporting spreadsheets, docs, slides, bases, and canvases.
View plugin →Generative UI plugin for DeepSeek Harness that renders interactive cards, charts, forms, and panels inline from dsh-ui code fences.
View plugin →Skill manager UI for DeepSeek Harness to discover, toggle, import, and update agent skills.
View plugin →