Installation
dsh plugin --profile web add github:DDDFXYqiming/dsh-vision-skillCopy
dsh plugin --profile web add dsh-vision-skillCopy
Plugins in this repository dsh-vision-skill v0.4.4 ✓
DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.
Official core packages (6) @deepseek-ai/cordis>=4.0.0-rc <5 shared @deepseek-ai/dsh-client-runtime^0.1.0-rc.6 shared @deepseek-ai/dsh-client-ui-conversation^0.1.0-rc.6 shared @deepseek-ai/dsh-credentials* shared @deepseek-ai/dsh-tools* shared @deepseek-ai/schemastery* shared Paths are pinned to commit eafb44378e41
Overview Vision skill plugin for DeepSeek Harness (image analysis and OCR)
Repository check result Results are bound to the listed commit and cover only static checks run by this registry. The Evidence Score measures reviewable information; it is not a compatibility percentage or a security guarantee.
Static repository check Sep 1, 2026, 5:34 AM No static findings
Evidence Score 83/100
Static risk No static findings
Files scanned 2
Findings 0 Evidence breakdown Source provenance 25/25
Install documentation 25/25
Maintenance 12/20
Compatibility evidence 11/20
Security signals 10/10
Compatibility confidence: Limited
Findings (0) No static findings were recorded for this commit.
Not run Dependency advisory database scan Installation execution test Runtime behavior verification Scanner 1.0.0 · Scorer 1.0.0