Plain text model image recognition plug-in
whitelonng/dsh-plugin-describe-image · skills
DeepSeek Harness plugin: describeimage — give a text-only model vision through an OpenAI-compatible VLM endpoint.
★ 5GitHub stars
0Forks
2026-08-15Last updated
TypeScriptLanguage
MITLicense
Project overview
A DeepSeek Harness plugin: the model-facing describeimage tool, which gives a text-only model (DeepSeek V4 and friends) image understanding.
This repository holds the plugin subtree as it lives inside deepseek-harness: package dependencies stay workspace:^, and building, type-checking, and testing happen inside a harness checkout (see INTEGRATION.md). The harness tree is the build environment, not this repo. Keep the two in sync with:
Install command
dsh plugin --profile web add github:whitelonng/dsh-plugin-describe-image