MJorgin/dsh-media-skills
dsh-media-skills is a tool for DeepSeek Harness. Free image reading & generation for DeepSeek Harness (rc.7 / rc.8 / v0.1.1-rc.1 / rc.2) — paste-image reading with auto vision transcription, DeepSeek-V4-Flash-Vision-Exp / GLM-4V-Flash / SenseNova / Gemini failover, Kolors + U1 Fast generation. No keys in repo.
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Solid free vision and image-generation skills for DeepSeek Harness with multi-provider failover and no committed keys.
README describes a structured Python bundle with a documented failover chain and bundled patch files for four Harness versions, but no tests or CI are mentioned in the provided excerpt.
The README explicitly states keys are never committed and images go only to user-chosen providers, though the install path pulls code from GitHub and the required Harness patches modify core behavior.
Solves a concrete, common gap by letting text-only DeepSeek Harness sessions read pasted images and generate new ones via free models like GLM-4V-Flash and Kolors.
Last updated 2026-08-24 with explicit support for rc.7, rc.8, v0.1.1-rc.1 and rc.2, and the repo is not archived, indicating active tracking of upstream releases.
README is thorough with badges, comparison table, capability matrix, quick-start links and translations into nine languages, though the excerpt cuts off mid-table and full setup details live in linked docs.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryINSTALL REFERENCE
dsh plugin --profile <name> add github:MJorgin/dsh-media-skillsThis command was extracted from an explicit README install reference and is display-only; the DSH host will not execute it automatically.
PROJECT TOPICS
VALIDATION LADDER
FAQ
Free image reading & generation for DeepSeek Harness (rc.7 / rc.8 / v0.1.1-rc.1 / rc.2) — paste-image reading with auto vision transcription, DeepSeek-V4-Flash-Vision-Exp / GLM-4V-Flash / SenseNova / Gemini failover, Kol
dsh-media-skills has 17 stars and 2 forks on GitHub, last updated 2026-08-24.
dsh-media-skills is distributed under the MIT license.
dsh-media-skills is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:agent-skills、skill、image-generation、vision。
liustack
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | The strongest vision add-on plugin for DeepSeek Harness, adding vision capability to text-only models like DeepSeek and GLM, paste an image and get structured JSON evidence (OCR, layout, semantics).
Ephemeral-AI-Lab
Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, commit what changed as deduplicated checkpoints, then branch, rewind or merge. Try it with LayerFS × DSH.
tong-io
TongFlow — Multimodal GenAI Studio
Anionex
[dsh] A more powerful visual toolkit for text-only models: one-line install and use, paste images for direct recognition, multi-image Q&A, screenshot-to-frontend UI restoration, and more｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
DDDMUC
Free web search provider for DeepSeek Harness - DuckDuckGo backend, no API key needed
anysearch-team
AnySearch web search provider and advanced search tools for DeepSeek Harness (DSH)