dsclaude

dsclaude contains 1 collected skills from Agents365-ai, with repository-level occupation coverage and site-owned skill detail pages.

Agents365-ai profile View on GitHub

skills collected

Stars

updated

2026-07-09

Forks

Occupation coverage

Software Developers

1 occupation categories · 100% classified

repository explorer

Skills in this repository

creator/repo/skill

skill

occupation

description

updated

deepseek-vision

software-developers

Use whenever the user references an image (local file path or http/https URL — screenshot, photo, diagram, UI capture, chart, error dialog) and you need to know what's in it to answer or act. Calls a vision model (Qwen3.6-Flash by default) via DashScope and returns a text description you can reason over. Especially important when running on a text-only backend like DeepSeek V4, but also useful as a dedicated OCR / detail extractor even when the main model is multimodal.

2026-07-09