DDDFXYqiming/Agent_Extensions

Agent Skills & DeepSeek Harness (DSH) 扩展库:通用智能体技能(General_skills)+ DSH 标准插件(dsh-plugin),开箱即用的 AI Agent 能力增强集合。

7Stars on the repository
7Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

DDDFXYqiming/Agent_Extensions

Skill Claude CodeCodex

Use when controlling Windows native desktop apps or real-browser sessions with GenericAgent-style coderun: dynamic Python execution, Win32/UIA/OCR/screenshots/CDP, and observe-act-verify loops.

7 2d ago C 45 tokens original MIT

markitdown-skill

02

DDDFXYqiming/Agent_Extensions

Skill Claude CodeCodex

Chinese-language guidance for using the MarkItDown skill, which converts source materials such as documents or data into structured, reusable output.

7 2d ago A 0 tokens original MIT

ppt-master

03

DDDFXYqiming/Agent_Extensions

Skill Claude CodeCodex

A system for turning source material such as PDFs, Word documents, URLs, and Markdown into SVG pages and then exporting them as PowerPoint presentations. It uses several roles and includes guidance for handling source files, commands, and outputs.

7 2d ago A 76 tokens original MIT

DDDFXYqiming/Agent_Extensions

Skill Claude CodeCodex

Use when user wants to summarize, analyze, or generate notes from a video URL. Converts video content into structured Markdown notes with timestamps, extracted visual frames, native multimodal image observations, and AI summaries. Supports Bilibili, YouTube, Douyin, Kuaishou, and local files.

7 2d ago A 66 tokens original MIT

vision

05

DDDFXYqiming/Agent_Extensions

Skill Claude CodeCodex

A vision skill for recognising and extracting information from local images, using a configured vision model. It includes a script that can describe images and return visible text.

7 2d ago A 45 tokens original MIT

memory

06

DDDFXYqiming/Agent_Extensions

Skill Claude CodeCodex

A cross-session memory system for storing and retrieving verified facts about your computer setup and lessons learned from previous tasks. It separates temporary candidates, environment facts, and reusable procedures.

7 2d ago A 66 tokens original MIT

vision

07

DDDFXYqiming/Agent_Extensions

Skill Claude CodeCodex

A vision skill for identifying and reading information in images, screenshots, and local image files. It can use image paths, pasted images, or clipboard captures as input.

7 2d ago A 50 tokens original MIT