gzh-holebright：把公众号写稿、配图到草稿箱串成一条 Agent 工作流
gzh-holebright 是 SkillHub 社区 Skill（@user_4320bbee/gzh，v1.0.0），面向微信公众号运营，将 AI 写稿、封面与正文配图、图片压缩、Markdown 转微信 HTML、推送草稿箱串成六步工作流，支持干货/情感/资讯/活泼等风格。本文基于 SkillHub 页面与安装文档说明定位、功能、skillhub CLI 安装路径（Cursor/Claude Code/Codex）及 requires_api_key 等注意事项，并给出官方技能页与 API 地址。
Read Moredsh-ppt-maker: DSH Web Plugin: One-Click End-to-End PPT Workflow Orchestration
The DSH (DeepSeek Harness) plugin `dsh-ppt-maker` provides a solution for authoring complex PPT generation workflows under a Web Profile. By encapsulating a 58KB orchestration prompt, it enables fully automated end-to-end workflows. Users can launch it with a single menu click; it supports either AI image generation or programmatic graphics, and includes a built-in HTML-to-PPTX conversion pipeline to ensure stable output. The workflow involves headless browser rendering and sandbox operations, requiring users to send a one-time permission command to bypass security pop-ups. The plugin uses a self-contained design, does not consume context, and ensures offline availability and security.
Read MoreDeepSeek Harness Plugin: dsh-academic-research Academic Research Pipeline
This article introduces a DeepSeek Harness (DSH) plugin designed specifically for academic research. Inspired by well-known projects, it aims to automate the entire workflow—from defining research questions and searching and verifying literature, to synthesizing findings, assisting with writing, and conducting final review—through an “everything is a plugin” approach. The plugin supports research pipelines and helps improve academic efficiency. Users should pay attention to permission isolation and license compliance; see its GitHub repository for installation and usage details.
Read Moredsh-polling: Add polling and scheduled task capabilities to DeepSeek Harness
dsh-polling is an MIT-licensed plugin for DeepSeek Harness designed to transform naturally described recurring tasks into Cron-driven scheduled polling tasks. It supports creating, editing, and managing tasks via natural language, making it suitable for scenarios such as periodically checking folders and web pages, scraping data, generating daily and weekly reports, and executing scripts. Core features include automatically parsing task requirements described in natural language using built-in model tools; executing tasks in independent real sessions without interrupting the current conversation, supporting multiple execution modes; and providing a Web UI for viewing task lists, searching, immediate execution, starting, stopping, and deleting tasks. The scheduling mechanism features a smart catch-up function (executing the most recent missed task upon startup after missing a scheduled time) and an anti-overlapping mechanism (newly triggered tasks during execution are skipped). Installation requires the dsh CLI.
Read More