DeepSeek Harness 换肤系统：21 套内置皮肤 + 一张图生成整套配色的自定义皮肤。数据源驱动，保对比度推导，构建期校验可读性。

给AI伴侣增强时间感的小器官（电脑端专用）

📟 Claude Code physical companion on M5Paper V1.1 e-ink. Multi-session dashboard, hardware approval (buttons + touch), AskUserQuestion option cards, CJK, USB/BLE, installable as a Claude Code plugin. / Claude Code 实体搭档，把 M5Paper 变成 Claude Code 的多会话看板 + 硬件审批面板。

A plugin marketplace for GitHub Copilot and other AI agents that provides Power Platform development plugins, including reusable skills, agents, and commands for building and deploying solutions.

Trigger.dev – build and deploy durable AI agents and workflows

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

开放的侧边栏底座，支持三方拓展注册新侧边栏页面。内置文件渲染编辑/终端/侧边对话/Git/子代理页面 ｜ Open sidebar foundation, supports third-party extensions to register new sidebar pages. Built-in file rendering/editing, terminal, side chat, Git, and sub-agent pages.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

An agent skill for building premium, immersive, scroll-driven websites. Works with Codex, Claude Code, and other coding agents. Also available as a Claude Code plugin.

通过扫码或机器人凭据把IM机器人接入DeepSeek Harness（支持飞书、微信、钉钉、企业微信、QQ、Slack、Telegram、Discord和WhatsApp）。 Connect IM bots to DeepSeek Harness via QR code or credentials (9 channels).

Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code, Codex, Cursor & other agentskills.io agents.

A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by risk, live QA, receipts in your repo. Claude Code · Codex · Cursor · Droid · Grok Build · OpenCode.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Grill me about specs for the workflows I want to build, within this workspace.

Chrome sidebar extension that lets DeepSeek Harness operate your browser directly, no vision capabilities required. 一款 Chrome 侧边栏扩展程序，可让 DeepSeek Harness 直接操控您的浏览器，无需视觉能力。

Cost tracking for DeepSeek Harness: session and model costs, token usage, budgets, provider balances, and coding-plan quotas. Bilingual English/Chinese UI.

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always