Voice input for DeepSeek Harness: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, plus any OpenAI-compatible API of your own).

Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini

Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citation

为 DeepSeek Harness 提供电脑控制插件：新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入（目前支持macos）｜Accessibility-first macOS Computer Use bundle for DSH with fresh observations, stale-state rejection, scoped permissions, and safe input.

Convert a local file (PDF, DOCX, XLSX, HTML, …) to markdown, or answer questions about its content. Use whenever the input is a file path, not a URL.

Git status badges for DeepSeek Harness: an input-row chip and a sidebar session-row action glyph, on every install — no patch and no manual step. Event-driven freshness over SSE.

Local dashboard for Claude Code and Codex CLI sessions: which Claude Code session needs input, every tool call and Claude Code subagent live, token cost and quota, several Claude accounts. Run npx ccdeck.

Edit images with Google Nano Banana 2 (image-to-image edit endpoint) on RunComfy. Documents Nano Banana Edit's strengths (preserve subject identity, swap background, localize edits with spatial language, multi-image batch edits up to 20 inputs), the schema, and when to route to GPT Image 2 edit / Fl

MCP server that gives AI assistants eyes and hands in the Godot editor: scene editing, input injection, deterministic game-time control, and live runtime state for agent-driven playtesting

Enables agents to capture real browser interactions over CDP, compile them into deterministic replay scripts with parameterized inputs and stored secrets, and execute those workflows with real input events — no page re-reading or LLM in the replay loop. Also emits portable Agent Skills from recorded workflows.

Virtual keyboard and gamepad for AI agents on Linux / Steam Deck — zero-dependency uinput daemons with an MCP server interface.

Lets AI coding agents build, test, and lint Android projects with Gradle, control devices and emulators via adb, automate UI through screenshots and input injection, and use a live IDE bridge for refactoring, code inspection, and run configurations. Works with any MCP client over stdio or authenticated HTTP.

Enables Claude and other MCP clients to list and query allowlisted Supabase tables, insert rows, and search, read, or create Notion pages. It ships with table allowlists, validated inputs, row limits, and an optional read-only mode that unregisters write tools, plus a mock mode for trying it without credentials.

Enables keyword search across source-traceable evidence chunks, listing opportunities linked to supporting evidence, and deterministic ROI calculations with model-proposed inputs and TypeScript-computed dollar figures.

Enables control of an attached Android phone over ADB, including screenshots, taps, typing, key/chord input via a virtual HID keyboard, UI inspection, and device information without root.

Enables MCP clients to create and control persistent, PTY-backed terminal sessions on macOS: launch commands and interactive programs, read output incrementally via byte cursors, send keystrokes, wait on conditions, and detect running/awaiting-input/exited states. Sessions run inside a Seatbelt sandbox with command policies, human approvals, secret redaction, and hash-chained audit logging.

Enables stateless, pure-visual control of Android devices and emulators through adb shell, providing screen capture, coordinate-based taps, swipes, keyboard input, and arbitrary adb command execution for agent-driven interaction.

Enables read-only access to Percona Monitoring and Management 2.x through PromQL metric queries and Query Analytics, so clients can list monitored databases, surface the slowest queries, inspect query details, and run validated SELECT queries against QAN's ClickHouse data. TLS verification, input validation, and Viewer-role tokens keep access strictly observational.

Enables AI assistants to inspect and query a TPC-H sales warehouse through read-only, allowlisted catalog tools and schema resources, with ad-hoc SQL disabled by default. It enforces strict arguments and input-free errors, while a differential attack suite verifies that query protections hold across MCP transports.

Exposes a multi-tenant helpdesk over MCP, enabling tool-based ticket, document, and notification operations while applying configurable authorization, tenant-isolation, input-handling, and rate-limit defenses.

Enables Codex sessions to observe and control the Windows desktop through screenshot reasoning, archived-frame inspection, pixel sampling, keyboard/mouse input, and workspace-local multimodal memory.

Enables AI agents to prepare, launch, monitor, inspect, and recover existing Nextflow workflows through MCP tools, while client-side expert skills guide pipeline-specific input selection, parameters, QC, and troubleshooting.

Enables deterministic execution, cryptographic security, and game-theoretic optimization through the Model Context Protocol, returning deterministic JSON tool results for agent telemetry and task inputs.

Enables AI agents to drive remote desktops through the local RustDesk client on macOS, launching sessions, capturing the session window, and injecting keyboard and mouse input. Exposes session lifecycle, screenshot, input, and device book capabilities as MCP tools.