为下一个工作流
找到对的 DSH 插件

A web-novel writing engine for DeepSeek Harness: parallel drafting, outlining and brainstorming with a separate DeepSeek key, lore and foreshadowing management, semantic vector retrieval, a corpus library, usage ledger, mechanical proofreading, and a local serialization plan.

Host-side Typert remote for dsh-tool-writing: serves project volumes, chapter status, corpus library, full-text search, evolution entries, and thread-graph data to the client writing panel.

AI paper-writing style guard: scans manuscripts for revision-process residue, defensive writing, and AI-writing tells (em-dash abuse, not-X-but-Y, LLM overused words, rule of three); writing_audit + writing_rules tools with auto-audit on paper file writes.

MCP bridge to gemini.google.com: vision analysis of images and videos, Imagen image and Veo video generation, and conversation management using the logged-in browser session with no API key.

Curated MCP server bundle: one install brings demo, memory, filesystem, GitHub, Playwright and remote HTTP MCP servers, plus a connectivity verifier tool and CI checks.

DSH↔Godot engine runtime bridge: launch and drive a running Godot 4.x game through its in-game TCP interaction server — 8 tools (scene/UI inspection, GDScript eval, input simulation, screenshots, headless static ops, script validation), replaces godot-mcp.

Privacy-safe local scanner for Codex, Claude Code, WorkBuddy, and CodeBuddy session/workflow metadata; persists aggregate evidence and recommends built-in DSH agent presets without retaining content, using a network, or changing presets.

Blender 3D production plugin with 30 modeling/reconstruction skills, 13 runtime tools, and 26 deterministic helpers for reference fitting, rendering, validation, animation, and portable export; installable as `dsh-blender`.

Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed to text via any OpenAI-compatible VLM before reaching the text-only DeepSeek — a keyed fast path (default qwen3.7-flash; DashScope/Zhipu/OpenRouter or any OpenAI-compatible endpoint) with your own key, or local Ollama auto-detected with zero config.

Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.

External vision plugin for DeepSeek Harness: whale-button config panel, image recognition with auto-reply, and agent screenshot/recognize tools.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.

Undo/redo & rollback system for DSH: every config change is auto-snapshotted; undo/redo/restore to any version from the WebUI or the offline CLI/GUI tools (works even when DSH fails to boot).

One shell tool for PowerShell / Git Bash / WSL on Windows plus an interactive PTY terminal; the default terminal is chosen by the user in DSH settings.

Download progress panel: URL downloader, agent shell/SSH transfer tracking and workspace black-box file-growth monitoring, shown in a draggable floating panel with live bytes, speed, percentage and ETA.

Bilibili video analysis: metadata, transcript (ASR fallback via Bijian/sherpa-onnx/whisper.cpp), comments, danmaku, and sharp keyframes with optional local vision descriptions.

Vision tasks for text-only models: intent-aware image Q&A, long-screenshot OCR, UI reproduction, grounding, and pixel diff.

Codex-backed `web_search`, `image_gen`, and `image_vision` tools for DeepSeek Harness, reusing ChatGPT OAuth login state.

HeartFlow (心虫) AGI layer-1 discriminator gate as a DSH plugin: 47-dimension rule-based text checking (heartflow_check tool) plus automatic output supervision at tools/post-execute, fail-closed when engine missing.

Create and manage sandboxed JavaScript tools with a Monaco editor and model-driven tool lifecycle.

Complement to official Creator mode: stage, validate, live-mount via ctx.plugin, score, and solidify or roll back in-memory tool-plugin trials.

Text-first computer use for DSH: background Chromium control via Playwright/CDP plus accessibility-first macOS control; actions stay pinned to the right process and window without taking the user's pointer, ships a Developer ID signed, notarized Universal 2 DMG.