367 results
DSH skill_manage: agent-managed procedural memory. Create/patch/edit/disable/delete skills in ~/.dsh/skills (user scope) or <projectRoot>/.dsh/skills (project scope), with validation, delete guards (agent-created marker, pin, path confinement), disable/enable via disable-model-invocation, and an English trigger-discipline system prompt section. Built on top of skill-filesystem's hot-reload watcher.
Graphical skill manager for DeepSeek Harness — create, edit, import, and delete SKILL.md skills from the web settings UI. · DSH 技能管理器：在网页设置里图形化新建、编辑、导入、删除 SKILL.md 技能。
Windows minimal agent preset for DeepSeek Harness: a one-line fixed persona, gitbash + str_replace_editor + web_search, no runtime context, no compaction. Installs the preset into the user's agent-presets root.
File-change monitor & code editor for the DSH Web UI: watch agent edits land as line-by-line diffs in real time, right beside your conversation, then view and edit any workspace file without leaving the browser.
Tacit learns what you leave unsaid in your prompts — from messy turns and your own corrections, with zero clicks — and tells the agent how to compensate, on every turn, via a system-prompt section you can read and edit.
Prompt Studio plugin for DeepSeek Harness: compose runtime prompts, overrides, and request-local synthetic turns in one live editor
Fylar Office Editor integration for the DeepSeek Harness Web profile, powered by Fylar Office SDK
Fold mis-rendered thinking content into collapsible blocks, render mermaid inline, show file-edit diff counts, rewrite composer drafts with the current model, and resume interrupted turns from the send button.
DSH bundle: workspace file-tree sidebar — browse/edit project files via /api/filetree (host) + client UI
Human-AI collaborative prototyping for DSH, Codex and MCP agents, from product clarification to editable Excalidraw wireframes and verified frontend generation.
WaveSpeed skill for DeepSeek Harness (dsh): generate and edit AI media (image, video, audio, 3D) via the open-source wavespeed CLI.
Skill studio for DeepSeek Harness: visualize all agent skills, view/edit their SKILL.md bodies, toggle model/user invocation, and mine session logs to extract reusable personal skills (auto-loadable by the agent) — from the web settings panel (Skill 工作台) and via skillmgr_* / skillmgr_extract_* tools
VS Code-style workspace file explorer for the DeepSeek Harness Web GUI: file tree with language-colored SVG icons, syntax-highlighted editor, in-window edit & save, rename, new file/folder
Markdown viewer for the dock file explorer: renders .md/.markdown/.mdx files with a one-click switch to the text editor.
Cloud workspaces for DeepSeek Harness: pick "Cloud (SSH)" in the workspace chooser and the agent's bash/read/write/edit/glob/grep tools transparently run on your Linux server over SSH. Includes ssh_* agent tools, an SSH host settings card, jump-host support and persistent connection pooling.
Labnana image generation for DeepSeek Harness: text-to-image / image-to-image / precise editing with credits estimation, subscription balance and web settings UI.
dsh plugin: daily RSS news digest from 46 curated sources, LLM-edited via the model already configured in dsh, delivered to your IM via webhook (ServerChan / PushDeer / WeCom / Telegram / Bark / gotify / custom).
Native DSH tools for Unreal Engine uasset inspection and the Blueprint node edits exposed by built-in UE Python
DSH plugin: parse current session history into editable structured mind maps and export Markdown, Mermaid, PlantUML, XMind text, and TODO briefs.
A DeepSeek Harness Mix plugin for vision routing plus GPT Image generation and editing.
DSH 右侧栏 Excel 编辑插件 v2：支持多工作表、单击选中/双击编辑、多选批量格式、色盘单步撤销、选中动画，并保存回原文件。
Visual Cordis plugin-tree composer for the DeepSeek Harness Web UI.
A stateful, Agent-controllable Jupyter workspace for DeepSeek Harness: a persistent ipykernel runtime the DSH agent can read, edit, execute, and inspect, with VS Code-aligned cell UI and .ipynb save/load.
DeepSeek Harness plugin: per-edit approval with a red/green line diff before write/edit/str_replace_editor — approve once or reject (Claude Code behavior).