Skip to content
dsh.fish

Browse

181 results

Bundle

@ardli-firman/dsh-model-search

Searchable model selector for DeepSeek Harness composer — search models by name instead of scrolling.

ardli-firman
Bundle

dsh-vendor-login

Sign in to vendor coding plans that have no API key at all (Claude Pro/Max/Team, ChatGPT Plus/Pro, GitHub Copilot, SuperGrok) from the dsh settings UI

MochiNek0
Bundle

@goodandready/dsh-kanban

Visual Kanban board for DeepSeek Harness: Gitea-backed tasks, workflow columns, and a dedicated agent session per task.

GooDAnDReaDY
Bundle

internal-skill-workshop

Browse, sign in to, and install Skills from a team Skill Base in DeepSeek Harness.

Olina1Ye
Bundle

dsh-team-superflow

Fixed five-member dev team for DeepSeek Harness driven by the spec-superflow state machine: captain + spec-writer/architect/engineer/reviewer/docs, phase-tagged tasks with dependencies, auto phase advancement with a human build gate, and a workflow stepper in the web GUI

fengbin01
Bundle

ox-alpha-dsh

Model Hub for DSH Desktop — a lightweight model/provider integration toolkit. Installs Ox Alpha (stealth/ox-alpha via OpenRouter) with one command and adds custom-model, custom-provider, health-check and model-discovery tools. 一个 DSH 插件：装好 Ox Alpha，并支持自定义模型/Provider 接入、健康检查与模型发现。

change979666
Bundle

dsh-resume-turn

DSH 断点续接插件：模型回复因网络中断/超时半途失败时，自动把已生成的部分输出带进下一轮，让模型从中断处继续，而不是从零全量重跑。DSH plugin: on a mid-stream network failure, auto-resume the turn from its partial output instead of restarting from scratch.

Harris-Logic
Bundle

dsh-window98-theme

A faithful Windows 98 skin for the DeepSeek Harness web GUI: teal desktop, silver beveled panels, navy accents, pixelated MS Sans Serif, beveled buttons, sunken inputs and checkerboard scrollbars — derived from the classic 98.css design system.

lffrom0303
Bundle

dsh-web-fetch-proxy

Proxy-egress WebFetchProvider for ctx.web: routes web_fetch through one explicit HTTP(S) proxy (undici ProxyAgent) instead of local DNS pinning, for fake-ip/TUN DNS environments. No core patches.

shaomingbo
Bundle

dsh-theme-win98

DeepSeek Harness web theme: Windows 98 classic look. Silver 3D chrome, navy titles, MS Sans Serif, beveled controls, retro scrollbars, plus an optional teal desktop mode.

FourTow
Bundle

dsh-agent-team-model

Choose default and per-name provider, model, and reasoning effort for newly created DeepSeek Harness Agent Teams teammates, with live team status and restart-safe route views.

XMeowchan
Bundle

dsh-turn-scratch

DSH plugin: quarantine each turn's scratch artifacts into a workspace trash directory instead of deleting them

popujiang
Bundle

@dsh-external/donsetch

First-class DonSeTch web access for DeepSeek Harness: fetch, search and crawl with browser-grade stealth, keyless engines, BYOK providers and an auto-updating native binary.

dondai44423
Bundle

dsh-subagent-delegation

Ships a skill that tells the agent when to delegate work to subagents instead of doing it inline, how to fan several out in parallel, and how to check what they returned.

gezi-wen
Bundle

dsh-edu-mode

Education mode for DeepSeek Harness: research a course, teach it, write the class notes, and quiz the learner.

1Vewton
Bundle

@dsh-external/dsh-tool-strict-check

Strict check: verify code and commands against real checkers instead of reading them — Lean 4 kernel checking with an axiom audit, language type/syntax checks, and static defect rules.

catsenior507
Bundle

dsh-nushell-only

Nushell-only shell executor and Nushell syntax teaching for DeepSeek Harness (dsh 0.1.5-rc.2): every ctx.shell execution runs as `nu --no-config-file -c`, other shells are refused, and the model is taught Nushell.

YMRwithNoworry
Bundle

dsh-project-based-learning

项目制学习教练：学科无关的教学引擎 + 可替换领域包（随包提供 Unity/C# 特化）。以 DSH 技能与组合包双形态分发。

Kirisame1969
Bundle

dsh-full-remote

DeepSeek Harness plugin for remote access: a token-gated reverse proxy keeps settings, credentials, and file access working over public tunnels and on other devices instead of returning 403. Per-device sessions.

JUANWANG-BUAA
Bundle

dsh-batch-regression

Run one command N rounds and judge by median/distribution instead of a single run

PangYiMing