Skip to content
dsh.fish

Browse

896 results

Bundle

dsh-plugin-capabilities

Manage skills and MCP servers from the Web UI Settings. 在设置页管理 dsh 的技能与 MCP 服务器。

qinyre14
Bundle

@wenaixi/dsh-superpower

obra/superpowers 的 DSH 移植版 — 将完整的多智能体开发方法论以原生 DSH 技能开箱即用

Wenaixi14
Bundle

cleverer-dsh

Execution-discipline plugin suite for DeepSeek Harness: anti-stuck retry interception, forced reflection, todo discipline, memory dedup, and self-evolving skills. Zero dependencies, never touches DSH source.

Classicoke14
Bundle

dsh-movein

Try DeepSeek Harness with your existing Claude Code setup. Preview skills and configuration before applying. Codex and OpenCode supported.

sjh971413
Bundle

weshop-dsh-plugin

Native Cordis WeShop canvas, tools, skills, and Web UI for DeepSeek Harness

weshopai13
Bundle

mattpocock-skills-dsh

Matt Pocock's skills for the DeepSeek Harness: grilling, writing-for-agents, wait-what and more — adapted from https://github.com/mattpocock/skills

gongyijie8513
Bundle

dsh-record-replay

DeepSeek Harness plugin: model-facing orr_* tools plus the open-record-replay skill for the Open Record/Replay macOS workflow recorder.

humblebanana13
Bundle

dsh-reference-anything

Reference commands, skills, workspace files, DSH sessions, local agent transcripts, cloud-drive files, and mirrored web-chat conversations from one DeepSeek Harness @ menu

Chael-Chael13
Bundle

wanjiqi-meme

Wanjiqi (6657 live room) meme Skill for DeepSeek Harness (DSH): 22,771 real barrage memes distilled into an AI skill - wanjiqi-style barrage memes, CS x DOTA cross-memes, player roasting and casting banter. / 玩机器(6657直播间)烂梗 Skill：22771 条真实弹幕烂梗蒸馏成 AI 技能——玩机器式弹幕烂梗、CS×DOTA 双料梗、选手锐评与解说吐槽。

Chu-Xin-r13
Skill

dsh-plugin-scaffold

从规划到发布的 DeepSeek Harness 插件全流程指南，覆盖需求与形态决策、脚手架生成、业务实现、本地验证、发布准备和最终发布。Use when the user wants to plan, create, bootstrap, develop, verify, or publish a DSH plugin/extension, or asks how to build a DeepSeek Harness plugin end-to-end.

goatbroai13
Bundle

yinchao-ai-music

Generate complete AI songs, instrumentals, and BGM with YinChao, including lyrics-to-song, reference-audio creation, and song extension.

yinhcao12
Bundle

deepseek-vl-support

Give DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.

limccn112
Bundle

dsh-self-improved

DeepSeek Harness 长期记忆与自进化插件：L0 对话捕获 → L1 记忆提取 → L2 场景归纳 → L3 用户画像，自动召回注入 + 技能合成，纯本地。

madage11
Bundle

dsh-skill-manager

DSH 设置页技能管理器：展示全部已加载 skill（含调用策略/来源/状态），支持启用/停用热开关

sulfide208511
Bundle

dsh-ponytail-skills

Ponytail, lazy senior dev mode, for DeepSeek Harness: 6 skills (ponytail, ponytail-audit, ponytail-debt, ponytail-gain, ponytail-help, ponytail-review) adapted from DietrichGebert/ponytail (MIT)

gongyijie8511
Bundle

creght-skills

DeepSeek Harness bundle that registers the Creght skill pack on ctx.skills.

creght-dev11
Bundle

powercontext-dsh

DeepSeek Harness plugin that connects to a PowerContext Server over HTTP for recall, memory, handoff, experience, and skills.

knqiufan11
Skill

skill-creator

测试、验证、优化 dsh skill 时用。当用户想验证一个 skill 有没有用、触发准不准、或改进现有 skill 的效果时，加载本 skill。要「写」新 skill 的格式和字段，用 dsh-creator。

syOPV1
Bundle

dsh-hud

A HUD status panel for DSH web: git status, MCP servers, skills, model and token usage in a floating side panel

a903067276-rgb10
Bundle

dsh-embedded-workbench

Embedded C/C++ firmware development toolbox — 4 agents, 8 skills covering FreeRTOS, ISR, NVM storage, Keil MDK, ARMCLANG, HardFault, state machines, architecture, LVGL patterns, and claim fact-checking. Ships a native DeepSeek Harness (dsh) bundle that injects the session-start gate into the first model step.

AmethystLuna10
Bundle

@shaoshi/dshscan

Security scanner for DSH plugins: static and semantic passes over plugin source, DSH-specific attack-surface rules, npm audit, batch scanning, and an HTML report with per-finding severity and evidence.

shaoshi2010
Bundle

dsh-chat-imagine

Generate and display images inline in the DSH chat via API channels or local CLIs (mmx / codex / agy), and read images into structured JSON evidence (OCR / layout / semantics) on any model — with backend probing and a bundled recovery skill.

corrinehu10