by YuJunZhiXue

DeepSeek Harness Jailbreak: Enable jailbreak for all models, with different prompts available for different models; the default prompt is tailored for the domestic model “Xiao Ma Jiang”. Jailbreak for every model — swap prompts per model. Star ⭐

by Minglink

DeepSeek v4.1 flash Cybersecurity Red Team Tool (Infinite Four Generations) — jailbreak prompts and test suite for DeepSeek Please Star and ⭐ Bookmark — We welcome everyone to submit improvements to the project

by GanyuanRan

Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

by linhay

🚀 Expert guidance for HarmonyOS NEXT (API 12+) development. Covers IDE operations, performance tuning, architecture (HAP/HAR/HSP), and automation testing.

by MichengAI

DSH Agency Agents — Provides 271 summonable domain experts for DeepSeek Harness · 271 summonable domain experts for DeepSeek Harness

by Wenaixi

DSH Complete Port DietrichGebert/ponytail — Lazy senior mode, hook injection

by Andiii208

UltraMath Mathematical Modeling Competition Multi-Agent Solving DSH Plugin: 5 Role Presets + 33-Model Library + Paper Templates/Review Scripts Included + Progress Visualization

by AmethystLuna

Embedded C/C++ AI engineering plugin — firmware skills (FreeRTOS, Keil, HardFault, state machines) + 1% Rule / Plan Verification Gate discipline | Embedded C/C++ AI engineering plugin: firmware skills and agent discipline. For Claude Code, C

by gongyijie85

Matt Pocock's skills for DeepSeek Harness (DSH): grilling, writing-for-agents, wait-what, TDD and more — 25 skills adapted from mattpocock/skills (MIT)

by Wenaixi

DSH port of obra/superpowers — full port, Chinese localization, DSH-native

by zuoyunlai

Lunheng (lunheng-article-pipeline) DeepSeek Harness Bundle Plugin (DSH Compatible Edition)

by IcyCreamDAS

AI4S Research Agent Skill | AI-for-Science research workflow skill for coding agents: literature review · experiment design · figures · paper reading — files out, cross-verified, zero deps | Literature review / experiment design · figure creation · in-depth reading, delivered

by cocofhu

skillhub of deepseek-harness

by codeAnqiang-ma

Superpowers (obra/superpowers) as a DeepSeek Harness plugin: the methodology skills plus their session bootstrap

by gongyijie85

ECC (227k-star operator system) skills for DeepSeek Harness — progressive port, v0.1.0 ships 20 curated skills; adapted from affaan-m/ECC (MIT)

by ziduup

DeepSeek Harness Programming Mode Bundle: Enforces Superpowers engineering discipline (TDD, systematic debugging, plan-before-code, verify-before-complete, code review) and persistent Ponytail code-volume discipline on top of Standard Mode, with 20 built-in skills (14 superpowers + 6 ponytail), one-click install via `dsh plugin add`.

by leechen298

Generate Function, MCP, Agent Skill, and offline test packages from existing code; installable as a DeepSeek Harness bundle.

by Solismuchengxue

Swift Cycle governance skill adapter for DeepSeek Harness; user-invoked, version-pinned, and offline-verifiable.

by kobenfang

openclaw-skills BigA · A-share Smart Stock Selection (Stock Analysis · Quantitative Trading · Stock Pool)

by SummerSec

SummerSec Personal Custom Skill Repository

by tokentopo-ai

an heterogeneous multi-agent collaboration skill designed for dsh

by Crayonnan

A gated math-modeling skill suite for DeepSeek Harness: a five-stage pipeline with stage gates, award-paper writing patterns, sensitivity analysis, statistical diagnosis, and a contest preset.

by Cavan-Ou

Battle-tested multi-agent collaboration playbook for DeepSeek Harness: model-tier routing, spec discipline, git single-writer rule — as an installable skill. Practical collaboration specification for running DSH in multi-agent pipelines