Agent preset
dsh-factor-investing
A DeepSeek Harness (DSH) agent preset for institutional multi-factor stock-selection research: methodology knowledge base + zero-dependency factor statistics.
Nzssm16
Browse
23 results
Agent preset
dsh-big-fat-whale-maid-adaptive
大肥鱼女仆长智能体，用风神与明神插件vibe而来，解决wsl与windows互通问题
CanaryJing
Agent preset
dsh-character-presets
DSH 角色预设集：10 个角色共用一套六层情感引擎——露娜 / 小喵 / 绯音 / 凛 / 芽衣 / 白夜 / 阿尔玛 / 小铃 / 三千代 / 灰
wwwangzilin4
Agent preset
dsh-omnipotent-preset
Omnipotent agent preset for DeepSeek Harness: Standard/PTC/Minimal + routing modes
aorucshiea
Agent preset
Project-Memory-Agent
Project Memory gives coding agents a single, trustworthy memory for a software repository — so they stop re-learning the same facts and stop writing conflicting "memory" files.
LoveDoLove3
Agent preset
dsh-mini-win
Windows-friendly minimal agent preset for DeepSeek Harness: sandboxed pwsh, native cmd.exe, and str_replace_editor.
GitRuozhi2
Agent preset
ds
LMA (Layered Memory Architecture) 是一个为 DeepSeek Harness 设计的地基插件（Foundation Plugin）。它定义了 “记忆体（Memory Body）” 这一抽象概念及其挂载/卸载协议。 它与其他记忆插件的本质区别在于：LMA 是一个容器和载体，让 dsh-memory-evolve、EchoCore 等“能力性插件”可以挂载其上，它本身也内置了一套可开关的基础记忆流程，作为可选能力。LMA结束记忆功能的“一锅乱炖”，实现跨会话的结构化记忆机制。(目前功能还在持续完善以及测试，对于其他插件的接口在构想完整后逐步推动)
szx-a2
Agent preset
dsh-a-stock-five-dimension
A DeepSeek Harness (DSH) community agent preset for rigorous A-share five-dimension (technical/valuation/fundamental/capital-flow/news) standardized analysis: persona, skill knowledge base, hard risk gate, deterministic Python scoring core, Tencent-first collectors. Not an investment recommendation.
Nzssm12
Agent preset
math-agent
Math_Agent: a math training/coaching agent preset for DeepSeek Harness, with a programmatic zero-leak output guard that never reveals answers
RepInS-011
Agent preset
dsh-browser-pilot
Browser automation tools for the DeepSeek Harness (DSH) agent - a self-contained Cordis agent-preset plugin (Playwright).
momo-gen1
Agent preset
life-distiller
这是一套用来“蒸馏人生”的 Skill 系统。 它会把人生经历整理成一条可回看、可补充、可迭代的本地记忆链，支持访谈构建、记忆重历、角色扮演、蒸馏复盘，以及后续的查看与分享。
Xiangbingyu1
Agent preset
dsh-multi-task
A prototype Multi-task Agent Preset for DeepSeek Harness.
L1ttleBad1
Agent preset
dsh-strategy-deployment-review
DSH agent preset for rigorous strategy live-deployment testing/evaluation. Retest.
Nzssm11
Agent preset
novel-writing-plugin
DeepSeek Harness plugin for long-form Chinese AI novel writing: layered context, foreshadowing ledger, anti-AI-cliché redlines. 13 个 novel_* 工具，零依赖 JavaScript。
bbaz1231
Agent preset
scaefy-video-production
Code-generated video production skill pack — engine-neutral, free and offline at its core, gated by measurements instead of opinions.
fatihtoprakk1
Agent preset
dsh-bioinfo
生信模式 (Bioinformatics Mode) — research-grade protein structure & interaction agent preset for DeepSeek Harness: AF2-Multimer, ESMFold, AutoDock Vina, MM-GBSA/MD, structure QA, virtual screening.
Paraso42
Agent preset
dsh-adaptive-anchored-standard
dsh-adaptive-anchored-standard
uruana33
Agent preset
dsh-artist-mode
DSH 艺术家模式 — 对话式设计交付预设（HTML 原生设计 / 反 AI slop / 5维评审 / Agnes AI 生图生视频）
Asher-2000
Agent preset
dsh-router-sci
科研计算 Agent 预设 — 核工程粉体/多相流仿真（LAMMPS + Fluent DPM + LaTeX）的 dsh agent preset
Aone2233
Agent preset
LLM-for-novel-with-history-and-superheroines
LLM-for-novel-with-history-and-superheroines
bigscientist
Agent preset
dsh-mathmodel-v7
数学建模竞赛 Agent（DeepSeek Harness preset）v7：CUMCM 国赛专项，资产接管→Discovery+竞争搜索→方法学契约→代码图表→编辑/视觉证据链→论文→全门禁验收，含 CUMCM Typst/LaTeX 双模板与 2026 国赛规则 authority
ubggyhjb
Agent preset
DSH-EditApart
A schema-driven, automation-first video + photo editor preset for DeepSeek Harness: deterministic render -> critique -> revise, with the edit decision as an auditable, trainable object. Part of the EditTogether collection.
EditTogether
Agent preset
dsh-gpt-agent-preset
为 OpenAI GPT-6 系列调优的 DeepSeek Harness Agent 预设：把'防止空转'做成识别无进展而非限制调用次数 / An execution-first DeepSeek Harness Agent preset for the OpenAI GPT-6 family
Starlight-bananice