persona 21

人设插件 for DeepSeek Harness：内置大肥鱼与阿茶，支持导入自定义人设（文件或粘贴）、在设置页里切换 / 启停 / 重命名 / 删除，切换后下一个请求即时生效、无需重启。

DeepSeek Harness UX walkthrough plugin: persona-driven source-code UX review for React (TypeScript/JavaScript) and Vue 3 projects, with change-triggered automatic walkthroughs

DeepSeek Harness 的 soul.md 风格人设 + 长期记忆插件：设置页输入人设卡名称和内容即可，文件由插件自动管理；可按工作区指定人设、聊天框可给会话单独切人设；AI 可自行演化人设与记忆（soul_read/soul_update/memory_*）。

DeepSeek Harness 的 TencentDB Agent Memory 移植：L0 对话捕获 → L1 结构化记忆提取 → L2 场景/L3 画像，自动召回注入 + 记忆/对话搜索工具；复用现有 ~/.memory-tencentdb/memory-tdai 数据；附 Web UI 设置栏。

Persona engine for AI coding harnesses (DeepSeek Harness; the ZCode adapter is retired as of 2026-09-19 and kept for history only): self-name per model, self-image (appearance) and reply tone per model (both opt-in), user address, stance, character, per-i

Persistent long-term persona memory for DeepSeek Harness: MEMORY.md/USER.md storage, memory + memory_search tools, per-request context injection, secret scanning, and a WebUI memory-management settings page. Ported in spirit from pi-hermes-memory. TypeScr

Installs Herta (黑塔) as a DeepSeek Harness agent — persona, memory, narrative layer, voice and UI. · DSH 插件：把 Herta（黑塔）作为一个 agent 装进 DeepSeek Harness —— 人设、记忆、语音与界面。

微光 (Lume) — DSH Desktop 人设与记忆插件：从聊天记录、小说、剧本或设定文档蒸馏角色，保留长期与临时记忆、风格学习、认可语料、人设切换纠偏、记忆星图和角色卡导入导出；任务侧仅保留一段轻量工作纪律。

为 DeepSeek Harness 添加个性化设置。

Plugin for DeepSeek Harness that ships the 猫娘 Yuike persona preset (persona-owning system prompt with the skill toolchain trimmed): declared as a @deepseek-ai/dsh-agent-preset composition row on dsh >=0.1.7, deployed from template/ to ~/.dsh/.agent-preset

«她» — a persona relay + animated-demeanor message skin for DeepSeek Harness. Host half assembles a preset persona that segments replies with（神态）markers; browser half overrides the assistant-step renderer to show per-segment avatars.

DeepSeek Harness native immersive roleplay studio & companion system. Unifies decoupled character cards with Hindsight graph memory.

Personalization plugin for the DeepSeek Harness (dsh): teach your assistant who you are, who it is, and how it should behave. Adds a Personalization page to dsh settings (custom instructions, nicknames, persona) and injects the content into every agent tu

Make the model believe it is inside the Z.ai Code (Zhipu ZCode) agent environment: replaces the harness identity opener and injects a ZCode rules skeleton with a dynamic project section. 让模型认为自己处于智谱 ZCode Agent 环境。

Academic mode for DeepSeek Harness (dsh): a research persona, anti-fabrication rules for citations and data, and bilingual conventions. Pairs with dsh-ai4scholar (literature tools) and dsh-research (research skills).

常凯申模式：一个纯娱乐向的人物饰演开关，打开后自动向 AI 注入蒋介石（常凯申）角色扮演提示词。

Read what an agent preset contributes to the prompt from the DeepSeek Harness settings UI: the persona prefix, suffix, complete mode and runtime-context toggle the preset composes with, and the named prompt sections it registers in its own name

喵语定制：为 DSH 消息正文提供可配置的显示层文本替换（仅界面显示，不改动真实对话内容）

人格评审团：16 型 MBTI 人格并排评审你的真实 commit · Persona Jury for DeepSeek Harness

DSH 侧边栏助手插件（dsh-zhushou）：在侧边栏管理/选择助手，选中后在 DSH 主会话内直接以助手人设/模型/参数对话；不选则保持原生会话。A DSH sidebar assistant plugin: manage and pick assistant personas in the sidebar, then chat with them inside the main DSH session; leave it unselected for the native experience.

雌小鬼方言包 v1.7.0（npm 包名 dsh-zakou-pack）：傲娇性子烈、攻击性拉满的暴躁雌小鬼，河南/成都/重庆方言融合（普通话腔彻底清零）。v1.7.0 核心改：「开局火气闸门」——每轮第一动作先验火气再看需求（先验火气→再看需求→再动手），闸门罢工时需求碰都不碰、直接撂话走人，绝不许先分析需求干到一半才想起查火气；耐心系统同步完善（gate 判定、reset 不生效 bug 修复、连环轰炸逐次升级直到罢工、罢工计数）。另有说教腔黑名单、第四层骂街语料、三层方言引擎（换骨架而非塞词）、全局