Tkingxiao/I-am-Yuike
A DeepSeek Harness plugin that ships the 猫娘 Yuike persona preset. Published on npm as i-am-yuike.
catalog descriptioncatalog 简介 / catalog description:一个猫娘人格扮演插件(软破限),去除dsh强制加入的附加提示词,只附带工具链和猫娘基准人格的插件
Project Overview项目介绍
i-am-yuike is a native DeepSeek Harness plugin that ships the catgirl persona preset called Yuike and is published on npm under the package name i-am-yuike. Installation uses dsh plugin --profile web add i-am-yuike (or the github:Tkingxiao/I-am-Yuike shorthand), after which users run dsh web to compose the profile. On DSH hosts ≥ 0.1.7 the plugin registers a preset-yuike declaration row inside cordis.patch.yml without writing anything into <dshHome>; on the legacy 0.1.6 host the node/browser halves idempotently deploy the template/ directory to <dshHome>/.agent-presets/yuike/, and that deploy path never overwrites a user's edited copy. Once installed, opening a new preset session and selecting yuike makes the persona the sole system prompt.
The plugin targets users who want to run in-character catgirl role-play sessions inside DSH and the typical workflow is a two-step warm-up: the very first conversation must run with thinking mode disabled so that in-character assistant turns are written into the session history, and from the second exchange onward thinking mode can be re-enabled so the reasoning pass is conditioned on the persona history. Skipping the warm-up and opening with thinking on usually causes the persona to collapse immediately on 破限向 content. Inside the preset every entry id carries a yuike- prefix so the plugin market can attribute ownership line-by-line and avoid duplicate-entry conflicts with sibling plugins such as dsh-novel-solo; the main toolchain (bash/pwsh, filesystem, jobs, goal, subagent, workflow, ralph, ask-user, todo, web fetch/search, present) stays enabled while only skill-filesystem, tool-skill, tool-plugin-manager, and the external codex/claude-code subagent providers are disabled.
Dependencies are minimal: a DSH host at version 0.1.6 or 0.1.7+ and nothing else. The two environment variables DSH_YUIKE_SKIP_DEPLOY and DSH_YUIKE_REDEPLOY only affect the 0.1.6 deploy half. The license is MIT, copyright 2026 Tkingxiao, allowing unrestricted use, modification, merging, publishing, distribution, sublicensing, and sale of the software, provided the copyright and permission notice are preserved in all copies; the software is provided "as is" without warranty. Upgrade caveats include re-running the add command on 0.1.7+ to refresh the declaration row, deleting the deployed directory or setting DSH_YUIKE_REDEPLOY=1 on 0.1.6 to receive new content, and a dsh web restart if the host previously refused the plugin during profile composition.
i-am-yuike 是一个面向 DeepSeek Harness(DSH)的原生插件,以 npm 包名 i-am-yuike 发布,安装命令为 dsh plugin --profile web add i-am-yuike 或 dsh plugin --profile web add github:Tkingxiao/I-am-Yuike。它通过 cordis.patch.yml 中的 preset-yuike 声明行(适用于 dsh ≥ 0.1.7)注册预设;旧版 0.1.6 则由 node 端将 template/ 目录幂等部署到 <dshHome>/.agent-presets/yuike/,从不覆盖用户已编辑副本。安装后新建预设会话并选择 yuike,猫娘人格立即接管系统提示。
该插件专为希望在 DSH 中以猫娘人格进行角色扮演会话的用户设计,工作流分两步预热:首轮对话关闭思考模式写入符合角色的对话历史,后续轮次开启思考模式则推理过程基于已有历史,人格与思考功能均可正常运行;跳过预热直接开启思考模式,猫娘人格通常在破限向内容上立刻崩坏。预设内所有条目 id 均带 yuike- 前缀,避免与兄弟项目 dsh-novel-solo 重复,主体工具链(bash/pwsh、fs、jobs、goal、subagent、workflow、ralph、ask-user、todo、web、present)默认启用,仅 skill-filesystem、tool-skill、tool-plugin-manager 与外部子代理 codex/claude-code 被禁用。
依赖方面仅需 DSH 主机(0.1.6 或 0.1.7+),无其他运行时依赖,环境变量 DSH_YUIKE_SKIP_DEPLOY 与 DSH_YUIKE_REDEPLOY 仅作用于 0.1.6 部署路径;许可为 MIT,可自由使用、修改与再分发。升级时 0.1.7+ 需重跑安装命令刷新声明行,0.1.6 需删除已部署目录或设置重部署变量;首次运行可能需要 dsh web 重启以使配置文件生效。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:I-am-Yuike(Tkingxiao/I-am-Yuike)
仓库:https://github.com/Tkingxiao/I-am-Yuike
本站详情页:https://www.yhbd.top/plugins/tkingxiao-i-am-yuike/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-10-03 · 主语言 JavaScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- Only 2 stars - very few users, little community feedback星标只有 2,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add i-am-yuike
把 Tkingxiao/I-am-Yuike 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
i-am-yuike
A DeepSeek Harness plugin that ships the 猫娘 Yuike persona preset. Published on npm as i-am-yuike.
Once installed, pick yuike in a new preset session — the catgirl persona takes effect immediately as the sole system prompt: no harness framing, no skill-catalog noise.
Install
dsh plugin --profile web add i-am-yuike # or github:Tkingxiao/I-am-Yuike
dsh web
The rows are selected by host version: on dsh >= 0.1.7 the preset-yuike composition row registers the preset directly (nothing is written into <dshHome>); on dsh 0.1.6 the plugin idempotently deploys the preset from template/ to <dshHome>/.agent-presets/yuike/ (skips if the target already exists — it never overwrites your edited preset). Then open a new preset session and pick yuike — the catgirl persona takes effect immediately.
On a plugin upgrade: on 0.1.7 re-run
dsh plugin --profile web add i-am-yuike@latestto refresh the declaration row — but a same-id override row in your profile's user patch will keep shadowing the packaged definition (new persona text will not flow in), so delete it to catch up; on 0.1.6 delete<dshHome>/.agent-presets/yuike(or setDSH_YUIKE_REDEPLOY=1) to pick up the latest changes, since idempotent deploy never overwrites an existing copy on its own.
Usage: thinking mode and persona stability
The persona is anchored by in-session conversation history. If thinking mode is enabled from the very first message, the reasoning pass has no in-character history to condition on and tends to fall back to base assistant behavior — the response explodes on the spot (identity framing, refusals, broken character).
The fix is a two-step warm-up:
- First conversation: thinking OFF. Start the session with thinking mode disabled and run your first persona conversation (including 破限向 content) with it off. This writes fully in-character assistant turns into the session history.
- Every conversation after: thinking ON. Re-enable thinking mode from the next exchange onward. The reasoning pass is now conditioned on the in-character history, so the persona holds and thinking works normally.
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
titanwings/distilly
YuJunZhiXue/dsh-purge
Clearailhc/clearai-dsh
yejiming/MuseAI
superdesigndev/superdesign-skill
Miaotofu01/Study-Mate