guo6x/dsh-palate
会生长的眼睛:为 DSH 智能体积累设计品味。
Project Overview项目介绍
dsh-palate is a native design review plugin built exclusively for DeepSeek Harness. Unlike most static design review tools that ship a fixed, unchanging set of rules to apply to every design, this plugin builds and grows a personal taste corpus that accumulates experience from every use. It follows a five-step process to build its judgment: observe the target design, stage structured analysis candidates, get explicit user confirmation of candidates, review new designs against accumulated taste, and calibrate principle effectiveness based on user feedback. Each step builds on the previous one to refine the plugin's ability to judge design according to your personal preferences and standards.
When you first install the plugin, it ships with a starter palate of 12 foundational design principles and four teaching examples (one good and bad dashboard, a readable table, and a generic landing page) to get you started. These starter examples are only added once when your local taste database is empty, so installing or upgrading the plugin will never overwrite an existing palate you have built up over time. It also includes two optional opt-in visual reference packs, one for Apple-style product storytelling and one for X-style direct utility, that you can add to your palate at any time to expand its baseline knowledge.
The plugin is open source under the permissive MIT license, and has no additional runtime dependencies beyond a working installation of Node.js version 22 or newer. All training decisions are explicit: the plugin only stages candidates for you to accept or reject, it never automatically adds unconfirmed analysis to your taste corpus. It does not include embedding-based semantic search, relying instead on tag and keyword matching to pull relevant examples and principles for reviews, and requires pairing with an existing vision or browser tool to inspect designs before staging evidence.
dsh-palate 是一款面向 DeepSeek Harness 的原生设计评审插件,和使用固定规则集的静态设计评审工具不同,它通过积累用户个性化的「品味语料库」来实现能力增长,使用越多判断能力就越强。它遵循观察分析、暂存候选、确认决策、参考已有品味评审新设计、校准有效性五步流程,不断累积经验优化后续设计评审结果。
它内置12条基础设计原则和4个入门教学案例(包含好/坏设计示例),还提供两个可选的视觉参考包:苹果产品叙事风格和X直接实用风格,供用户根据场景调用。用户可以引导代理完成设计观察,暂存分析候选,经用户确认后加入语料库,再基于积累的语料评审新设计,适合需要培养个性化设计审美的设计团队使用。
该插件为 MIT 许可开源,不需要额外运行依赖,仅要求 Node.js 版本 22 或以上。它不做基于嵌入的语义匹配,仅支持按标签、关键词检索本地语料,所有训练和反馈决策都需要用户显式确认,不会自动学习,设计观察能力需要配合现有视觉工具或浏览器使用。
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:dsh-palate(guo6x/dsh-palate)
仓库:https://github.com/guo6x/dsh-palate
本站详情页:https://www.yhbd.top/plugins/guo6x-dsh-palate/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 3 · 最近提交 2026-08-30 · 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 3 stars - very few users, little community feedback星标只有 3,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 github:guo6x/dsh-palate
把 guo6x/dsh-palate 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
🍷 dsh-palate — an eye that grows
中文说明 · DeepSeek Harness plugin
Design-audit tools measure with a fixed ruler. dsh-palate trains an eye that grows.
Most design-review plugins ship a static ruleset and apply it forever — use them once or a thousand times, the judgment is identical. dsh-palate is the opposite: it keeps a taste corpus that accumulates. Every example you feed it and every principle you distill sharpens the judgment your agent draws on. The more you use it, the better its eye gets.
Why this exists
Taste is not a gift — it's pattern recognition built from exposure. See enough good and bad design, and the rules emerge. dsh-palate turns that into a mechanism an agent can actually use:
- Observe — inspect a screenshot, URL, or design and name concrete visual evidence
- Stage — turn that analysis into examples and principles that wait in a reviewable candidate queue
- Confirm — only an explicit accept/reject decision changes the corpus; rejected ideas stay visible without changing taste
- Review — critique a new design against the accumulated taste, not a generic checklist
- Calibrate — record which recommendations actually helped; only confirmed helpful principles gain evidence, so the palate compounds honestly
What the agent gets
| Tool | What it does |
|---|---|
palate_intake |
Stage a structured visual analysis as pending example/principle candidates; it never changes taste by itself |
palate_candidates |
Inspect pending, accepted, or rejected visual-training candidates and their source sessions |
palate_decide |
Apply the user’s explicit accept/reject decision; this is the only candidate-to-palate mutation path |
palate_review |
Assemble the accumulated taste (principles + relevant past examples) as context, so the agent critiques grounded in learned judgment |
palate_feedback |
Use a review_id to record whether a critique helped and which principles were accepted or rejected; only accepted principles gain evidence |
palate_add |
Feed an example (good/bad/note + reason + tags) into the corpus — grows the palate |
palate_learn |
Distill a new principle from experience and add it to the codified taste |
palate_packs |
Inspect opt-in visual-reference packs and whether they are already applied |
palate_seed |
Apply one or more visual-reference packs exactly once, without overwriting existing taste |
palate_list |
Browse the accumulated corpus |
palate_principles |
List the codified principles, ordered by evidence |
palate_effectiveness |
See which principles were accepted or rejected in real review feedback |
palate_stats |
How much taste has accumulated: examples studied, principles distilled |
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 →
Minglink/dsh-infinite-gen-4
kenryu42/cc-safety-net
hyhmrright/brooks-lint
toby-bridges/api-relay-audit
hashgraph-online/hol-guard
SeaOf0/dsh-redteam-model
howmp/dsh-pentest
saya-ch/dsh-mobile