Zenjibad/skill-injector-plugin
自动将用户选择的技能(如“穴居人”、“马尾辫”)注入DeepSeek Harness会话中:每次提示或会话开始时注入一次,并设有设置页面和编辑器指示器。
Project Overview项目介绍
This is a native plugin built exclusively for DeepSeek Harness (DSH) that automatically injects user-selected skills into every new DSH session. It supports two injection modes: injecting the skill content with every user prompt, or injecting it once only when the session starts. It includes a dedicated configuration settings page and a status indicator that displays active skills directly under the chat composer input area. To install it, you run the dsh plugin add command from your DSH terminal, pointing to either a local checkout of the repository or the GitHub URL directly, then restart DSH to activate it.
The plugin is designed for DSH users who regularly rely on specific custom skills and want them active automatically across all sessions, eliminating the need to manually invoke the skill each time you start a new chat. On the settings page, you can check the box next to any skill you want to enable, select your preferred injection mode, and save your changes. The plugin pulls skill content directly from DSH’s live skill registry at load time, so it never copies skill files to its own directory, and it automatically applies injections to all subagents to keep voice consistent across the entire agent tree.
This plugin is released under the open source MIT license, and it only reads from the skill registry, never modifying, creating, or deleting any skill files. All user configuration is stored in DSH’s native user settings store, same as other DSH settings, and all injected content comes from local trusted skill files, no external network content is pulled. It uses DSH’s official design tokens to match your active theme, persists across DSH restarts, and requires only one installation to work automatically on every subsequent boot of DSH, no extra configuration is needed after the initial install.
这是一个专为DeepSeek Harness (DSH)开发的原生插件,功能是自动向DSH会话注入用户选中的技能,比如常用的/caveman、/ponytail技能。它支持两种注入模式:每轮提示都注入,或是仅在会话开始时注入一次,同时自带设置页面和输入区下方的注入状态指示器。用户可以通过DSH的dsh plugin add命令从本地目录或GitHub仓库安装该插件,安装后需要重启DSH才能生效。
该插件面向需要在每次会话中固定启用特定技能的DSH用户,省去了每次手动输入技能调用指令的重复操作。在设置页面,用户可以勾选想要启用的技能,选择注入模式后保存配置,插件会实时从DSH的技能注册表读取技能内容,不会复制文件到本地。它还支持对子代理注入技能,保证整个代理树的输出风格一致。
该插件遵循MIT许可证开源,不会对技能注册表进行写操作,所有用户选择都存储在DSH的用户设置文档中,注入的内容均来自本地可信的技能文件,不会从网络拉取内容。插件使用DSH官方的设计令牌适配主题,能够跟随系统主题自动切换配色,安装后会随DSH启动自动加载,一次安装永久生效,无需每次会话重新配置。
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:skill-injector-plugin(Zenjibad/skill-injector-plugin)
仓库:https://github.com/Zenjibad/skill-injector-plugin
本站详情页:https://www.yhbd.top/plugins/zenjibad-skill-injector-plugin/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 5 · 最近提交 2026-09-13 · 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 5 stars - very few users, little community feedback星标只有 5,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:Zenjibad/skill-injector-plugin
把 Zenjibad/skill-injector-plugin 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
skill-injector-plugin · Auto-Inject Skills into DeepSeek Harness (DSH)
Auto-inject user-chosen skills (e.g.
/caveman,/ponytail) into every DSH session — every prompt or once at session start — with a settings page and a composer indicator. 在 DSH 会话中自动注入所选技能(如 /caveman、/ponytail):每轮提示或仅在会话开始时,含设置页与输入区指示。中文文档: README.zh.md · LLM index: llms.txt · Agent guide: AGENTS.md
Keywords: dsh-plugin · deepseek-harness-plugin · skills · skill-injection · caveman · ponytail
📑 Table of Contents
- ✨ Features
- 🏗️ How it works
- 🚀 Quick start
- ⚙️ Configuration
- ❓ FAQ
- ⚠️ Security notes
- 📦 Project structure
- 🙏 Credits
✨ Features
| Feature | Description |
|---|---|
| ⚙️ Settings page | Settings → Skill Injector: checkbox list of available skills, injection-mode radio, save; unresolved skills are listed with the reason and a Retry button (plus Remove once a session has established scope) |
| 🪧 Composer indicator | One line under the chat input: Injected Skills: caveman, ponytail · Mode: each-prompt, refreshed every 5s (with a · N unresolved suffix while skills are unresolved) |
| 🔁 Two injection modes | each-prompt (system-prompt section, re-rendered every request) vs start-only (one durable skill-invocation message stamped at session start) |
| 📚 Live skill registry | Reads skill bodies from ctx.skills at load time; no copied files; each selected skill is classified (ready / unknown / unavailable / load-failed / no-scope) and a transient failure keeps injecting the last-good body |
| 🧩 Subagents included | Injection applies to subagents too (consistent voice; no filtering) |
| 🌗 Theme-aware | All colors use --dsw-alias-* design tokens |
| ♨️ Survives restarts | Real profile-bundled plugin: install once with dsh plugin add, auto-loads on every DSH boot — no per-session define, no cordis_define |
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 →
Jungod1121/dsh-anchored-standard
lilyblessing/dsh-mcp-skill-panel
SaiSenBox/dsh-prompt-manager
jiesou/dsh-stream-rules