hellosky983/dsh-skillradar

DSH插件:扫描会话中可见的技能,并根据与近期对话的相关性对其进行排序。

Project Overview项目介绍

This is a native DeepSeek Harness plugin built exclusively for DSH. It scans all skills available to the current active session, calculates a relevance score for each skill by measuring token overlap between the skill’s metadata and the recent conversation text, and supports both English and Chinese text analysis. After scoring, it returns a ranked list of skills that are recommended to load next for the current task. Users can install it directly via the DSH CLI by running dsh plugin add github:hellosky983/dsh-skillradar, or clone the source code and install it locally. It is verified to work with DSH version 0.1.0-rc.6 and newer, with the latest compatibility check completed in August 2026.

When working with multiple skills in a DSH session, both the model and the user often struggle to identify which skill is most relevant to the current task. This plugin solves that problem by providing a clear, deterministic ranked list of skills sorted by relevance. It is designed for users and developers who regularly work across multiple skill domains and want a fast, reliable way to narrow down skill options. After installation, you can invoke it by either asking the agent to scan for relevant skills, or running the skill_radar command directly in the CLI. By default it returns up to 15 top skills, but you can adjust this limit via the plugin configuration.

The plugin runs all scoring locally and does not require any network access, external credentials, or environment variables. It only reads the most recent 8000 characters of conversation text from the current session and the available skill catalog, and does not write any data to your DSH profile or system. It is released under the open source MIT license, and you can configure it to return a maximum number of results or scan a different session than the current active one. If the tool does not appear after installation, you can try restarting DSH or checking your plugin configuration to resolve the issue.

dsh-skillradar 是专为 DeepSeek Harness(DSH)开发的原生插件,功能是扫描当前会话中所有可用技能,基于技能标签和近期对话文本(同时支持中英文)的分词重叠度计算相关性得分,最终输出排序后的推荐技能列表,帮助用户和模型选择接下来要加载的技能。它支持通过 DSH CLI 直接从 GitHub 安装,也可以克隆源码后本地安装,要求 DSH 版本不低于 0.1.0-rc.6,最近一次验证是在 2026 年 8 月。

这款插件解决了 DSH 会话中技能数量较多时,模型和用户都无法快速判断当前任务该加载哪个技能的问题。它面向需要在多个技能领域间切换工作的开发者和普通用户,能够快速提供确定性的技能相关性排序结果,帮助缩小技能选择范围,提升工作效率。用户既可以通过自然语言指令让 agent 调用插件,也可以直接通过命令行触发全量扫描。

插件不依赖外部网络,所有评分都在本地完成,仅读取当前会话最近 8000 字符的对话内容和技能目录,不会写入任何数据,也不需要凭证或环境变量配置。它采用 MIT 许可证开源,用户可以配置返回技能的最大数量,也支持指定扫描非当前会话的技能目录。遇到问题可查看 DSH profile 日志调试。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • 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 add github:hellosky983/dsh-skillradar

把 hellosky983/dsh-skillradar 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-skillradar

Awesome DSH Plugin

A DeepSeek Harness plugin that scans every skill visible to the current session, scores each against the recent conversation text (English + Chinese token overlap), and returns a ranked recommendation of which skill to load next.

Overview

DSH sessions expose many skills, and neither the model nor the user always knows which one applies. This plugin answers "what should I load right now?" with a concrete, ranked answer. It suits agents and users who work across many skill domains and want a fast, deterministic relevance signal.

Compatibility

  • DSH version: 0.1.0-rc.6
  • Mainline: verified against deepseek-harness mainline snapshots of 2026-08-14
  • Last verified: 2026-08-14

Install / Uninstall

Install (from GitHub):

dsh plugin add github:hellosky983/dsh-skillradar

Or clone and install locally:

git clone https://github.com/hellosky983/dsh-skillradar.git
cd dsh-skillradar
dsh plugin add .

Upgrade: re-run the install command after git pull.

Disable temporarily: remove the plugin row from your profile composition, or run:

dsh plugin remove dsh-skillradar

Uninstall: remove the dsh-skillradar dependency and its bundle entry from the profile package.json, then pnpm install.

Quick start

After install and restart, tell the agent:

Scan the current session and tell me which skill fits this task.

or invoke the tool directly:

skill_radar  # with no arguments, scans the current session

Example output:

Skill Radar — 16 skills visible
  100%  github-upload [github, 仓库, readme, 上传]
   85%  cordis-plugin-development [client, host, cordis, run]

Configuration

Option Type Default Description
session_id string current session Session to scan instead of the current one
limit integer 15 Maximum number of skills returned

No environment variables, no secrets, no external configuration files.

Permissions & data

  • Reads: the current session's recent message text (last 8000 chars) and the skill catalog via ctx.skills / ctx.sessionQuery.
  • Writes: nothing. The tool only returns a scored list.
  • Network: none. All scoring is local text analysis.
  • Credentials: none.

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 →

← 上一个 Prev dsh-set-workspace 下一个 Next dsh-overleaf →