
Compare multiple skills on the same task and pick the winner.
Install Forkprobe
Likely fails to load: not on npm, needs a build, and ships no `prepare` script — a git install fetches sources, not built artifacts, so the entry point is never produced.
This install is expected to fail
prepare script to run it, and is not published to npm — so nothing produces the compiled output the loader then goes looking for.Three things would fix it, all of them on the author's side: publish the package to npm, add a prepare script that builds on install, or commit the build output to the repository. Until one of those happens, the command below is here so you can reproduce the failure, not so you can install it.
What would be run — expected to install and then fail to load
# 1. add the bundle to a profile — --profile my-profile points at $DSH_HOME/profiles/my-profile
dsh plugin --profile my-profile add github:Jayden-X-L/forkprobe
# 2. verify: the bundle should show up as a layer in the resolved config
dsh --profile my-profile --dump-config
# 3. boot the profile
dsh --profile my-profileBefore you run it
- A plugin runs with your permissions once loaded: it can read your files, use your credentials and reach the network. Tool approvals do not sandbox it.
- Installing from git resolves a moving branch. Pin a commit —
github:Jayden-X-L/forkprobe#<commit-sha>— so the code you reviewed is the code you install.
Prerequisites
- API key
- Required — see the repository README for which provider.
- Network access
- Not required at runtime.
- Language
- Python — a git install pulls this source, not build output.
Install check
Every field the verdict was derived from, so you can re-derive it yourself
| Field checked | Result | Weight | What the spec says about it |
|---|---|---|---|
| lifecycleScripts | pass | info | no install-time scripts |
| dsh.bundle | pass | fatal | package.json declares a `dsh.bundle` layer |
| dsh.bundle.patch file | pass | fatal | patch file present at `dsh-plugin/cordis.patch.yml` |
| npm registry | missing | warn | `forkprobe-dsh` is not published to npm |
| prepare script | missing | fatal | needs a build but ships no `prepare` script — a git install fetches sources, not built artifacts |
- Verdict reason
- git-only + needs build + no prepare script
- package.json read
- package.json
- Rules applied from
- docs/user/develop/basic/publish.md
- Checked at
- 2026-08-15
From the README
Excerpt as published by the author, plain text, unedited
· · · ForkProbe 是一个 AI Skill 选型与试跑工具。它会把同一个任务交给模型本身和多个候选 skill,并排试跑,生成本地 HTML report,让你看到真实输出之后再选择 winner。 **v0.10 新增 DeepSeek Harness 原生插件:** DSH 用户可以直接安装 `forkprobe-dsh`,通过原生 `forkprobe_compare` 工具并行启动候选 subagent,打开同一套本地 Report,并在点击“继续”后把用户选择的结果返回当前 DSH Agent。插件不再嵌套启动第二个 `dsh` 进程,也不会复制 DSH 凭据;安装前的用户确认、本机 Skill 扫描、候选去重、匿名 Winner 分享和此前全部场景继续支持。 选定 winner 后,Report 的“继续”按钮会同时保存本地 handoff,并让 Agent 沿胜出 Skill 继续任务。用户可以在同一区域选择是否匿名分享本次 Skill 选择,为未来的社区推荐先验积累样本。 当网络上的 skill 越来越多时,问题不再是“有没有 skill”,而是“当前任务到底该用哪个 skill”。ForkProbe 的目标很直接:先把结果摊开,再让 Agent 沿着你选中的路径继续工作。 - 你不确定当前任务该用哪个 skill,想先看真实输出再决定。 - 你想比较 baseline 和多个 skill,而不是只相信 skill 的描述。 - 你的交付物是 PPTX、科研 figure package、调研报告、可运行网页或视频成片,需要看文件、预览和 QA。 - 你想从本机已安装 Skill、EverMind Skill Hub、GitHub 或 BYO 路径中找到候选,再做一次小规模试跑。 - 不适合简单确定性任务:如果答案或工具路径已经很明确,直接执行
Topics
GitHub topics on this repository
More in Agent Skill Mcp Installable
Ranked by similarity inside the cluster, not alphabetically
Dsh Wuyun Liuqi
dhicoc
五运六气(运气学)AI Agent 技能包的 DeepSeek Harness(dsh)Cordis 插件:31 个 SKILL.md 技能原样封装,一行 dsh plugin add 安装。
Dsh Plugin Dev Skill
SmileTao
帮助 AI 正确地编写 DeepSeek Harness (dsh) 插件的skill
Dsh Plugin Builder
kingjly
Agent Skill that turns a capability into an installable DeepSeek Harness (dsh) plugin. | 把能力做成可安装 dsh 插件的 Agent Skill
Feedback Plugin
baizz1
学情阶段反馈 DSH 插件包:skill 编排 + Playwright MCP 浏览器工具供给,辅助老师在 follow-class-reminder 网站配置家长反馈评语模板
Dsh Hyperframes
STARDUSTLC666
DSH 视频创作技能插件:注册 HyperFrames by HeyGen 官方移植技能五件套(HTML 写视频/CLI/注册表/网址转视频/GSAP),安装即用。· HyperFrames skill plugin for DeepSeek Harness.
Dsh Fail Logger
Areium
DeepSeek Harness(DSH)插件:自动记录所有执行模式(原生工具 / PTC run_code / 代码内嵌工具调用)的工具失败错因,去重、计数、确定性排序后沉淀进 skill 的机器维护实录区段——让 Agent 越用越少错。