dsh-repair

DeepSeek Harness Development & Runtime Low risk

Ships a skill plus six Node scripts for a DSH install that will not come up - walking the boot stages before readiness, the plugin dependency bridges and junctions under a profile, dead or duplicated plugin rows, and the upgrade path. The scripts are diagnostics first; the rebuild helper only writes when it is given --fix.

携带一份技能加 6 个 Node 脚本，用来处理装完起不来的 DSH——沿 readiness 之前的引导阶段、profile 下的插件依赖桥与 junction、失效或重复的插件行、以及升级路径逐段排查。脚本默认只诊断，重建脚本只有显式加 --fix 才写盘。

How to install

DeepSeek Harness dsh plugin add dsh-repair

About

dsh-repair 一个 DSH 插件，内容只有一份技能：安装时把包内的 skills/ 注册为一个技能根，于是这份技能随插件进入 agent 的技能目录。 sh dsh plugin --profile web add dsh-repair 技能覆盖什么 **起不来怎么查**：boot 崩在 readiness 之前（ERR_MODULE_NOT_FOUND、cannot resolve profile bundle）、插件 node_modules 里 junction/symlink 穿透损坏、树外插件的依赖桥悬空 **活着但残废**：服务静默失效（模型页缺提供方、按钮死）、配置能解析但 apply 抛异常、适配器静默丢弃它目录里没有的模型 id、日志干净却功能死了 **依赖桥**：树外插件（link:）拿不到宿主核心包时的桥机制，以及 bridge-doctor.js / bridge-rebuild.js 的体检与重建 **升级 DSH**：升级前停实例、备份、隔离预演；升级后的三层验证与 settings.yaml 复查 **Windows 远程作业**：跨机经 SSH 收拾 Windows 上的 DSH 时的一整份坑清单（进程生命周期、引号转义、PowerShell、pnpm junction、路径漂移） scripts/ 里六个脚本随技能一起发：bridge-do…

GitHub ↗

Recommendation signals

54 Tool quality · Based on stars, downloads, maintenance, security and docs

– User interest · Adjusted by in-site views, install copies and download clicks

54 Overall

0views

0unique visitors

0install copies

0download clicks

0outbound clicks

Links

GitHub ↗ npm ↗ Homepage ↗ Report issue ↗

Basic safety check

Findings: None
Sources: curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics: deepseek-harness, dsh, dsh-plugin, skill

Related plugins

MCP Server

Score100

langfuse

langfuse/langfuse

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

☆ 34.9K ↓ 6.5M Development & Runtime ↗

Claude Code

Score92

claude-code-templates

davila7/claude-code-templates

CLI tool for configuring and monitoring Claude Code

☆ 30.9K ↓ 9.9K Development & Runtime ↗

Claude CodeCodex

Score84

cc-safety-net

kenryu42/claude-code-safety-net

A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

☆ 1.6K ↓ 25.2K Development & Runtime ↗

Claude CodeCodex

Score82

loki-mode

asklokesh/claudeskill-loki-mode

Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 8 quality gates.

☆ 1.1K ↓ 12.6K Development & Runtime ↗