wangzhe04/ruyi-workbench-oss
开源 Windows 本地 AI 工作台｜OpenAI-compatible + Claude CLI，99 个桌面/Office 工具，可回退文件操作与可视化多 Agent 工作流。
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit wangzhe04/ruyi-workbench-oss/.claude ./rig-ruyi-workbench-oss # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/api-debugger .claude/skills/api-debugger $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/browser-debug .claude/skills/browser-debug $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/claude-md-management .claude/skills/claude-md-management $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/code-review-offline .claude/skills/code-review-offline $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/code-simplifier .claude/skills/code-simplifier $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/commit-workflow .claude/skills/commit-workflow $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/devops-ci-local .claude/skills/devops-ci-local $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/document-workflow .claude/skills/document-workflow $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/feature-development .claude/skills/feature-development $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/frontend-design-craft .claude/skills/frontend-design-craft $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/local-docs-context .claude/skills/local-docs-context $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/lsp-local-setup .claude/skills/lsp-local-setup $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/office-automation .claude/skills/office-automation $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/offline-packaging .claude/skills/offline-packaging $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/plugin-development .claude/skills/plugin-development $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/research-synthesis .claude/skills/research-synthesis $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/security-guidance .claude/skills/security-guidance $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/spreadsheet-analysis .claude/skills/spreadsheet-analysis $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/structured-writing .claude/skills/structured-writing $ npx degit wangzhe04/ruyi-workbench-oss/ruyi-workbench/resources/plugins/ruyi-offline/offline-toolkit/skills/windows-control .claude/skills/windows-control
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (20)
API 调试网页调试项目记忆管理离线代码审查代码精简提交工作流本地 CI 校验文档处理功能开发前端设计精修本地文档检索本地语言智能Office 自动化离线打包插件开发调研与综合安全加固表格分析结构化写作Windows 桌面操控
Hooks (1)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | $CLAUDE_PROJECT_DIR/.claude/hooks/session-start.sh |
Similar rigs
yazelin/personal-brand-site-starter
把一個人的話問出來，做成一頁式的個人品牌網站。給 AI 代理人照著跑的四階段流程：訪談、選型、建站、驗收。零依賴，四種風格，四種會流動的首屏。
Pragmatist 899 tok ·
UiPath/coder_eval
Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.
Pragmatist 5.1k tok ·
JimLiu/baocut
BaoCut: an AI video agent with an editable timeline. Transcribe, subtitle, translate, dub, cut and animate.
Skill Collector 3.2k tok ·
intentic/intentic
An open-source workspace for coding agents, running on your own machine. More work. Less AI waste. Same subscriptions.
Skill Collector 6.6k tok ·