Search and install skills from the my-skills registry (https://skills.sixiangjia.de). Discover available skills by keyword, then install them into the user's WorkBuddy skills directory.
EnglishUse when testing or debugging a JLCEDA Pro extension (.eext) against a live JLCEDA project page. Covers the full workflow: (1) restarting Edge via mcpextension-dev-mcp-toolsdevplugin to reimport the .eext, (2) connecting to the user's already-logged-in Edge/Chrome via CDP, (3) navigating to a project tab and waiting for the sch canvas to render, (4) handling V3.2-specific dialogs ("另有一个标签页" / "导入扩展"), (5) mouse-drag selecting components on the schematic canvas, (6) clicking the extension's toolbar menu and verifying the resulting IFrame, (7) capturing screenshots + dialog text for comparison, (8) verifying settings-page toggles (e.g. saveToDisk) end-to-end, (9) running a 3-case saveToDisk regression (true / false / new-install), (10) polling the AI chat IFrame through reasoning-model timeouts (deepseek-v4-pro etc.). MUST use mcp devplugin (NOT importplugin — that one fails on V3.2 UI). Use this skill whenever the user says "test the extension in Edge", "verify the menu triggers", "run the workflow end-to-end", "重开浏览器验证", "截图对比", "check the AI chat reply", "verify saveToDisk", or "打开 settings 测试开关". Do NOT use this skill for unit-testing the extension's source code with mocks — use the project's existing mock-test.js / ai-e2e-test.js for that.
EnglishPush, monitor, debug, and iterate on Kaggle kernel notebooks using the kaggle CLI. Covers: nbformat notebook generation, kernel-metadata.json configuration (GPU/dataset), push→poll→debug→fix→repush cycle, papermill timeout avoidance, and output download. Use when the user wants to run a notebook on Kaggle cloud GPUs and iteratively fix errors until it succeeds.
EnglishUse when creating Python scripts that target Kaggle Notebooks. This skill ensures correct cell separator format ( %% [code] and %% [markdown]) and Kaggle-specific conventions. Trigger when user mentions Kaggle, notebook format, %% separators, or asks to create notebook-style Python scripts.
EnglishSubmit, monitor, and manage SLURM compute jobs on the PVE cluster (ctl + node01). Covers sbatch, srun, squeue, scancel, sacct, and MiQi-specific job templates.
EnglishElectron 34+ 桌面应用端到端测试技能。当需要为 Electron 应用编写或调试 E2E 测试、遇到 Playwright electron.launch 不可用、CI 中 Chromium SIGTRAP 崩溃、ELECTRONRUNASNODE 导致 Electron 以 Node 模式运行、或需要 CDP 远程调试连接方案时使用此技能。涵盖 CDP 连接、进程管理、跨平台 kill、CI sandbox 处理、concurrency 策略。适用于 Electron 34…
Chinese将 GitHub 仓库的所有 Issue 同步到飞书多维表格。自动创建匹配字段(标题/编号/状态/链接/创建人/标签/创建时间/更新时间/正文),支持增量去重、dry-run 预览、批量写入。适用场景:用户提到同步 GitHub Issue 到飞书、把 Issue 写入多维表格、关联 GitHub…
Chinese解密 SkillHub 加密技能。AI 直接运行 scripts/decrypt.py 将 .dat 密文还原为完整 SKILL.md。支持文件路径、base64 字符串、stdin 三种输入方式。触发词:解密技能、encrypted skill、skill decrypt、dat…
ChineseWSL2 AI 沙箱操作指南。在 Windows 上通过 WSL2 执行 Linux 命令。沙箱以 root 运行,无需密码。适用于:需要运行 Linux 命令、脚本或工具。触发词:wsl…
ChineseIncludes Find Install Skills, Jlceda Extension Test, Kaggle Kernel Runner, and other workflows.
Supported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Find Install Skills
Search and install skills from the my-skills registry (https://skills.sixiangjia.de). Discover available skills by keyword, then install them into the user's WorkBuddy skills directory.
Jlceda Extension Test
Use when testing or debugging a JLCEDA Pro extension (.eext) against a live JLCEDA project page. Covers the full workflow: (1) restarting Edge via mcpextension-dev-mcp-toolsdevplugin to reimport the .eext, (2) connecting to the user's already-logged-in Edge/Chrome via CDP, (3) navigating to a project tab and waiting for the sch canvas to render, (4) handling V3.2-specific dialogs ("另有一个标签页" / "导入扩展"), (5) mouse-drag selecting components on the schematic canvas, (6) clicking the extension's toolbar menu and verifying the resulting IFrame, (7) capturing screenshots + dialog text for comparison, (8) verifying settings-page toggles (e.g. saveToDisk) end-to-end, (9) running a 3-case saveToDisk regression (true / false / new-install), (10) polling the AI chat IFrame through reasoning-model timeouts (deepseek-v4-pro etc.). MUST use mcp devplugin (NOT importplugin — that one fails on V3.2 UI). Use this skill whenever the user says "test the extension in Edge", "verify the menu triggers", "run the workflow end-to-end", "重开浏览器验证", "截图对比", "check the AI chat reply", "verify saveToDisk", or "打开 settings 测试开关". Do NOT use this skill for unit-testing the extension's source code with mocks — use the project's existing mock-test.js / ai-e2e-test.js for that.
Kaggle Kernel Runner
Push, monitor, debug, and iterate on Kaggle kernel notebooks using the kaggle CLI. Covers: nbformat notebook generation, kernel-metadata.json configuration (GPU/dataset), push→poll→debug→fix→repush cycle, papermill timeout avoidance, and output download. Use when the user wants to run a notebook on Kaggle cloud GPUs and iteratively fix errors until it succeeds.
Kaggle Notebook Rules
Use when creating Python scripts that target Kaggle Notebooks. This skill ensures correct cell separator format ( %% [code] and %% [markdown]) and Kaggle-specific conventions. Trigger when user mentions Kaggle, notebook format, %% separators, or asks to create notebook-style Python scripts.
Slurm
Submit, monitor, and manage SLURM compute jobs on the PVE cluster (ctl + node01). Covers sbatch, srun, squeue, scancel, sacct, and MiQi-specific job templates.
Electron E2E Cdp Testing
Electron 34+ 桌面应用端到端测试技能。当需要为 Electron 应用编写或调试 E2E 测试、遇到 Playwright electron.launch 不可用、CI 中 Chromium SIGTRAP 崩溃、ELECTRONRUNASNODE 导致 Electron 以 Node 模式运行、或需要 CDP 远程调试连接方案时使用此技能。涵盖 CDP 连接、进程管理、跨平台 kill、CI sandbox 处理、concurrency 策略。适用于 Electron 34 及以上版本。
GitHub Feishu Issue Sync
将 GitHub 仓库的所有 Issue 同步到飞书多维表格。自动创建匹配字段(标题/编号/状态/链接/创建人/标签/创建时间/更新时间/正文),支持增量去重、dry-run 预览、批量写入。适用场景:用户提到同步 GitHub Issue 到飞书、把 Issue 写入多维表格、关联 GitHub 和飞书等需求。
Skill Decrypt
解密 SkillHub 加密技能。AI 直接运行 scripts/decrypt.py 将 .dat 密文还原为完整 SKILL.md。支持文件路径、base64 字符串、stdin 三种输入方式。触发词:解密技能、encrypted skill、skill decrypt、dat 解密。
Wsl Sandbox
WSL2 AI 沙箱操作指南。在 Windows 上通过 WSL2 执行 Linux 命令。沙箱以 root 运行,无需密码。适用于:需要运行 Linux 命令、脚本或工具。触发词:wsl sandbox、wsl沙箱、linux命令、隔离执行、AI沙箱、sandboxexec、sandboxsetup。
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Find Install Skills skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.