jlceda-extension-test
Skill2 starsChanged 18 days agoNo licenceView on GitHub
This skill should be used when testing or debugging a JLCEDA Pro extension (.eext) against a live JLCEDA project page. Covers the full workflow: (1) restarting Edge via mcp__extension-dev-mcp-tools__dev_plugin 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 `dev_plugin` (NOT `import_plugin` — 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.
- Sends data out
In this repository19 other files it gives its agents.
- cnc-dfm-repairSkill
- cnc-part-designSkill
- daily-new-recordSkill
- daily-reportSkill
- docx-work-reportSkill
- electron-e2e-cdp-testingSkill
- find-install-skillsSkill
- github-feishu-issue-syncSkill
- kaggle-kernel-runnerSkill
- kaggle-notebook-formatSkill
- mcu-display-renderingSkill
- mkdocs-material-siteSkill
- skill-decryptSkill
- skillhubSkill
- slurmSkill
- weekly-reportSkill
- work-ledgerSkill
- 写paperSkill
- wsl-sandboxSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
19 rules. About 0 are common, 11 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.