live-panel
VerifiedBuild a terminal-style, always-running animated architecture diagram (a "live panel") from a JSON config and render it to an mp4. Use when the user wants a system, agent or org architecture diagram that looks like a monitoring dashboard in a terminal window - fixed layout, glowing packets on the wires, scrolling log, counters, bars that flip state - as a screen-recording-style video or a live web page, instead of a static picture or a step-by-step reveal. 中文:当用户要做"活的"架构图、agent 树或系统监控面板风格的动画(mp4 视频或循环网页)时使用——终端里一直在跑的监控面板外观,固定布局、线上流动的数据包、滚动日志、翻转的计数器和状态条;不是静态图,也不是分步演示。
examples/excalidraw-import/config.json
View on GitHub{
"meta": {
"title": "A tiny agent loop",
"source": "agent-loop.excalidraw"
},
"canvas": {
"preset": "16:9",
"duration": 15.0,
"fps": 30,
"width": 1920,
"height": 1080
},
"theme": {
"preset": "light-pastel",
"font": "Excalifont, Xiaolai, \"Noto Sans CJK SC\", sans-serif",
"fonts": [
{
"family": "Excalifont",
"src": "Excalifont-Regular-Latin.woff2",
"weight": "400"
},
{
"family": "Xiaolai",
"src": "Xiaolai-Regular.ttf",
"weight": "400"
}
],
"colors": {
"bg": "#ffffff"
}
},
"elements": [
{
"type": "view",
"kind": "excalidraw",
"space": [
1000,
636
],
"period": 15.0,
"t0": 0,
"seed": 5,
"boil": {
"step": 0.125,
"variants": 4,
"amp": 0.5
},
"roughness": 1.05,
"strokeWidth": 2.6,
"edgeRough": 0.8,
"edgeMulti": false,
"noteSize": 28,
"edgeGap": 6,
"texts": [
{
"t": "A tiny agent loop",
"x": 107.6,
"y": 109.7,
"size": 48,
"c": "ink",
"align": "left",
"weight": 0.6,
"underline": {
"hue": "yellow",
"width": 16,
"dy": 22,
"tilt": -4
}
}
],
"nodes": [
{
"id": "user",
"t": "User",
"x": 178.9,
"y": 276.2,
"w": 237.8,
"h": 107.0,
"hue": "yellow",
"sub": "asks a question",
"size": 33,
"subSize": 22,
"r": 22
},
{
"id": "agent",
"t": "Agent",
"x": 500.0,
"y": 276.2,
"w": 261.6,
"h": 107.0,
"hue": "blue",
"sub": "plans the next step",
"size": 33,
"subSize": 22,
"r": 22
},
{
"id": "tools",
"t": "Tools",
"x": 821.1,
"y": 276.2,
"w": 237.8,
"h": 107.0,
"hue": "green",
"sub": "search · code",
"size": 33,
"subSize": 22,
"r": 54
},
{
"id": "check",
"t": "Check",
"x": 500.0,
"y": 502.2,
"w": 261.6,
"h": 107.0,
"hue": "red",
"sub": "good enough?",
"size": 33,
"subSize": 22,
"r": 36
},
{
"id": "answer",
"t": "Answer",
"x": 821.1,
"y": 502.2,
"w": 237.8,
"h": 107.0,
"hue": "violet",
"sub": "back to the user",
"size": 33,
"subSize": 22,
"r": 22
}
],
"edges": [
{
"id": "a1",
"from": "user",
"to": "agent",
"fromSide": "right",
"fromOff": 0.0,
"toSide": "left",
"toOff": 0.0
},
{
"id": "a2",
"from": "agent",
"to": "tools",
"fromSide": "right",
"fromOff": 0.0,
"toSide": "left",
"toOff": 0.0
},
{
"id": "a3",
"from": "tools",
"to": "check",
"fromSide": "bottom",
"fromOff": -0.2,
"toSide": "right",
"toOff": -0.33,
"pts": [
[
797.3,
339.2
],
[
737.8,
413.0
],
[
640.3,
484.3
]
]
},
{
"id": "a4",
"from": "check",
"to": "answer",
"fromSide": "right",
"fromOff": 0.0,
"toSide": "left",
"toOff": 0.0,
"label": "yes",
"labelSize": 24,
"labelAt": [
666.5,
526.6
]
},
{
"id": "a5",
"from": "check",
"to": "agent",
"fromSide": "left",
"fromOff": 0.0,
"toSide": "bottom",
"toOff": -0.45,
"pts": [
[
369.2,
502.2
],
[
309.7,
448.6
],
[
321.6,
365.4
],
[
440.5,
339.2
]
],
"dashed": true,
"label": "no, retry",
"labelSize": 24,
"labelAt": [
240.7,
375.2
]
}
],
"steps": [
{
"node": "user",
"edge": "a1"
},
{
"node": "agent",
"edge": "a2"
},
{
"node": "tools",
"edge": "a3"
},
{
"node": "check",
"edge": "a4"
},
{
"node": "check",
"edge": "a5"
},
{
"node": "answer"
}
]
}
]
}Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |