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-aqua/config-3x4.json
View on GitHub{
"meta": {
"title": "AQuA inner + outer loop (excalidraw view)",
"lang": "en"
},
"canvas": {
"preset": "3:4",
"duration": 32,
"fps": 30
},
"theme": {
"preset": "light-pastel",
"font": "Excalifont, Xiaolai, \"Noto Sans CJK SC\", sans-serif",
"fonts": [
{
"family": "Excalifont",
"src": "Excalifont-Regular-Latin.woff2",
"weight": "400"
}
],
"colors": {
"bg": "#ffffff",
"muted": "#5c636b",
"xblue": "#b8d3ec",
"xgreen": "#bedcb9",
"xyellow": "#f5e49e",
"xred": "#ecbcb6",
"xviolet": "#d3c6ef"
}
},
"credit": {
"text": "after Google adk-recipes AQuA diagram, via @Saboo_Shubham_ · https://github.com/google/adk-recipes/tree/main/core/python/ambient-quality-agent\nhttps://x.com/Saboo_Shubham_/status/2112428713979900248 · recreation, motion illustrative · made with live-panel (excalidraw view)",
"y": 1412,
"size": 12.5,
"lh": 16,
"c": "#868e96",
"font": "\"Noto Sans CJK SC\", sans-serif"
},
"elements": [
{
"type": "view",
"kind": "excalidraw",
"space": [
1000,
1330
],
"period": 32,
"t0": 1.55,
"seed": 11,
"boil": {
"step": 0.125,
"variants": 4,
"amp": 0.5
},
"noteSize": 30,
"roughness": 1.05,
"strokeWidth": 2.6,
"edgeRough": 0.8,
"edgeMulti": false,
"zones": [
{
"x": 34,
"y": 165,
"w": 932,
"h": 570,
"fill": "#f1f6fc",
"r": 40
},
{
"x": 34,
"y": 802,
"w": 932,
"h": 478,
"fill": "#f1f7ef",
"r": 40
}
],
"texts": [
{
"t": "Ambient Quality Agent (AQuA)",
"x": 500,
"y": 95,
"size": 56,
"c": "ink",
"weight": 0.8,
"underline": {
"hue": "yellow",
"width": 16,
"dy": 20,
"tilt": -4
}
},
{
"t": "INNER LOOP:\nBuild & Test\n(local / CI)",
"x": 140,
"y": 236,
"size": 28,
"c": "slate"
},
{
"t": "OUTER LOOP:\nShip, Monitor & Learn\n(24/7 in production)",
"x": 940,
"y": 1227,
"size": 22,
"c": "sage",
"align": "right"
}
],
"icons": [
{
"kind": "laptop",
"x": 500,
"y": 415,
"w": 112
},
{
"kind": "cloud",
"x": 500,
"y": 1033,
"w": 150
}
],
"nodes": [
{
"id": "offline",
"t": "offline\nevals",
"x": 500,
"y": 259,
"w": 222,
"h": 112,
"hue": "green",
"size": 38
},
{
"id": "evalset",
"t": "eval set",
"x": 800,
"y": 449,
"w": 222,
"h": 96,
"hue": "blue",
"size": 38
},
{
"id": "coding",
"t": "coding\nagent /\noptimizer",
"x": 200,
"y": 449,
"w": 222,
"h": 140,
"hue": "yellow",
"size": 34
},
{
"id": "compare",
"t": "compare\n+ deploy",
"x": 500,
"y": 644,
"w": 226,
"h": 112,
"hue": "red",
"size": 38
},
{
"id": "live",
"t": "live\ntraffic",
"x": 500,
"y": 870,
"w": 210,
"h": 108,
"hue": "blue",
"size": 38
},
{
"id": "online",
"t": "online\nevals",
"x": 800,
"y": 1033,
"w": 216,
"h": 112,
"hue": "violet",
"size": 38
},
{
"id": "sweep",
"t": "AQuA\nsweep",
"x": 500,
"y": 1195,
"w": 216,
"h": 108,
"hue": "green",
"size": 38
},
{
"id": "root",
"t": "AQuA root\ncause",
"x": 200,
"y": 1033,
"w": 226,
"h": 116,
"hue": "yellow",
"size": 38
}
],
"edges": [
{
"id": "e1",
"from": "evalset",
"to": "offline",
"fromSide": "top",
"toSide": "right",
"bend": 0.25,
"fromOff": -0.45,
"toOff": 0
},
{
"id": "e2",
"from": "offline",
"to": "coding",
"fromSide": "left",
"toSide": "top",
"bend": 0.25,
"fromOff": 0,
"toOff": 0
},
{
"id": "e3",
"from": "coding",
"to": "compare",
"fromSide": "bottom",
"toSide": "left",
"bend": 0.25,
"fromOff": 0,
"toOff": 0
},
{
"id": "e4",
"from": "compare",
"to": "evalset",
"fromSide": "right",
"toSide": "bottom",
"bend": 0.25,
"fromOff": 0,
"toOff": -0.1
},
{
"id": "deploy",
"from": "compare",
"to": "live",
"fromSide": "bottom",
"toSide": "top",
"bend": 0,
"fromOff": 0,
"toOff": 0,
"width": 3.6,
"label": "deploy",
"labelAt": [
566,
763
]
},
{
"id": "e5",
"from": "live",
"to": "online",
"fromSide": "right",
"toSide": "top",
"bend": -0.25,
"fromOff": 0,
"toOff": 0
},
{
"id": "e6",
"from": "online",
"to": "sweep",
"fromSide": "bottom",
"toSide": "right",
"bend": -0.25,
"fromOff": 0,
"toOff": 0
},
{
"id": "e7",
"from": "sweep",
"to": "root",
"fromSide": "left",
"toSide": "bottom",
"bend": -0.25,
"fromOff": 0,
"toOff": 0
},
{
"id": "d1",
"from": "online",
"to": "evalset",
"fromSide": "top",
"toSide": "bottom",
"bend": 0.17,
"fromOff": 0.72,
"toOff": 0.72,
"dashed": true,
"label": "failing transcripts\nseed evals",
"labelAt": [
908,
768
],
"labelAlign": "right"
},
{
"id": "d2",
"from": "root",
"to": "coding",
"fromSide": "top",
"toSide": "bottom",
"bend": -0.17,
"fromOff": -0.72,
"toOff": -0.72,
"dashed": true,
"label": "root causes, evidence\n& raw traces",
"labelAt": [
72,
768
],
"labelAlign": "left"
}
],
"steps": [
{
"node": "compare",
"edge": "e4",
"note": "not better yet",
"at": [
500,
536
],
"align": "center",
"dur": 1.5,
"dwell": 0.62
},
{
"node": "evalset",
"edge": "e1",
"note": "run it again",
"at": [
846,
352
],
"align": "center",
"dur": 1
},
{
"node": "offline",
"edge": "e2",
"note": "scoring offline…",
"at": [
640,
190
],
"align": "left",
"dur": 1
},
{
"node": "coding",
"edge": "e3",
"note": "trying another fix",
"at": [
338,
500
],
"align": "left",
"dur": 1
},
{
"node": "compare",
"edge": "deploy",
"note": "better → ship it",
"at": [
500,
536
],
"align": "center",
"dur": 1.5
},
{
"node": "live",
"edge": "e5",
"note": "real users, 24/7",
"at": [
500,
974
],
"align": "center",
"dur": 1
},
{
"node": "online",
"edge": "e6",
"note": "reviewing sessions",
"at": [
692,
961
],
"align": "right",
"dur": 1
},
{
"node": "sweep",
"edge": "e7",
"note": "grouping failures",
"at": [
500,
1093
],
"align": "center",
"dur": 1
},
{
"node": "root",
"edge": "d2",
"note": "root cause found",
"at": [
140,
933
],
"align": "left",
"dur": 1
},
{
"node": "coding",
"edge": "e3",
"note": "applying the fix",
"at": [
338,
500
],
"align": "left",
"dur": 1
},
{
"node": "compare",
"edge": "deploy",
"note": "better → ship it",
"at": [
500,
536
],
"align": "center",
"dur": 1.5
},
{
"node": "live",
"edge": "e5",
"note": "real users, 24/7",
"at": [
500,
974
],
"align": "center",
"dur": 1
},
{
"node": "online",
"edge": "d1",
"note": "a failing transcript!",
"at": [
692,
961
],
"align": "right",
"dur": 1
},
{
"node": "evalset",
"edge": "e1",
"note": "new eval case",
"at": [
846,
352
],
"align": "center",
"dur": 1
},
{
"node": "offline",
"edge": "e2",
"note": "scoring offline…",
"at": [
640,
190
],
"align": "left",
"dur": 1
},
{
"node": "coding",
"edge": "e3",
"note": "patching the agent",
"at": [
338,
500
],
"align": "left",
"dur": 1
}
]
}
]
}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 |