Skip to content

sumitaich1998/jarvisvr / skills/stage/present-data

present-data

Verified

Choose the right visualization for a dataset and render it — table, chart, network graph, or globe — then place it well. Use when an agent has structured data to show, for "chart this", "show it as a table", "graph these relationships", or comparisons. Triggers: chart, graph, table, visualize, plot, compare, breakdown, show the data, trend.

Present Data

Pick the visualization that best fits the data's shape and the user's question, build valid props, and place it comfortably.

Choosing the widget

Data shape / intentWidgetTool
Rows × columns, look up valuesdata_tableshow_data_table
Trend / comparison of serieschart_3d (line/bar)show_chart
Distribution / parts of wholechart_3d (pie/scatter)show_chart
Entities + relationshipsgraph_3dshow_graph
Geographic points / flowsvolumetric_globe / map_3dshow_globe / show_map
Short prose / KPIspanelshow_panel

Steps

  1. Inspect the data (types, cardinality) and the user's question.
  2. Select from the table above; prefer the simplest that answers it.
  3. Build props to schema (e.g. chart_3d requires chart_type + series; data_table requires columns + rows).
  4. Render, then place via arrange_holograms (charts/tables read best world/surface at ~1.2 m).
  5. Narrate the takeaway in agent.speech — the headline, not every number.

Output

chart_3d (show_chart, props per registry.json):

{ "widget_type": "chart_3d",
  "props": { "chart_type": "bar", "title": "Quarterly Revenue",
             "labels": ["Q1","Q2","Q3","Q4"],
             "series": [ { "name": "FY2026", "values": [14,20,15,26], "color": "#4FC3F7" } ],
             "y_axis_label": "Revenue ($M)", "show_legend": true } }

data_table (show_data_table):

{ "widget_type": "data_table",
  "props": { "title": "Devices",
             "columns": [ { "key": "name", "label": "Name", "type": "string" },
                          { "key": "watts", "label": "Watts", "type": "number" } ],
             "rows": [ { "name": "Ceiling Light", "watts": 12 }, { "name": "Heater", "watts": 0 } ],
             "sortable": true } }

Edge cases

  • Tiny data (1–2 numbers) → a panel/text_label, not a chart.
  • Too many series/rows → aggregate or paginate; keep it legible.
  • Categorical vs continuous → bar for categories, line for time series.
  • Selection events (select_point, select_row) → drill down or explain.
  • Raw source, not data → that's research-agent; you visualize what it returns.
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: 468kUpdated Claude CodeCodexVerifiedInstall
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: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 321kUpdated Claude CodeCodexVerifiedInstall