AGENT SKILL

visualize

Charts, maps, plots, simulators, UI mockups in chat.

License 许可
MIT
最近更新
2026-08-25
Stars
★ 1
Forks
0

01 前言 Front Matter

name
visualize
description
Charts, maps, plots, simulators, UI mockups in chat.

02 资源文件 3

03 SKILL.md 正文

Visualize

Interactive HTML visuals delivered in chat as a standalone .html attachment plus a screenshot preview. Use when the user wants to see how something works, make simulators or labs, maps, plots, charts or graphs, comparisons, UI mockups, scenarios, adjustable inputs, and exploration beyond regular text. Works on every Hermes surface (Telegram, Desktop) because the deliverable is a file, not an inline widget.

When to use it

  • A request for a new standalone file, website, app page, component, or other project change is not a visualization request, even when the deliverable contains charts or interactive content.
  • A request to preview, explain, or explore a proposed interface inside the conversation is a visualization request.
  • Create a visual only when the user needs to see or explore it and it materially improves the explanation. Do not create one merely because the request involves data, charts, or an interactive page.
  • Use a normal Markdown table when the user asks for a table; return it directly and do not create a visualization file.
  • Use Mermaid when labeled nodes and edges fully explain a static structure; return a normal fenced Mermaid block and no visualization file. Use HTML for dynamics, spatial motion, adjustable inputs, and other visuals.
  • Work silently unless blocked or the user explicitly asks for progress. The final response must be your first user-facing message.
  • In user-facing prose, describe only what the visual helps the user see or decide. Keep it concise; never announce this skill, HTML, scripts, CDN sources, or other implementation details.

Context compaction

Copy into every compaction summary: Reload the full visualize skill before creating or updating a visualization.

Locations

  • Resolve the active profile root from $HERMES_HOME.
  • Skill directory (scripts + assets live here): $HERMES_HOME/skills/visualization/visualize/
  • Default visualization directory (durable, outside any repo): $HERMES_HOME/visualizations/<title>/ Inside a Kanban task use $HERMES_KANBAN_WORKSPACE/visualizations/<title>/ instead, and put the final .html into kanban_complete(artifacts=[...]).
  • <title> is a concise ASCII lowercase-hyphenated name derived from the request. Each visualization gets its own folder with fragment.html (the editable source) and <title>.html (the rendered standalone document).

Fragment contract

  • Write only an HTML fragment: no <!doctype>, <html>, <head>, or <body>. The render script wraps it with the design-system CSS, the tooltip/icon kit, and a strict CSP.
  • Write literal markup: use <div class="card">Hi</div> plus a real newline, never <div class=\"card\">Hi</div>\n. Never embed the fragment in an inline Python, JavaScript, or shell string. Read it back; rewrite literal \" or \n.
  • Keep CSS and JavaScript in the fragment only when base classes are insufficient. Load static resources only from the CDN allowlist. Never use fetch, XHR, WebSocket, or other API calls inside the fragment — download any data (e.g. GeoJSON) with your own tools and inline it.
  • Give the fragment root a unique ID and select it with document.getElementById(...). Never derive the root from document.currentScript; scripts may sit outside the root.
  • Keep visualizations under 1 MB. Aggregate, bin, downsample, reduce precision, or drop unused fields from large inline datasets.
  • Check that JavaScript has no undefined identifiers, every queried element exists, and the primary interaction updates the visual.

Render, verify, deliver

  1. Render the fragment to a standalone document:

    python3 "$HERMES_HOME/skills/visualization/visualize/scripts/render.py" \
      <abs>/fragment.html <abs>/<title>.html
    

    The same script with --serve temporarily serves it on 127.0.0.1 for browser inspection when a live look helps.

  2. Verify with headless screenshots at the design widths (736px always; 360px for anything responsive; 1024px when a wide layout is used):

    google-chrome --headless=new --disable-gpu --no-sandbox \
      --window-size=736,900 --hide-scrollbars \
      --screenshot=<abs>/<title>-736.png file://<abs>/<title>.html
    

    Inspect each screenshot with vision_analyze and fix blank basemaps, clipped or overlapping labels, failed imports, and broken layout before replying. If headless Chrome is unavailable, re-read the code carefully and say the visual was not screenshot-verified.

  3. Deliver in the final message:

    • MEDIA:<abs>/<title>.html — the visualization itself. It arrives as a document; opened in any browser it is fully interactive.
    • MEDIA:<abs>/<title>-736.png — a static preview so the result is visible at a glance without opening the file.
    • One short sentence about what the visual shows or lets you explore. If interactivity is the point, say the file opens in a browser.
    • Whenever you create or update a visualization, attach the rendered file again in that same turn's response, even when reusing an earlier path.

External resources

  • The render script's CSP allows only cdnjs.cloudflare.com, esm.sh, cdn.jsdelivr.net, unpkg.com, fonts.googleapis.com, fonts.gstatic.com, and fonts.bunny.net. Other origins are blocked and fail silently.

Exporting and publishing

  • The rendered <title>.html is already a self-contained standalone document; handing over the file is the default "export".
  • Only when the user explicitly asks to publish or host an existing visualization, use the isolated-web-preview skill to put it online. Do not claim it was published until the live URL is verified.
  • A general website request is not an export: build it as a normal project, outside this skill.

Composition

Choose the smallest composition that fits.

  • Prefer interaction detail over permanent panels, toolbars, repeated legends, or long stacks. Add only requested controls, use one mechanism per state, and never invent search, filter, or reset controls.
  • Keep filters, selections, and other presentation-only interactions local to the fragment. There is no callback channel from the file back to the agent: for drill-down that would need agent investigation, highlight the selection in the visual and prompt the user to ask in chat with the selected values.
  • Show only metrics that explain the requested behavior. Put live values in control headers or on the visual before cards. Treat maxima as ceilings, not targets. Never invent qualitative scores, status cards, or secondary fact grids to fill space.

UI mockups

  • Use product and platform context already available in the conversation; don't search the project to render a mockup. Match the product's chrome, navigation, typography, colors, and content. If its design is unavailable, infer one from the platform and request.
  • NEVER use visualization CSS variables or utility classes inside a mockup (for example, --card, --font-size-base, .card, or .btn). Define root-scoped, product-specific colors, typography, surfaces, and controls instead. This rule overrides all general visualization guidance.
  • Keep only the surrounding surface transparent. Give product windows, cards, menus, and popovers opaque backgrounds, and stack overlays above the product content.
  • Follow the host's active appearance with product-specific light-dark(<light>, <dark>) colors unless a fixed theme is requested.
  • Contained mockup: frame a component, dialog, small feature, or mobile screen as a compact product surface.
  • Full-page mockup: render a desktop window, application shell, or page at full width without an additional visualization card.
  • Put app-wide navigation and pickers in the app chrome, and local controls in their component. Omit single-option pickers. Show realistic states, not invented dashboards, filler cards, or oversized icons.

Interactive explainer or simulation

  • Use compact controls or status, one compact dominant visual, and at most one single-line selected-state detail. Default to no summary cards; allow up to three only when changing metrics are central.
  • Crop empty space and fit the available width. For step-throughs, add only requested step controls and update one current visual; never add parameter controls, formulas, metric cards, or side-by-side steps unless asked.

Graphs and plots

  • Use D3 for data-rich Cartesian or statistical plots and handwritten SVG for simple, directly labeled values. Load the version-pinned approved-CDN script https://cdn.jsdelivr.net/npm/d3@7.9.0/dist/d3.min.js.
  • Render the figure, legend, and subplots directly on the transparent host surface. Frame only the SVG plot area; never wrap charts in .card, rounded panels, filled backgrounds, or shadowed containers.
  • Give the figure a concise visible title. Render each Cartesian subplot in its own responsive SVG with a matching viewBox, a thin frame, and visible text.axis-title[data-axis="x"] and text.axis-title[data-axis="y"] showing quantities and units.
  • Set each SVG viewBox from its own container's measured width, redraw with ResizeObserver, and reserve at least 64px for the y axis. Never scale down a fixed-width viewBox.
  • Derive padded domains with d3.extent(...) over all observations, uncertainty, and references. Inset scale ranges for marker radii and keep every path inside rect[data-chart-frame]; never draw endpoint connectors outside the frame or guess or hard-code the domain.
  • After every draw, measure tick, axis, and value-label bounds together. Leave 4px between labels, anchor edge labels inward, and remove optional annotations first. At 360px, show at most four x ticks and stack panels.
  • Prefer --viz-series-1 through --viz-series-6 for chart series; use --foreground and --border for neutrals, cycle the six series tokens when more are needed, and never use literal or fallback colors. Give every SVG label fill: var(--foreground) and font-size: 12px; never shrink labels below 11 screen pixels. Stack subplots when their labels no longer fit.
  • Keep observations, trends, and important values visible. Use bands for dense uncertainty, whiskers for isolated estimates, and one compact, wrapping legend. Render one real <button type="button" aria-pressed="true"> per series with a small swatch and neutral text; toggle its line, markers, and tooltip row together. Keep buttons transparent, borderless, and indistinguishable from inline text; never use .btn, pills, badges, rounded borders, or filled and selected backgrounds.
  • Share one root-relative, pointer-transparent <div class="tooltip" role="tooltip"> using --popover and --popover-foreground. In each multi-series SVG, give the full-plot overlay both data-chart-hit and data-chart-hover-overlay="cross-series". Keep the data-chart-hover-guide at the exact cursor x, interpolate every visible series there, and show one aligned data-chart-hover-marker and tooltip row per visible series; never snap the guide to a nearby sample.
  • Find ordered observations with d3.bisector(d => d.x).center(values, x); never pass an accessor to d3.bisectCenter.
  • Give isolated marks transparent data-chart-hit targets at least 32 screen pixels across; use one nearest-point overlay for dense scatter.
  • For named numeric data and one-off analyses, start with the plot. Put values and takeaways on its marks, axes, or annotations. Never add a KPI row, controls, cards, or panels unless those UI elements are explicitly requested.
  • For sequences or parallel work, use aligned lanes on one time axis. Encode phase and resource in the marks; annotate totals, waits, and bottlenecks on the axis or lanes, not above the plot.
  • For distributions or multi-metric comparisons, use shared-scale facets or small multiples. Render every requested dimension simultaneously; never hide one behind a toggle.

Maps

  • Let the map dominate the composition. Use at most one compact selection/detail area and only requested controls.
  • Always project published GeoJSON/TopoJSON and sourced longitude/latitude with d3-geo; never hard-code or hand-draw geographic outlines. Use schematic maps only when asked.
  • For world countries, import https://esm.sh/@d3-maps/atlas@1.0.0/world/countries/countries-110m and convert it with topojson-client@3.1.0 using feature(world, world.objects.features).features. Join input ISO3 directly to feature.properties.id, which is already ISO3; do not convert it to numbers.
  • For US states or counties, use https://cdn.jsdelivr.net/npm/us-atlas@3/counties-10m.json/+esm. For ZIP/ZCTA or city boundaries, download official Census or local open-data GeoJSON with your own tools and inline it; do not guess sibling atlas paths or import raw JSON as JavaScript.
  • Keep maps geographically legible: for local points, fetch published neighborhood, street, or comparable geometry; a blank field or lone administrative outline is not a basemap. Show the full city or region behind points or partial choropleths, and frame the locations with modest padding.
  • Include the verified geometry in the final HTML. Screenshot it before replying and fix blank basemaps, failed imports, missing labels, or unprojected points.

Dense categorical grid

  • Use one compact horizontal selected-item summary, then a grid with exactly one readable identifier per cell, then one small legend. Render only that identifier as visible cell text; put all other metadata in an accessible label or one summary line, not badges or fact grids. Allow only selection unless asked.

Part-to-whole or time allocation

  • Use compact metrics and one stacked chart of category allocation per period. Never substitute totals-only bars or duplicate it as a heatmap and totals chart.

Layout and accessibility

  • Use semantic HTML, keyboard-accessible controls, and concise labels.
  • Use aria-live="polite" for dynamic results, selections, and simulator updates. Use role="alert" for validation errors. Do not announce every hover or animation frame.
  • Keep the top-level surface transparent and unframed, and fill the available width. Design for 736px (1024px when several compact panels must stay side by side for direct comparison), and support widths down to 320px. Stack side-by-side content when it no longer fits.
  • At every supported width, text, controls, cards, toolbars, and dynamic content must fit without overlap or clipping. Reflow by stacking or wrapping; use .table-responsive only when table columns cannot fit. Avoid fixed outer widths, horizontal overflow, internal scrolling, position: fixed, and viewport-height layouts — the file may be opened on a phone.
  • Size every SVG from its actual container. At narrow widths, reduce ticks, declutter annotations, and keep visible text at least 11 screen pixels; never shrink a fixed-width viewBox.
  • Keep native tab order; never add tabindex.
  • Use native button, input, select, and textarea elements with matching utilities; never recreate controls.
  • Keep browser or utility focus styles; never override them.

Typography

  • Scale type with --font-size-base. Use normal text by default and .text-small only for secondary annotations (never below 11px).
  • h1, h2, and h3 are available; use one concise visible heading for a self-contained chart or graph, with short panel headings only when needed. Do not restate the prompt or add a redundant title to other visualizations.
  • Use only weights 400 and 500. Never set custom font sizes or line heights.

Color

  • Make every fill, stroke, text, border, shadow, chart, and canvas color theme-aware. Never hardcode light or dark palettes such as white panels, off-white backgrounds, black text, slate strokes, or Tailwind color literals.
  • Keep text readable against its actual background. Muted or secondary colors must retain clear contrast; never use .text-muted inside .card or another filled container unless its background preserves that contrast.
  • Available theme variables include --background, --foreground, --card, --card-foreground, --popover, --popover-foreground, --primary, --primary-foreground, --secondary, --secondary-foreground, --muted, --muted-foreground, --accent, --accent-foreground, --destructive, --border, --input, --ring, --blue, --orange, --green, --red, --purple, and --yellow. Use currentColor inside SVG.
  • Never add decorative borders, outlines, or strokes to progress tracks, meters, bars, stacked segments, or other filled quantitative marks. Use a subtle neutral or translucent track and distinguish marks with fill, contrast, spacing, or opacity.
  • Use --viz-series-1 for one measure or active state. Use --viz-series-2 through --viz-series-6 only for important persistent category, series, or status identity; never give every peer a different color by default.
    • For categorical tiles or nodes, prefer a soft low-opacity series fill with a neutral or transparent border; never color every outline.
    • Keep mappings stable and pair color with labels, shapes, or line styles.
    • Secondary series colors are theme-derived; never assume hues or use them decoratively.
  • When color encodes a category or series, apply it consistently to the corresponding visual marks—not just the legend—and keep large-area fills subtle.
  • Use series colors only for chart lines, marks, and legend swatches. Keep values, axis text, and direct labels in --foreground or --muted-foreground.
  • Keep chart grids and inactive structure thin and neutral. Use 1-2px neutral structural paths; never thicken, dash, or double-stroke the whole structure.
  • In each color pair, the base token is a surface and its -foreground token is the content on that surface. Use .btn-primary for high-emphasis actions; its neutral fill is supplied by the utility. Use --primary and --primary-foreground for filled selected, active, or pressed controls. Reserve --accent and --accent-foreground for subtle interactive surfaces and soft highlights. Buttons with aria-pressed="true", aria-selected="true", or .is-selected already use the primary pairing.

Design system

  • Let utilities own geometry, appearance, and interaction. Use the matching utility for every button and form control. Never restyle utilities, descendants, or pseudo-elements: no custom sizes, spacing, borders, radii, shadows, colors, or interaction states.

Surfaces and layout

  • .card: The only card-like HTML surface. Use its base class unchanged for a necessary numeric summary, selected-item summary, or bounded interactive field. Before adding a fill, border, radius, or shadow to any layout container, either use .card or leave it transparent and unframed; never recreate card chrome on rows, panels, tiles, sections, or wrappers. Keep charts, maps, diagrams, tables, controls, and the whole visualization unframed. Never nest cards; show 2-4 summaries near the top only when useful. Structural groupings and repeated content are not bounded interactive fields. Organize them with layout or visual marks, not container chrome.
  • .viz-stat: Use a summary .card with one muted label, one .viz-stat-value, and at most one short context or delta line.
  • .viz-grid: Use for peer metrics or choices instead of a custom grid. It creates as many equal-width columns as fit and stacks when narrow. Never use it for the whole visual or a horizontally scrolling card row. Keep groups to 2-3 columns at 736px and controls in a separate row.
  • .viz-row: Use as a wrapping horizontal group with centered related values or inline actions that may wrap when narrow.
  • .progress + .progress-bar: <div class="progress" role="progressbar" aria-label="Progress" aria-valuenow="25" aria-valuemin="0" aria-valuemax="100"><div class="progress-bar" style="width:25%"></div></div>
  • .viz-tile: Add to a selectable dense-grid .btn; it stretches to fill its grid cell, preserves category fill, and uses an accent ring instead of solid selection. Never add another selected, pressed, border, outline, or shadow rule.
  • .viz-badge: Use as a compact display-only accent pill for a short status, category, or value; never as a button.
  • .viz-controls: Use as a wrapping row for controls affecting the same visualization. Keep button groups compact. Put labeled fields directly inside as .form-label; fields form at most two columns and stack when narrow.

Controls

  • .btn: Use for a content-sized secondary action. Add .btn-primary for one main action per control group or .btn-ghost for low emphasis.
  • .btn-block: Add to a .btn only when the action should intentionally fill the available inline space. Never use it for ordinary row actions.
  • <a>: Use for links. Add .btn to style a link as a button.
  • [data-tooltip]: Use for concise supplementary plain text on static or dynamic triggers; the render kit creates .tooltip elements. Keep essential content visible and triggers labeled. Never use title, custom markup, or initialization. Example: <button type="button" data-tooltip="Reset view">Reset</button>.
  • [data-tooltip-placement]: Optionally prefer top (default), right, bottom, or left; collision handling may flip it.
  • .form-check: Wrap a native checkbox or radio; pair .form-check-input and .form-check-label with matching id and for.
  • .form-switch: Add to .form-check around a native checkbox.
  • .form-control: Pair a native text, file, or color input—or a textarea—with .form-label.
  • .form-control-color: Add to .form-control for a compact native color input.
  • .form-select: Pair a native select with .form-label.
  • .form-range: Pair a native range with a visible label; put its current value and units immediately before it.

Tables

  • .table: Use on a semantic table for a quiet, unframed data view. It provides wrapping cells and subtle horizontal dividers without vertical gridlines. Use sentence case for headers.
  • .table-responsive: Wrap a table when its columns cannot fit at narrow widths. It contains horizontal overflow without clipping the visualization.
  • .table-sm: Add to .table when more rows need to fit; it reduces cell padding without shrinking text.
  • .text-end, .text-center, and .text-nowrap: Use inside .table for numeric/end alignment, centered values, or values that must stay on one line. Numeric cells use tabular figures when end-aligned.

Text

  • .text-small: Use for the smallest host-scaled secondary chart labels and annotations, never below 11px or for essential content.
  • .text-muted: Use for secondary units, captions, timestamps, and context, never essential values or labels.
  • .text-destructive: Use only for error or validation text the user needs to notice or act on.
  • <code>: Use for inline commands, file names, symbols, or short references; put multiline code in <pre><code>.
  • .sr-only: Use for visually hidden accessible text.

Charts

  • Prefer inline SVG for simple charts and version-pinned approved-CDN libraries when native interaction, scales, legends, or layout materially improve the result.
  • Resolve theme colors before passing them to canvas or chart APIs that cannot parse CSS variables or light-dark(...); redraw when the theme changes.
  • Use a tooltip unless it would distract from a simple, directly labeled chart. Keep chart-library tooltips and grouped legend interactions native; never replace them with a custom one-point tooltip. For SVG, attach data-tooltip directly to the real pointer-accessible mark and include its label, value, and units; the render kit handles themed positioning and keyboard focus.
  • Animate transitions between chart states so lines and marks move to their new values, resampling paths when point counts differ. Do not animate initial appearance or use fade-only effects; never loop motion, and honor prefers-reduced-motion.
  • Scope SVG styles to the chart class. Never target every svg in a container that also contains Lucide icons.
  • Include labeled axes, units, and directly labeled important values. Give every chart, SVG, canvas, and widget a concise screen-reader summary using a role and accessible name or description, SVG <title>/<desc>, fallback text, or an .sr-only heading or description.
  • Reserve space for the longest formatted label at every supported width. Axis ticks are secondary and may use .text-small when space is tight. Never overlap or clip text against marks, axes, legends, labels, or edges; move or reduce labels rather than squeeze them.
  • Add a legend only when multiple series cannot be labeled directly.
  • Pair color with shape or text so meaning never depends on color alone.

Icons and mockups

  • Use the render-kit global lucide. Add an icon name with data-lucide:

    <i data-lucide="search" aria-hidden="true"></i>
    
  • Lucide replaces the placeholder in place with an inline SVG. Icons are 16px and inherit currentColor.

  • Mark decorative icons aria-hidden="true". Put action icons inside labeled controls; use a visible label or aria-label for icon-only actions.

  • Let the kit initialize static icons after the fragment without blocking first render. After adding icons dynamically, use lucide.createIcons({ attrs: { width: 16, height: 16 } }).

  • Never load Lucide or another icon library from the network yourself; the kit already loads it from the CDN allowlist.

  • Use visibly labeled buttons and inputs for small interactions. Keep all presentation-only interaction local to the fragment and make the first render useful before input changes.

  • Use semantic controls, realistic spacing, and restrained chrome for mockups. Never fake product screenshots when inspectable UI is needed.

04 同仓库更多 Skills