Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add holoviz-dev/holoviz-skills --skill developing-with-holovizgit clone --depth 1 https://github.com/holoviz-dev/holoviz-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/holoviz-dev/holoviz-skills/developing-with-holoviz)<a href="https://agentmods.dev/skills/holoviz-dev/holoviz-skills/developing-with-holoviz"><img src="https://agentmods.dev/badge/skills/holoviz-dev/holoviz-skills/developing-with-holoviz/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/holoviz-dev/holoviz-skills/developing-with-holoviz"><img src="https://agentmods.dev/badge/skills/holoviz-dev/holoviz-skills/developing-with-holoviz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.01480 |
| Opus 5 | $0.00043 | $0.00740 |
| Sonnet 5 | $0.00017 | $0.00296 |
| Haiku 4.5 | $0.00009 | $0.00148 |
Grade A, and why
developing-with-holoviz scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developing with HoloViz
This is a routing skill. You MUST read every sub-skill file listed in the table below that matches the task BEFORE writing any code or giving any answer. Do not skip this step!
Contents
Instructions
- Identify which sub-skill(s) apply from the Loading Table below.
- Read each matching sub-skill file in full.
- Only after reading the sub-skill file(s), proceed with the task.
For new apps, prefer panel-material-ui over standard Panel templates — it provides modern Material Design components out of the box.
Loading Table
A single request often spans multiple skills. Read ALL that apply. Paths below are relative to this file's directory (developing-with-holoviz/).
| User Need | File(s) to read |
|---|---|
| Typed, validated, reactive parameters | skills/param/SKILL.md |
| Quick exploratory plots from DataFrames / xarray | skills/hvplot/SKILL.md |
| Compose a layered, faceted view to compare a metric across groups | skills/hvplot/SKILL.md + skills/hvplot/composing-exploratory-plots.md |
| Make a chart explanatory for an audience (one message, presentation-ready) | skills/hvplot/SKILL.md + skills/hvplot/distilling-explanatory-plots.md |
| Build a data story / graphic article (charts + narrative) | skills/hvplot/distilling-explanatory-plots.md + skills/panel/SKILL.md + skills/panel/using-material-ui.md + skills/panel/data-storytelling.md |
| Dashboard, data app, or interactive tool | skills/param/SKILL.md + skills/panel/SKILL.md + skills/panel/using-material-ui.md |
| Convert a design / screenshot / React app into a Material UI (pmui) app | skills/panel/SKILL.md + skills/panel/using-material-ui.md + skills/panel/converting-designs-to-material-ui.md (+ skills/panel/building-custom-components.md for rich/clickable pieces) |
| Keep an existing React/JSX UI and serve it as the app, embedding Panel components inside it | skills/panel/SKILL.md + skills/panel/building-custom-components.md + skills/panel/wrapping-react-apps.md |
| HoloViews elements, opts, tooltips, formatters, tools | skills/holoviews/SKILL.md |
| Remove chart junk / clean a plot — hide or autohide toolbar, disable wheel-zoom, one-axis gridlines, share axes, place legend | skills/holoviews/SKILL.md + skills/holoviews/decluttering-plots.md |
| Embedding plots in Panel (HoloViews/hvPlot, Matplotlib, Plotly, ECharts; DynamicMap, responsive sizing) | skills/param/SKILL.md + skills/panel/SKILL.md + skills/panel/plotting-in-panel.md + skills/holoviews/SKILL.md |
Stop repeating the same option on every component or chart — session defaults, pn.config, hv.opts.defaults, class param defaults |
skills/panel/SKILL.md + skills/holoviews/SKILL.md |
| Display, filter, sort, or select rows in a data table | skills/panel/SKILL.md + skills/panel/using-tabulator.md |
| Plot points or tracks on a map basemap (tiles, Web Mercator, no geo stack) | skills/holoviews/SKILL.md + skills/hvplot/SKILL.md |
| Custom components — pure-Python (Viewer/PyComponent) or JS/React/AnyWidget | skills/param/SKILL.md + skills/panel/SKILL.md + skills/panel/building-custom-components.md |
| Playwright UI testing for Panel components | skills/panel/building-custom-components.md + skills/panel/using-pytest-playwright.md |
| Review or audit a Panel app | skills/panel/SKILL.md + skills/panel/reviewing-panel-apps.md |
| Serve, screenshot, verify rendered output, benchmark startup, and debug a Panel app in a dev loop | skills/panel/SKILL.md + skills/panel/iterating-on-panel-apps.md |
| Structure or scale a larger app — multiple views over shared state, sessions, caching, threading, deployment | skills/panel/SKILL.md + skills/panel/designing-panel-architecture.md |
| Migrate an existing plain-Panel app to Material UI / pmui | skills/panel/SKILL.md + skills/panel/migrating-to-material-ui.md |
| Debug a Panel app that serves but misbehaves — nothing updates, blank Page, flicker, screenshot spinner, version/deprecation surprises | skills/panel/SKILL.md + skills/panel/troubleshooting-panel-apps.md |
What ships with it
30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- skills/datashader/.gitkeep 0 B
- skills/geoviews/.gitkeep 0 B
- skills/holoviews/decluttering-plots.md 9.2 KB
- skills/holoviews/SKILL.md 15 KB
- skills/hvplot/composing-exploratory-plots.md 4.2 KB
- skills/hvplot/distilling-explanatory-plots.md 3.1 KB
- skills/hvplot/SKILL.md 17 KB
- skills/lumen/.gitkeep 0 B
- skills/panel/building-custom-components.md 16 KB
- skills/panel/converting-designs-to-material-ui.md 5.9 KB
- skills/panel/data-storytelling.md 2.0 KB
- skills/panel/designing-panel-architecture.md 16 KB
- skills/panel/examples/dashboard.py 21 KB runs code
- skills/panel/examples/graphic_story.py 8.5 KB runs code
- skills/panel/examples/wizard.py 20 KB runs code
- skills/panel/iterating-on-panel-apps.md 21 KB
- skills/panel/migrating-to-material-ui.md 15 KB
- skills/panel/plotting-in-panel.md 12 KB
- skills/panel/reviewing-panel-apps.md 10.0 KB
- skills/panel/scripts/layout_lint.py 17 KB runs code
- skills/panel/scripts/preflight.py 18 KB runs code
- skills/panel/scripts/test_layout_lint.py 13 KB runs code
- skills/panel/scripts/test_preflight.py 9.7 KB runs code
- skills/panel/SKILL.md 15 KB
- skills/panel/troubleshooting-panel-apps.md 11 KB
- skills/panel/using-material-ui.md 28 KB
- skills/panel/using-pytest-playwright.md 5.0 KB
- skills/panel/using-tabulator.md 5.3 KB
- skills/panel/wrapping-react-apps.md 13 KB
- skills/param/SKILL.md 14 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 65 lines · 85 tokens per session scan A cae0817342eb
developing-with-holoviz is a skill published in the GitHub repository holoviz-dev/holoviz-skills (5 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 85 tokens to every session and 1,480 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…