Semiotic is a React library for building data visualizations such as charts, network graphs, streaming displays, and coordinated dashboards. It is used by developers who need to render data-driven interfaces, including with AI coding assistants. Its schemas and MCP server support the catalogue's add-ons for generating chart code.
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 agentmods add skills/nteract/semiotic/blog-postnpx skills add nteract/semiotic --skill blog-postgit clone --depth 1 https://github.com/nteract/semioticWrote 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/nteract/semiotic/blog-post)<a href="https://agentmods.dev/skills/nteract/semiotic/blog-post"><img src="https://agentmods.dev/badge/skills/nteract/semiotic/blog-post.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.03355 |
| Opus 5 | $0.00022 | $0.01677 |
| Sonnet 5 | $0.00009 | $0.00671 |
| Haiku 4.5 | $0.00004 | $0.00335 |
Grade A, and why
blog-post 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 5d 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing a Semiotic blog post
This skill writes one entry for the Semiotic blog. The blog lives at
/blog/; entries live at /blog/<slug>/. Three story shapes are
supported — pick the one that matches what's being written:
- Chart explainer — single chart, "what / why / when / wiring".
- Release summary — what's new in a version, ordered by impact.
- Narrative / case study — comparative posts ("X vs Y"), walkthroughs, recreations of historical visualizations.
Every entry follows the same structure regardless of shape. The why-care section is non-negotiable: the post has to give the reader a reason to read it that lands even if they're not currently using Semiotic. The blog isn't reference docs; it's a publication that happens to be hosted on the docs site.
Before writing anything
Ask the user for the author byline unless they've already given one. Don't assume "Elijah Meeks" by default — many entries will be co-authored or attributed to "Semiotic Team" for releases. One short question, then proceed.
File structure
For a new entry with slug <slug>:
- Body component —
docs/src/blog/entries/<slug>.jsx. Default export is{ slug, title, subtitle, author, date, tags, excerpt, component, ogChart? }. Thecomponentis a React function returning JSX (the entry's body — no header, no chrome, theBlogEntryViewwraps it). - Register in registry —
docs/src/blog/entries.jsimports the new file and adds it toblogEntries. - Register in metadata mirror —
docs/src/blog/entries-meta.jsgets the same metadata object (withoutcomponent, without the React imports). This mirror is read by the OG-card generator and the prerender script, both of which run under plain Node and can't load JSX.
Both registry files must stay in sync. The OG-card generator and
prerender script read entries-meta.js; the React app reads
entries.js.
Required fields
{
slug: "kebab-case-route",
title: "Title-Case Headline",
subtitle: "One or two sentences orienting the reader.",
author: "Author Name", // ASK THE USER if unspecified
date: "YYYY-MM-DD", // ISO; controls sort order
tags: ["release"] | ["chart-explainer", "xy"] | ...,
excerpt: "2–3 sentence preview shown on the index card.",
component: Body, // function returning JSX
ogChart: { component: "DifferenceChart" }, // optional, see OG step
}
What ships with it
3 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.
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.
- 5d ago First seen · 335 lines · 44 tokens per session scan A c5f054b7c16f
blog-post is a skill published in the GitHub repository nteract/semiotic (2,691 stars, last pushed 3d ago), licensed Apache-2.0. It adds 44 tokens to every session and 3,355 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
anyviz
Use when 用户请求选择、创建、改进或统一数据可视化,并需按数据与意图选择图表、主题及 D3.js、ECharts、Mapbox、Three.js、Matplotlib、Plotly 或 ggplot2 技术栈。.
chart-builder
Use this skill when creating data visualizations, selecting the right chart type, or generating chart code. Trigger phrases: 'build a chart', 'visualize this data', 'create a graph', 'plot these numbers', 'which chart should I use for'. Not for building interactive dashboards, designing UI components, or creating…
chart-designer
Design effective data visualizations and charts. Generate chart configurations for ECharts, Chart.js, and other libraries. Create dashboards and reports.
observer
Run a study session over a video or podcast the user wants to understand: transcribe it, prepare the concepts and the visuals before they press play, then answer whatever they ask at the exact moment they pause, with charts you build on the spot. Use this whenever the user shares a YouTube or podcast link and wants it…
observer
Run a study session over a video or podcast the user wants to understand: transcribe it, prepare the concepts and the visuals before they press play, then answer whatever they ask at the exact moment they pause, with charts you build on the spot. Use this whenever the user shares a YouTube or podcast link and wants it…
understanding-streamlit-architecture
Explains Streamlit's internal architecture including backend runtime, frontend rendering, and WebSocket communication. Use when debugging cross-layer issues, understanding how features work end-to-end, planning architectural changes, or onboarding to the codebase. Covers ForwardMsg/BackMsg protocol, script rerun…