Raven is an open-source agent harness for running long-term AI work with terminal execution, tracing, memory, skills, evaluation, and reusable workflows. People use the current release to operate and improve persistent AI workflows, while its described future direction is a multi-agent system that combines specialized harnesses.
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 EverMind-AI/Raven --skill create-data-visualizationsgit clone --depth 1 https://github.com/EverMind-AI/RavenWrote 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/evermind-ai/raven/create-data-visualizations)<a href="https://agentmods.dev/skills/evermind-ai/raven/create-data-visualizations"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/create-data-visualizations/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/evermind-ai/raven/create-data-visualizations"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/create-data-visualizations.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 | $0.00090 | $0.02595 |
| Opus 5.5 | $0.00036 | $0.01038 |
| Sonnet 5.5 | $0.00018 | $0.00519 |
| Haiku 4.5 | $0.00009 | $0.00260 |
Grade A, and why
create-data-visualizations 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 1mo 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
创建数据可视化
核心目标
把数据变成可正确比较、查找、解释或监测的视觉证据。图形先回答问题，再展示字段；成熟工具负责 尺度、mark、交互和渲染，模型负责问题定义、数据语义、视图组合和解释边界。
按以下顺序工作：
读者问题 → 数据语义与状态 → 可复算 view model → 关系与编码
→ 视觉系统与图形引擎 → 代表视图 → 完整状态与终态
当主要价值来自量值关系、统计结构或数据状态时使用本 Skill。真实地理位置、投影或路网运算为主时
转地图；系统组成与流程为主时转技术图；查询、告警、处置、权限或持久工作流为主时，产品 Skill
拥有工作流，本 Skill 只拥有数据视图。浏览器交付与 $build-polished-visual-frontends 组合；它负责
产品视觉语言和 Web 工程，本 Skill 继续拥有数据、分析、编码与图形语义。
1. 先确定读者任务
只选一个主要模式，其他模式作为从属目标：
| 模式 | 用户真正需要完成什么 | 初始状态必须回答 |
|---|---|---|
| 探索 | 提出、比较和排除假设 | 当前范围、覆盖、质量和可比较关系 |
| 解释 | 无需操作也能理解一个有边界的发现 | 结论所对应的 mark、尺度、基准和证据 |
| 监测 | 重复判断状态、变化和是否需要行动 | 当前值、基准、时间窗、新鲜度和异常依据 |
| 出版 | 稳定复现和传播一个版本的证据 | 数据版本、版面、单位、来源和导出合同 |
为每个主问题写一行：
观测单位 / 时间与人群 / 指标和单位 / 比较基准 / 关系
数据状态 / 允许结论 / 禁止推断 / 精确读数入口 / 必要交互
一个主视图只承担一个首要关系。多视图只能形成概览—比较—细查、证据序列或监测共视，不能因为 字段多就平均铺成 dashboard。
2. 先建立真实数据状态
冻结数据来源、版本、键、粒度、单位、范围、覆盖和聚合规则。至少区分：
- 真实零；
- 缺失或未上报；
- 不适用；
- 抑制；
- 估计或临时值；
- 低可靠性或低样本；
- 异常值；
- 修订值与过期数据。
这些状态从 source 进入 validated records、derived dataset、view state、view model、图、表、摘要和 导出，不能在渲染阶段临时猜测。缺失不能变成零，低可靠性不能只靠降低透明度，过期数据不能继续 伪装成实时。
标题数字、图形、表格和下载从同一版本化 view model 派生。记录筛选、join、分母、权重、聚合、 舍入、排序、ties 和区间；用代表值独立复算，而不是相信图形看起来合理。
3. 分别选择产品视觉系统与数据工具
数据工具负责图形语法、尺度、交互和渲染；成熟设计系统负责页面外壳、控件、表格周边、反馈和 响应式。两者是不同选择，必须通过共享字体、token、密度、图例、选中和焦点形成一种视觉语言。
| 任务与约束 | 优先考察 |
|---|---|
| 清晰统计关系、解释图、小倍图和编辑式注释 | Observable Plot |
| 可移植、可校验的声明式 spec 与组合视图 | Vega-Lite；必要时下沉 Vega |
| 产品中的联动分析与中文生态 | AntV G2 |
| 高频监测、常见业务图型和较大 Canvas 数据量 | Apache ECharts |
| 多页交互报告、构建期数据快照和静态部署 | Observable Framework + Plot/其他适合引擎 |
| 精确表格、筛选、排序和虚拟长列表 | TanStack Table / Virtual 或成熟 Data Grid |
| 受治理指标、权限、查询和持续 BI | 组织已有 BI；无真实实例时不要模拟 |
| 高层工具无法表达的专属几何或直接操作 | D3，只实现能力探针确认的最小缺口 |
Observable Framework 是数据报告和 data app 的候选环境，不是所有分析产品的默认 UI。持续业务操作 通常采用成熟产品设计系统加 Plot、G2、ECharts、TanStack 等专业能力；不要让 Framework 的默认主题、 图表库默认配色或组件库示例页直接决定成品。
选型时查看真实样张（环境提供本地 visual catalog 时以其图版为准，可联网时看官方样张），并在当前
环境运行包含最难数据状态和交互的最小示例。比较原生数据模型、
任务覆盖、状态与无障碍、主题能力、框架集成、离线、性能、维护、许可和导出。选中的工具必须原生
拥有对应能力；只导入一个 mark、画一条轴或在 package.json 中出现名字，不算使用。
What ships with it
2 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.
- 1mo ago First seen · 161 lines · 90 tokens per session scan A c6c18e63e7ab
create-data-visualizations is a skill published in the GitHub repository EverMind-AI/Raven (5,463 stars, last pushed today), licensed Apache-2.0. It adds 90 tokens to every session and 2,595 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
anatomy
Explain an idea as an interactive isometric machine figure.
mcp-oauth-remote-gateway
Manual OAuth for remote MCP servers on headless gateways.
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
honcho
Configure and troubleshoot Honcho memory for Hermes.