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 design-editorial-and-presentationsgit 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/design-editorial-and-presentations)<a href="https://agentmods.dev/skills/evermind-ai/raven/design-editorial-and-presentations"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/design-editorial-and-presentations/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/design-editorial-and-presentations"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/design-editorial-and-presentations.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 | $0.00086 | $0.02458 |
| Opus 5.5 | $0.00034 | $0.00983 |
| Sonnet 5.5 | $0.00017 | $0.00492 |
| Haiku 4.5 | $0.00009 | $0.00246 |
Grade A, and why
design-editorial-and-presentations 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
编辑与演示设计
核心目标
把材料编辑成可讲、可读、可定位、可引用并可继续维护的发布物。质量来自内容顺序、字体关系、 图像职责、版面节奏和媒介适配，不来自更多卡片、边框或模板。
按以下顺序工作：
读者任务 → 自然媒介 → 内容脊柱 → 视觉系统与专业工具
→ 代表页型 → 完整序列 → 各媒介终态
本 Skill 决定编辑结构、自然媒介、出版工具和领域质量。最终由浏览器消费时，与
$build-polished-visual-frontends 组合；它负责 Web 实现和视觉系统，本 Skill 继续拥有内容顺序、
页型和出版语义。通用安全、渲染、review 与交付沿用 $visual-artifact-design，不在这里重复。
1. 先选择自然媒介
按读者如何使用内容选择主合同，不按文件扩展名选择：
| 主合同 | 用户行为 | 自然母版 |
|---|---|---|
| 分页出版 | 翻阅、查找、携带、引用或印刷 | 分页源、母版、样式和文本流 |
| 现场演示 | 在限定时间和观看距离内跟随讲述 | slide master、layout、notes 和放映状态 |
| 连续长文 | 在屏幕上阅读、定位、返回和重排 | 语义内容源、长文布局和稳定锚点 |
| 自动化报告 | 从数据、引用和参数反复重建 | 可执行文档、模板、数据和锁定环境 |
| 可访问 PDF | 使用辅助技术读取结构化 PDF | 上游语义母版与验证/修复管线 |
混合交付可以共享内容模型，但不能强迫共享同一布局。印刷跨页、连续阅读和投影演示分别设计， 只保持内容事实、顺序关系和视觉身份一致。
持续栏目、搜索、订阅或 CMS 运营转内容网站；自由筛选和数据发现转数据可视化；持续编辑、审批和 持久状态转产品工具；单张传播转营销图形。
2. 开工前写一张编辑卡
只记录会改变成品的决定：
读者与场景: 谁在何时阅读、观看或查找
主要任务: 读完或看完后应理解、找到或决定什么
媒介: 主合同、尺寸、页数或时长、设备和交接格式
内容脊柱: 论证、时间、对照、过程或浏览结构
内容状态: 已提供、可核验、缺失、受限和不得推断的部分
视觉方向: 真实参考、字体关系、图像角色、密度和节奏
专业工具: 候选、选择理由、原生母版和明确不用的方案
代表页型: 最能暴露方向、密度、资产或跨媒介风险的画面
来源、权利、版本、工具比较和构建记录属于内部 evidence，不是默认的版面内容。成品只显示读者为 理解当前内容所需的来源、状态和限制；详细账本放入交付说明、附录或按需展开，不把治理过程做成 横幅、卡片墙和灰色微字。
3. 分别选择视觉系统与专业工具
先确定编辑视觉系统：字体家族和角色、网格、版心、图像裁切、标题节奏、颜色职责、页码与导航。 再选择能原生承担媒介能力的工具。两者必须在代表页型中共同成立，工具默认模板不能自动成为设计。
| 任务与约束 | 优先考察 |
|---|---|
| 精细分页、品牌出版和专业印前交接 | Adobe InDesign、Affinity Publisher；开放格式可考察 Scribus |
| HTML/CSS 同源并同时需要分页 PDF 与 Web 阅读 | Vivliostyle；具体能力不足时再比较 Paged.js |
| 纯 PDF、结构化技术文档或高度可复现排版 | Typst |
| 数据、引用和多格式周期报告 | Quarto + Pandoc |
| 连续阅读的静态长文 | Astro/MDX 或现有内容系统 |
| 组织现场演示与可编辑交接 | PowerPoint、Keynote；浏览器技术演示可考察 Slidev |
这不是强制清单。先检查现有项目、接收方格式、语言与字体、自动化、许可、离线、印前和目标设备， 再查看真实样张（环境提供本地 visual catalog 时以其图版为准，可联网时看官方样张）并对最难页型 做最小能力验证。商业或 GUI 工具当前不可调用时，选择可用替代方案或 明确人工交接；不要声称使用了未实际运行的工具。
选定工具后采用它的原生结构：母版、段落/字符样式、文本流、notes、内容 schema、分页规则、交叉 引用和导出路径。不能只借它导出一次 PDF，再在另一套手写布局里维护真正的页面。
4. 先编辑内容脊柱
选择最适合读者任务的主结构：
- 判断 → 证据 → 决定：决策简报、方案建议；
- 问题 → 发现 → 重构：调查长文、观点演讲；
- 时间／过程推进：历史、教程、项目复盘；
- 对照 → 取舍：方案、产品或政策比较；
- 浏览／查找：目录、指南、手册和图录。
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 · 146 lines · 86 tokens per session scan A 4a4be10915be
design-editorial-and-presentations is a skill published in the GitHub repository EverMind-AI/Raven (5,463 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 2,458 once invoked, about $0.0003 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
anatomy
Explain an idea as an interactive isometric machine figure.
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
ip-as-logo
Design minimal cute IP mascot marks readable at 32px.
tldraw-offline
Drive and script tldraw offline canvases with an agent.
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
baoyu-infographic
An infographic generator that turns supplied content into a visual summary using different information layouts and visual styles. It supports standard and custom image proportions and multiple languages.