k2f-research-poster
Transform research papers, manuscripts, and findings into conference-ready academic posters with viewing distance typography, balanced columns, and high visual density. Use when asked to create an academic poster, scientific poster, conference poster, or A0/A1 poster. Create research posters with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
- Installs
- 747
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/suzheng/k2f --skill k2f-research-poster- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads k2f-research-poster automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
K2F Research Poster — AI-Native Aesthetic Design
Purpose
Convert scientific manuscripts, experiment data, and academic notes into print-ready conference posters. Posters fail when treated as oversized papers; attendees scan from 1.5–2 meters away and spend under 90 seconds. This skill enforces scientific distillation, viewing-distance hierarchy, strict 1-page geometry, and high visual density while eliminating multi-page overflow and blank lower thirds.
Built on K2F
This skill produces conference posters as .K2F packages. Follow the k2f skill for authoring: unpack or init a workspace, edit the semantic JSON tree (content/root.json), customize styles/theme.json, pack/verify, and export. K2F separates semantic structure from styling, compiling an immutable render lock that guarantees pixel-identical output across PDF, PPTX, DOCX, and IDML.
Before you build, install the core skill: npx skills add suzheng/k2f --skill k2f.
When to Use
- Creating conference posters from paper drafts, preprints, or notes.
- Designing large-format scientific presentations (Arch E 48"×36", 36"×48", ISO A0/A1).
- Transforming multi-page manuscripts into a single-page visual synthesis.
- Exporting vector PDF, editable PPTX, or IDML.
Inputs
- Dimensions: Landscape (48"×36" / ISO A0) or portrait (36"×48" / A0). Default: 48"×36" landscape (3 columns).
- Findings: Abstract, methods, key results, and conclusions.
- Visuals: Figures, plots, diagrams, and logos.
- Metadata: Title, authors, affiliations, paper/repo URL.
Workflow
1. Understand
Distill content into three tiers:
- 3-Second: Title, logos, takeaway banner.
- 30-Second: Conclusion-driven section headers, key charts, metric callouts.
- 3-Minute: Concise methods, data tables, references.
2. Plan
- Word Budget: 400–600 words (limit: 300–800). Posters are visual abstracts.
- Grid: Pinned header, 3-column body (2–3 for portrait), footer (
catalog/content/ex_poster_shell.json). - Visuals: Dedicate >= 40% area to diagrams, plots, cards, or tables.
3. Build
- Shell: Paper size in
manifest.json. Wrap root inpage_shellwith pinnedheight(page_height - margins) andbreak_inside: "avoid". - Typography (
styles/theme.jsonfor 1.5–2 m): Title 72–90 pt (bold), Headers (h1/h2) 36–44 pt, Subheads/Metrics (h3/stat_number) 28–34 pt, Body (body) 22–26 pt (>= 18 pt min), Captions 16–18 pt. - Components: Convert statistics to cards (
ex_card_bands.json) or tables (ex_table.json). Use{ "fr": 1 }growers to prevent gaps.
4. Validate
- Run
pack_verify.py --workspace <path> --render. - Single-page check:
pages=1. Pages > 1 is a hard defect. - Bottom-fill check: Baselines align above footer without voids (
PAGE_UNDERFILL). - Inspect rendered PNGs for legibility and clipping.
5. Revise
When overflowing or unbalanced:
- Cut non-essential text before shrinking fonts.
- Convert sentences into bullets or metric cards.
- Adjust column gap or card padding in
theme.json. - Reduce role font sizes globally in
theme.jsonby 1–2 pt.
Rules & Constraints
- Strict 1-Page Envelope: Posters are single-canvas presentations; spilling to page 2 disrupts display boards. Pin
page_shellheight to content box (page_height - margins) to guarantee single-page compilation. - Viewing Distance Physics: Reading distance is 1.5–2 m; body text below 20 pt is unreadable to standing attendees. Prune text rather than shrinking typography.
- Conclusion-Driven Headers: Scanning attendees decide whether to stop in seconds. State findings (e.g., "Model Cuts Latency by 42%") instead of generic labels ("Results").
- Styles in Theme Only: Define styling in
styles/theme.json. Keeping semantic nodes clean allows global adjustments and predictable compilation. - High Contrast: Conference halls have varied lighting; maintain WCAG AAA contrast using calm academic palettes with vibrant accents.
Common Failure Modes
| Failure Mode | Root Cause | Solution |
|---|---|---|
Multi-Page Overflow (pages > 1) | Unpinned height or excess text. | Pin page_shell height; prune text under 700 words. |
Empty Lower Canvas (PAGE_UNDERFILL) | Short text without growers. | Add { "fr": 1 } growers or enlarge visuals. |
| Wall of Text | Raw paper text pasted. | Condense to 3–4 bullets per card; use metric callouts. |
| Tiny Typography | Document fonts (< 18 pt) used. | Scale in theme.json: Title >= 72 pt, H1 >= 36 pt, Body >= 22 pt. |
| Lopsided Columns | Unequal column distribution. | Rebalance sections (Col 1: Problem; Col 2: Methods/Results; Col 3: Impact). |
Quality Checklist
- Geometry: Pinned
page_shellmatching content box; strictlypages=1. - Word Budget: 300–800 words total across poster.
- Hierarchy: Title readable from 5 m; headers from 2 m; body from 1.5 m.
- Visual Ratio: >= 40% surface area in figures, metrics, or tables.
- Column Balance: Baselines align evenly without voids.
- Export Fidelity: Clean vector PDF and editable PPTX shapes.
FAQ
What does the k2f-research-poster skill do?
Transform research papers, manuscripts, and findings into conference-ready academic posters with viewing distance typography, balanced columns, and high visual density. Use when asked to create an academic poster, scientific poster, conference poster, or A0/A1 poster. Create research posters with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
How do I install k2f-research-poster?
Run npx skills add https://github.com/suzheng/k2f --skill k2f-research-poster in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/k2f-research-poster/ (personal) or .claude/skills/k2f-research-poster/ (project).
Which AI agents can use k2f-research-poster?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is k2f-research-poster safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains k2f-research-poster?
It is published by suzheng in suzheng/k2f. It has 747 recorded installs.
More from suzheng/k2f
k2f-worksheet
suzheng/k2f
Design printable, fill-in-ready worksheets—practice sets, graphic organizers, lab records, reflections, or gap-closure forms—from learning goals and source material. Use when the user asks for a worksheet, handout with answer spaces, practice problems, graphic organizer, or structured questions students complete in class or at home. Create worksheets with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
k2f-quotation
suzheng/k2f
Create client-ready sales quotations from scope notes, line items, rates, and terms—structured so buyers can compare options, accept, or convert to an invoice without rework. Use when the user asks for a quotation, quote, estimate, proposal pricing, or RFQ response. Create quotations with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
k2f-idml
suzheng/k2f
Blueprint multi-page print publications—brochures, magazines, catalogs, annual reports, lookbooks—for designer handoff with spread-aware story flow, typed editorial blocks, and art direction before layout. Use when the user asks for InDesign, IDML, editorial layout, print collateral, or an editable package for a production designer. Create idmls with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
k2f-sales-deck
suzheng/k2f
Turn discovery notes, proposals, and product proof into buyer-ready sales decks with a prospect-centered story, one objective per meeting, and evidence-backed slides. Use when the user asks for a sales deck, demo presentation, proposal deck, executive briefing, or sales slides (not a fundraising pitch deck or generic company overview). Create sales decks with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
k2f-invitation
suzheng/k2f
Turn event facts and tone notes into print or digital invitations with ceremonial copy, layered logistics, and suite-consistent visual intent—not posters, programs, or slide decks. Use when the user asks for a wedding invitation, party invite, gala card, save-the-date, RSVP insert, or mobile e-invite. Create invitations with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
k2f-flyer
suzheng/k2f
Turn event details, offers, or brand notes into a single-page flyer with a scannable headline, one primary call to action, and mood-matched visual intent—not a brochure, slide deck, or poster wall. Use when the user asks for a flyer, leaflet, handout, promo sheet, open-house sheet, or print/digital one-pager for events, sales, restaurants, fitness, real estate, hiring, or community campaigns. Create flyers with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。