posterskill-academic-posters
AI-assisted academic conference poster generation from Overleaf source using Claude Code
What this skill does
# posterskill — Academic Poster Generator > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. posterskill is a Claude Code skill that generates print-ready, interactive conference posters from your Overleaf paper source. It produces a single self-contained HTML file with a built-in drag-and-drop visual editor — no build step, no server required. ## Installation & Setup ```bash git clone [email protected]:ethanweber/posterskill.git poster cd poster # Clone your Overleaf paper source git clone https://git.overleaf.com/YOUR_PROJECT_ID overleaf # Optional: add reference posters for style matching cp ~/Downloads/some_reference_poster.pdf references/ ``` Start Claude Code and trigger the skill: ```bash claude ``` ``` /make-poster ``` Claude will ask for your project website URL and any formatting specs, then generate a `poster/` directory with `index.html`. ## Directory Structure ``` poster/ # this repo ├── .claude/ │ └── commands/ │ └── make-poster.md # the skill command ├── overleaf/ # your cloned Overleaf project ├── references/ # optional reference PDFs for style matching └── poster/ # generated output ├── index.html # the poster (self-contained) └── logos/ # downloaded institutional logos ``` ## What Gets Generated The output `poster/index.html` is a React app (loaded via CDN) containing: - **`CARD_REGISTRY`** — each card's title, color, and JSX body content - **`DEFAULT_LAYOUT`** — column structure and card ordering - **`DEFAULT_LOGOS`** — institutional logos for the header - **`window.posterAPI`** — programmatic API for layout automation ## Visual Editor Features Open `poster/index.html` in Chrome to access the built-in editor: | Feature | How to Use | |---------|-----------| | Resize columns | Drag column dividers left/right | | Resize cards | Drag row dividers up/down within a column | | Swap cards | Click one diamond handle, then another | | Move/insert cards | Click a handle, then click a drop zone | | Adjust font size | Click **A-** / **A+** buttons in toolbar | | Preview print layout | Click **Preview** button | | Export layout | Click **Copy Config** to get JSON | ## Programmatic API (`window.posterAPI`) Available in the browser console or via Playwright automation: ```js // Swap two cards by ID posterAPI.swapCards('method', 'results') // Move a card to a specific column and position posterAPI.moveCard('quant', 'col1', 2) // Resize a column (in mm) posterAPI.setColumnWidth('col1', 280) // Set a specific card's height (in mm) posterAPI.setCardHeight('method', 150) // Scale all text globally posterAPI.setFontScale(1.5) // Measure whitespace waste (lower = better layout) posterAPI.getWaste() // Get the current layout as an object posterAPI.getLayout() // Get the full config as JSON (paste back to Claude) posterAPI.getConfig() // Reset to default layout posterAPI.resetLayout() ``` ## Iteration Workflow The core loop for refining your poster: 1. **Claude generates** first draft, opens `poster/index.html` in your browser 2. **You edit** in the browser — drag dividers, swap cards, resize columns 3. **Click "Copy Config"** in the toolbar to export your layout as JSON 4. **Paste the JSON back to Claude** — it updates `DEFAULT_LAYOUT` in the HTML 5. **Repeat** until the layout is perfect 6. **Print to PDF**: File → Print → Margins: None, Background Graphics: On ## Playwright Automation (used internally by Claude) Claude uses Playwright to automate layout verification. You can use it too: ```js const { chromium } = require('playwright'); async function optimizePoster() { const browser = await chromium.launch(); const page = await browser.newPage(); await page.goto(`file://${__dirname}/poster/index.html`); // Use the posterAPI to adjust layout programmatically const waste = await page.evaluate(() => posterAPI.getWaste()); console.log('Whitespace waste:', waste); // Resize a column await page.evaluate(() => posterAPI.setColumnWidth('col1', 300)); // Take a screenshot for visual verification await page.screenshot({ path: 'poster-preview.png', fullPage: true }); // Generate PDF at print resolution await page.pdf({ path: 'poster.pdf', width: '841mm', // A0 landscape width height: '1189mm', printBackground: true, }); await browser.close(); } ``` ## Card Registry Structure Each card in the poster is defined in `CARD_REGISTRY`: ```js const CARD_REGISTRY = { abstract: { title: "Abstract", color: "#f0f4ff", body: ` <p>Your abstract text here. Supports full JSX including <strong>bold</strong>, <em>italic</em>, and inline math.</p> ` }, method: { title: "Method", color: "#fff8f0", body: ` <img src="figures/pipeline.png" style={{width:'100%'}} /> <p>Caption describing the pipeline above.</p> ` }, results: { title: "Results", color: "#f0fff4", body: ` <table>...</table> ` } }; ``` ## Default Layout Structure ```js const DEFAULT_LAYOUT = { columns: [ { id: 'col1', widthMm: 280, cards: ['abstract', 'method'] }, { id: 'col2', widthMm: 320, cards: ['results', 'quant'] }, { id: 'col3', widthMm: 280, cards: ['conclusion', 'references'] } ] }; ``` ## Inputs Claude Uses | Input | Where It Comes From | Required | |-------|--------------------|---------:| | Paper content | `overleaf/` directory | Yes | | Project website | URL (asked at runtime) | Yes | | Reference posters | `references/*.pdf` | No | | Author website | URL for brand matching | No | | Formatting specs | Conference URL or text | Asked if missing | | Logos | Auto-downloaded to `poster/logos/` | Auto | ## Common Patterns ### Adding a custom figure card ```js // In CARD_REGISTRY, add a new card custom_fig: { title: "Qualitative Results", color: "#fafafa", body: ` <div style={{display:'grid', gridTemplateColumns:'1fr 1fr', gap:'8px'}}> <img src="figures/result1.png" style={{width:'100%'}} /> <img src="figures/result2.png" style={{width:'100%'}} /> </div> <p style={{fontSize:'0.85em', textAlign:'center'}}> Comparison on held-out test scenes. </p> ` } ``` Then add it to `DEFAULT_LAYOUT`: ```js { id: 'col2', widthMm: 320, cards: ['results', 'custom_fig'] } ``` ### Logos configuration ```js const DEFAULT_LOGOS = [ { src: 'logos/university.png', height: 60 }, { src: 'logos/lab.png', height: 50 }, { src: 'logos/sponsor.png', height: 45 }, ]; ``` ### Printing to PDF In Chrome: 1. Open `poster/index.html` 2. Click **Preview** to verify layout 3. `Ctrl+P` / `Cmd+P` 4. Set **Margins: None** 5. Enable **Background graphics** 6. Set paper size to your conference spec (A0, 36×48in, etc.) 7. Save as PDF ## Troubleshooting **Poster looks different in print vs browser** → Use Chrome (not Firefox/Safari). Enable "Background graphics" in print dialog. **Figures not loading** → Ensure figure paths in the HTML are relative to `poster/index.html`. Claude copies figures to `poster/figures/` — verify the directory exists. **Logos not fetched** → Claude uses Playwright to download logos from your project website. If it fails, manually copy logo files to `poster/logos/` and update `DEFAULT_LOGOS` paths. **Layout config not updating after paste** → Make sure you paste the full JSON from **Copy Config** — Claude looks for the complete `DEFAULT_LAYOUT` and `DEFAULT_LOGOS` objects to replace. **Font too small/large for poster size** → Use `posterAPI.setFontScale(1.2)` in the browser console, or click **A+** / **A-** buttons, then Copy Config and paste to Claude. **Whitespace gaps between cards** → Run `posterAPI.getWaste()` in console to quantify. Use `posterAPI.setCardHeight('cardId', heightMm)` to tune card heights, or drag row dividers manually. ## Example Output See the [Fillerbuster poster](http://ethan
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.