CLAUDE.md examples from real projects

Olow304CLAUDE.md

memvid

Olow304/memvid/CLAUDE.md

cargo clippy cargo fmt # Run examples cargo run --example basic_usage cargo run --example pdf_ingestion # Benchmarks cargo bench ``` ## Key APIs ```rust // Create/Open let mut mem = Memvid::create("file.mv2

iamgioCLAUDE.md

quarkdown

iamgio/quarkdown/CLAUDE.md

LaTeX, with high-quality typography and layout customization - Compiler, parser and renderer to: - HTML - PDF (via a headless Chromium browser) - Plain text - CLI tool Quarkdown supports different document types, which

No other project uses it yet

storytoldCLAUDE.md

wordcraft

storytold/wordcraft/CLAUDE.md

docx`, `formats` | line breaking, pagination, tables, headers/footers, hit testing; OOXML I/O; TXT/MD/HTML/RTF/ODT | | L3 | `render`, `pdf`, `proof` | vello_cpu rasteriser; krilla PDF; proofing | | L4 | `engine` | Session, undo, **command registry**, Word feature

No other project uses it yet

zoteroCLAUDE.md

zotero

zotero/zotero/CLAUDE.md

submodules: - `reader/` -- PDF/EPUB/snapshot reader with annotations - `note-editor/` -- Rich text note editor - `document-worker/` -- PDF processing (extraction, manipulation) - `translators/` -- 760+ web translators for importing metadata from websites - `styles/` -- CSL citation

No other project uses it yet

yusufkaraaslanReads credentialsCLAUDE.md

Skill_Seekers

yusufkaraaslan/Skill_Seekers/CLAUDE.md

cli/document_skill_builder.py:DocumentSkillBuilder` sits between `SkillConverter` and the 9 document scrapers (epub, word, pptx, html, pdf, jupyter, man, rss, chat). It owns `categorize_content`, reference-file writing (tables, truncation, image guard

d2phapCLAUDE.md

ImageGlass / source

d2phap/ImageGlass/source/CLAUDE.md

watcher, caching) │ │ └── Photos/ # Photo, PhotoMetadata, PhotoColorProfile, etc. │ ├── Printing/ # Print layouts, layout engine, page renderer, PDF writer, PrintSession (see "Printing") │ ├── ServiceProviders/ # Interface contracts + shared providers │ │ ├── AppAPIs/ # App API provider interfaces │ │ ├── FileSearchService

browserlessReads credentialsCLAUDE.md

browserless

browserless/browserless/CLAUDE.md

automation via Docker. It supports Puppeteer and Playwright libraries, and provides REST APIs for PDF generation, screenshots, scraping, and more. ## Build & Development Commands ```bash # Full build (TypeScript + adblock + schemas + devtools

No other project uses it yet

jina-aiCLAUDE.md

reader

jina-ai/reader/CLAUDE.md

SERP. ### Worker threads `ThreadedServiceRegistry` (`src/services/threaded.ts`) extends `civkit`'s `AbstractThreadedServiceRegistry`. CPU-heavy work (DOM manipulation, PDF parsing, markify) runs in worker threads. The registry sniffs hyperthreading and sets `maxWorkers` to `cpus.length

No other project uses it yet

zubair-trabzadaCLAUDE.md

geo-seo-claude

zubair-trabzada/geo-seo-claude/CLAUDE.md

schema/*.json` | JSON-LD schema templates by business type | | `templates/` | `geo-report-style.css` + `geo-report-template.html` for the PDF report | | `docs/` | Long-form documentation (keep in sync with code) | | `examples/` | Sample audit outputs, proposals

genspark-aiCLAUDE.md

genoffice

genspark-ai/genoffice/CLAUDE.md

content is never re-authored by the theme.** Page surfaces, cell fills, slide content, PDF page bitmaps, export/print stylesheets, chart palettes, highlight color maps, stamps, and WordArt presets are document

No other project uses it yet

storytoldCLAUDE.md

vectorcraft

storytold/vectorcraft/CLAUDE.md

sample files. Write test inputs from scratch from the public specifications (PostScript Language Reference, PDF / ISO 32000, TIFF, EPSF/DCS). - Behaviour comes only from public documentation (helpx, published specs, public forum

No other project uses it yet

StarTrail-orgCLAUDE.md

PixelRAG

StarTrail-org/PixelRAG/CLAUDE.md

overview and `deploy/README.md` for how it runs in production. ## Layout - `render/` — `pixelshot` capture (Playwright/CDP, PDF) - `embed/`, `index/` — tiles → vectors → FAISS index - `serve/` — FAISS search API (`pixelrag serve`) - `web/` — Next.js frontend

No other project uses it yet

pacifioDeletes or force-pushesCLAUDE.md

atlas

pacifio/atlas/CLAUDE.md

load-bearing.** Two copies of `@codemirror/*` or `pdfjs-dist` break editor theming and PDF rendering _in production only_. `bun install`/`bun update` leave nested duplicates; after a lockfile change

digoalCLAUDE.md

blog

digoal/blog/CLAUDE.md

1.md (应用开发) │ ├── 2.md (日常维护) │ ├── 7.md (问题诊断与性能优化) │ └── ... (35 categories total) ├── me/ # Author biography ├── pic/ # Images ├── pdf/ # PDF files ├── backup/ # Backup files ├── old_blogs_from_163/ # Pre-2018 migrated articles from

OpenCoworkAIReads credentialsCLAUDE.md

open-codesign

OpenCoworkAI/open-codesign/CLAUDE.md

system (aligned with open-cowork tokens) artifacts/ # Artifact schema (HTML / React / SVG / PPTX) exporters/ # PDF / PPTX / ZIP exporters (lazy-loaded) templates/ # Built-in demo prompts and starter templates shared/ # Types

jacob-bdCLAUDE.md

notebooklm-mcp-cli

jacob-bd/notebooklm-mcp-cli/CLAUDE.md

unified content (audio, video, infographic, slides, etc.) | | `download_artifact` | Download any artifact (audio, video, pdf, markdown, json). Supports `wait`, `wait_timeout`, `poll_interval` params and returns `download_url` when

wadituCLAUDE.md

czsc

waditu/czsc/CLAUDE.md

权重时序图 / lightweight-charts 自包含 HTML - 已删除：`bar_generator.py` / `bi_info.py`（Rust 已实现）、`st_components.py` / `echarts_*` / `pdf_report` / `html_report_builder` / `word_writer` / `signal_analyzer` / `crypto/` / `czsc/svc/` / `plotting/backtest.py` / `plotting/common.py`（本次清理 删除 Streamlit 组件库与回测可视化函数；迁移详见

coleam00CLAUDE.md

ottomator-agents / claude-skill-archon

coleam00/ottomator-agents/claude-skill-archon/CLAUDE.md

specific** about capabilities and use cases 3. **Mention file types** or domain terms (e.g., "PDF", "API", "authentication") **Good Description**: ```yaml description: Extract text and tables from PDF files, fill PDF

tagspacesReads credentialsCLAUDE.md

tagspaces

tagspaces/tagspaces/CLAUDE.md

build-time JWT step. - `/extract-pdf` and `/hide-folder` are gone. `/extract-pdf` had no callers (PDF text goes through the indexer's `extendedExtraction`) and was an arbitrary-file-read primitive; `/hide-folder

MicrosoftCLAUDE.md

poml

microsoft/poml/CLAUDE.md

writer.ts`): Converts reader-produced intermediate representation to final output format - **Utilities** (`util/`): Image processing, PDF handling, token counting, XML content assist ### VS Code Extension (`packages/poml-vscode/`) - **Extension Entry** (`extension.ts`): Main activation