RecSys-Industrial-Book
jhljx/RecSys-Industrial-Book/CLAUDE.md
claude/skills/recsys-engineering/SKILL.md` The PDFs are authoritative. Build only the ignored local index; never commit extracted PDF text or a prose-equivalent Markdown book
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
jhljx/RecSys-Industrial-Book/CLAUDE.md
claude/skills/recsys-engineering/SKILL.md` The PDFs are authoritative. Build only the ignored local index; never commit extracted PDF text or a prose-equivalent Markdown book
daloopa/investing/CLAUDE.md
TICKER` — Cash conversion cycle, earnings quality & working capital deep-dive ### Investment Deliverables (.docx, .xlsx, .pdf) - `/research-note TICKER` — Generate professional Word research note - `/build-model TICKER` — Build multi-tab Excel financial model
Akylas/oss-weather/.claude/CLAUDE.md
lives under `app/`: - `app/components/` — all `.svelte` screens/components/modals, grouped by feature (`camera`, `edit`, `list`, `ocr`, `pdf`, `pkpass`, `qrcode`, `security`, `settings`, `view`, `common`, `widgets`). Platform-specific logic uses `.android.ts` / `.ios.ts`. - `app/services/` — domain
Siddhesh2377/ToolNeuron/CLAUDE.md
# ToolNeuron — Repo Guide Project memory for this repo. **When you change anything that affects
vorojar/Folio-OCR/CLAUDE.md
Chinese OCR prompt: 识别正文 + 跳过页眉页脚 + 表格输出为 Markdown/HTML - Auto-strips ```` ```markdown ``` ```` fences from model output - PDF → PNG via PyMuPDF at 2x resolution - Upload returns SSE stream (`init` → `page` × N → `done
duolahypercho/fusion-fable/CLAUDE.md
best practices for creating different document types (a docx skill for Word documents, a PDF skill for creating/filling PDFs, etc). These encode hard-won trial-and-error about producing professional
guiyumin/vget/CLAUDE.md
defines supported media types: - `MediaTypeVideo` - Video files (Twitter, etc.) - `MediaTypeAudio` - Audio files (podcasts) - `MediaTypePDF` - PDF documents - `MediaTypeEPUB` - EPUB ebooks - `MediaTypeMOBI` - MOBI ebooks - `MediaTypeAZW` - AZW ebooks - `MediaTypeUnknown` - Fallback (treated as video
neosun100/DeepSeek-OCR-WebUI/frontend/CLAUDE.md
party OCR APIs**. The tool converts scanned images/multi-page PDFs into: - Markdown - DOCX - Text+Image PDF All processing except OCR API calls must run **entirely in the browser**. --- ## Core Constraints (VERY
Autonomy-Logic/openplc-editor/CLAUDE.md
real-time communication - **Winston** for structured logging (main process) - **serialport** for serial communication - **pdf-lib** + **@pdf-lib/fontkit** for PDF export (print/export-to-PDF) ## Important Patterns ### When bumping the app version
ying-ge/FigureYa/CLAUDE.md
knitted report ├── easy_input_*.csv # Standardized input data files ├── example*.png # Style reference images ├── *.pdf # Vector graphic outputs └── output_*.txt # Results and tables ``` ### Key Architectural Patterns **1. Self-Contained Analysis
anthropics/healthcare/plugins/healthcare/skills/fraud-detection/scripts/CLAUDE.md
runs first (e.g. `fixedWidthToCsv()`), writes a clean headered CSV, then `ingest:` reads it normally. | | `pdf` | prose policy doc (NCCI manual, MLN article) | curl → `pdftotext -layout` → `policy/ .txt`. No DuckDB table
Community-Access/accessibility-agents/claude-code-plugin/CLAUDE.md
Full guided web accessibility audit | | document-accessibility-wizard | Document audit for .docx, .xlsx, .pptx, .pdf | | office-remediator | Programmatic Office document (Word/Excel/PowerPoint) remediation | | markdown-a11y-assistant | Markdown audit - links, headings, emoji
Community-Access/accessibility-agents/CLAUDE.md
step-by-step walkthrough | | Document Accessibility Wizard | Document accessibility audit for .docx, .xlsx, .pptx, .pdf - single files, folders, recursive scanning, delta scanning, severity scoring, remediation tracking, compliance export (VPAT/ACR
langchain-ai/langchain-google/CLAUDE.md
Part.from_bytes` type to pass a variety of data types (images, audio, video, pdf). ```python from google.genai import types with open('path/to/small-sample.jpg', 'rb') as f: image_bytes = f.read() response = client.models.generate
gtmagents/gtm-agents/CLAUDE.md
briefs, strategies | | `.csv` | Lead lists, data exports | | `.json` | Structured data, configurations | | `.xlsx` | Spreadsheets, reports | | `.pdf` | Final deliverables | --- ## Core Concepts ### 1. Plugins (67 total) Self-contained capability packages organized
rashidazarang/chatgpt-chat-exporter/CLAUDE.md
tool for exporting ChatGPT and Google Gemini conversations to Markdown, HTML, or print-ready PDF. Pure JavaScript that runs in the browser console or as userscripts — no runtime dependencies. ## Architecture
Pratiyush/llm-wiki/CLAUDE.md
what didn't sync and why. Non-AI adapters (Obsidian, Jira, Meeting, PDF) are opt-in only — they never fire on a default `sync` without explicit `enabled: true` in `sessions_config.json
gianlucasb/hallucinator/CLAUDE.md
Rust crates. ## Project Overview **Hallucinated Reference Detector** - Detects potentially fabricated references in academic PDF papers by validating against multiple databases (CrossRef, arXiv, DBLP, Semantic Scholar, ACL Anthology, Europe PMC, PubMed
bluewave-labs/verifywise/CLAUDE.md
Authentication architecture | `docs/technical/architecture/authentication.md` | | Multi-tenancy architecture | `docs/technical/architecture/multi-tenancy.md` | > Backend-specific refs (middleware, logging, BullMQ, email, PDF) are in `Servers/CLAUDE.md`. > Frontend-specific refs (styling, components, design tokens) are in `Clients/CLAUDE.md`. --- ## Additional Resources
kazukinagata/shinkoku/CLAUDE.md
path transactions.csv # ふるさと納税 uv run shinkoku furusato summary --db-path shinkoku.db --fiscal-year 2025 # PDF ユーティリティ uv run shinkoku pdf extract-text --file-path document.pdf uv run shinkoku pdf
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.