radon
joemccann/radon/CLAUDE.md
running for browser automation; check which instance is attached before driving the UI. - PDF rendering: skip WeasyPrint and md-to-pdf (missing native libs / no Chromium). Go straight to headless
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.
joemccann/radon/CLAUDE.md
running for browser automation; check which instance is attached before driving the UI. - PDF rendering: skip WeasyPrint and md-to-pdf (missing native libs / no Chromium). Go straight to headless
joemccann/radon/cloud/CLAUDE.md
Other targets, modified receipts, unrecognized paths and unverified source bytes are refused. ## MarketDesk deferred PDF archive `radon-marketdesk-pdf.service`, `.timer` and its runtime drop-in are setup-listed and manifest-pinned. Normal
joemccann/radon/web/CLAUDE.md
# Radon Web — CLAUDE.md Frontend rules and correctness invariants for the Next.js app. Loaded automatically
Johnson-Jia/video-clipforge/CLAUDE.md
编排和模式选择的权威工作流定义。 ## 什么是 ClipForge ClipForge 是 AI 驱动的通用短视频制作系统。通过 DAG 编排管线,将任意内容(文本、URL、PDF、GitHub 数据等)转化为抖音就绪的竖屏视频,含旁白、BGM 和封面。内容分类(GitHub、漫画、小说等)通过 `clipforge/categories/` 中的分类配置定义。 **核心管线**:`内容 → 设计
oomkapwn/enquire-mcp/CLAUDE.md
overclaim instance #13 (v3.9.0-rc.4): CLAUDE.md header line said "**Still deferred to v3.9.0+:** ... OCR'd PDF watcher embed-sync, HNSW in-memory live update, R-10 adaptive refill" — but the status
xu-xiang/awesome-top-skills/tags/claude.md
# Tag: claude - Back: [Tags](README.md) - Tagged skills: 219 | Skill | Repo | Summary | ⭐ | ⬇️ | Updated | Tags | | - | - | - | -: | -: | - | - | | [product
zhurudong/andrej-karpathy-llm-wiki/templates/CLAUDE.md
架构 ``` . ├── raw/ # 不可变原始文章(LLM 只读,人类只在摄入时写入) │ ├── YYYY-MM-DD-标题.md │ └── assets/ # 原文附件(图片、PDF 等),按文章分子目录 │ └── / # 与 raw .md 同 stem(过长时可缩写) │ └── NN-描述.{png,jpg,pdf,...} ├── wiki
arcadeai-labs/agent-library/CLAUDE.md
multi-modal assets (text, code, images, PDFs) ### Current Status - **Multi-Modal Support Complete:** Code, PDF, and image parsing with asset type preservation - **Parser Registry:** Automatic parser selection based on file
BulloRosso/etienne/CLAUDE.md
Project-specific Claude Code settings ├── data/ │ └── permissions.json # Tool permissions └── out/ # Output files ``` ## Working with PDF and Office Format Documents The standard skill **office-and-pdf-documents** provides document parsing capabilities
hummingbot/skills/CLAUDE.md
hummingbot-deploy` | Deploy Hummingbot infrastructure | | `lp-agent` | CLMM liquidity provision agent | | `slides-generator` | Create PDF slides from markdown | ## Installation Use the standard [skills CLI](https://github.com/vercel-labs/skills): ```bash npx skills
Joanium/Joanium-Classic/CLAUDE.md
with `electron-updater` for auto-updates - **Notable deps:** xterm.js (terminal), exceljs, jszip, mammoth, pdf-parse --- ## Workspace Structure ``` Core/Electron/ Main-process entry + window management Packages/Capabilities/ Integration modules (APIs, system tools) Packages/Features
joneqian/claude-skills-suite/CLAUDE.md
skills-suite/ ├── skill_seekers/ # Main Python package │ ├── cli/ # CLI tools (doc_scraper, github_scraper, pdf_scraper, etc.) │ └── mcp/ # MCP server implementation (FastMCP-based) ├── configs/ # Pre-built scraping configs for popular
applypack/applypack/CLAUDE.md
becomes text, an address is never followed) and `datasets/posting-file.ts` (bytes → text by kind, the PDF and `.docx` readers of `src/resume/`; `identifyPosting`, `savedPostingJob`) are pure. A change to what a saved
joe-qai/qa-skills/CLAUDE.md
into Skills | examples/ | | `prompt-engineer` | Prompt engineering and optimization | references/ | | `xlsx` | Excel processing | recalc.py | | `pdf` | PDF processing | pypdf, pdfplumber | | `pptx` | PPT processing | thumbnail.py, markitdown | ## Common Development Commands ### Python Environment ```bash
nicholasglazer/gnosis-mcp/CLAUDE.md
extras: `[postgres]` (asyncpg), `[embeddings]` (onnxruntime, tokenizers, numpy, sqlite-vec), `[web]` (httpx, trafilatura), `[rst]` (docutils), `[pdf]` (pypdf), `[formats]` (docutils + pypdf). Model download uses stdlib `urllib` (no `huggingface-hub` dependency). ## Tools ### Read
felipefontoura/spec-driven-development-book/CLAUDE.md
source of truth. The pipeline produces **three artifacts**: a print-ready 6×9" PDF (via Typst), a reflowable EPUB 3 (via marked + html-to-epub) and a static multi-page
estevesjh/mcp-ads-arxiv/CLAUDE.md
reading full-text files before aligning with the user**. **IRON RULE: never read a PDF's raw bytes or text. Always serve the docling-generated markdown** produced by `get_paper
ractive/hyalo/.claude/CLAUDE.md
mailto:`, `file://`) | `attachment` (resolved to a non-`.md` vault file: an image, a PDF, an Obsidian `.base`). `external` and `attachment` links are never broken and are not graph edges
workos/aie-europe-skills-at-scale/CLAUDE.md
slides && pnpm build # Build static SPA cd slides && pnpm export # Export to PDF (needs playwright-chromium) ``` Slides are a single `slides.md` file using Slidev markdown syntax. `---` separates slides. HTML comments
AI-Riksarkivet/ra-mcp/CLAUDE.md
handler scaffold `require_keyword` + `format_results`) that the 13 dataset libraries and the pdf-mcp guide search all reuse instead of each rolling their own search. Cross-cutting MCP helpers
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.