second-brain
henrydaum/second-brain/CLAUDE.md
extension list, which would drift from what is installed. That is right for a PDF and inverted for a pointer: `parse_gdoc` opens with `json.loads(sdk.fs.read(path))`, so being textual
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.
henrydaum/second-brain/CLAUDE.md
extension list, which would drift from what is installed. That is right for a PDF and inverted for a pointer: `parse_gdoc` opens with `json.loads(sdk.fs.read(path))`, so being textual
chrisryugj/Docufinder/CLAUDE.md
Anything 프로젝트 로컬 문서 검색 앱 - HWPX, Office, PDF 지원 (Tauri + React) ## Quick Start ```bash # 프론트엔드 개발 서버 pnpm dev # Tauri 개발 모드 (Rust 빌드 포함) pnpm tauri:dev # 프로덕션
vincentarelbundock/marginaleffects/r/CLAUDE.md
documentation website generation with Quarto integration - Built-in support for both HTML and PDF book rendering ### Code Organization Conventions - Model-specific methods follow `get_predict.classname()` pattern - Test files use `test
xjtulyc/MedgeClaw/CLAUDE.md
/output/` | CSV、图表、报告 | | Dashboard | `data/ /dashboard/` | state.json, dashboard.html, serve.py | | 科学写作 | `writing_outputs/ _ /` | LaTeX、PDF、参考文献 | | 临时文件 | `data/ /temp/` | 中间产物 | **禁止写入:** - ❌ 项目根目录 - ❌ `outputs/`(已废弃,仅保留兼容) - ❌ OpenClaw workspace **`.gitignore` 已配置忽略所有输出目录,确保不会误提交数据
opendatalab/MinerU-Document-Explorer/CLAUDE.md
PDF/DOCX/PPTX files (requires Python 3 + pymupdf/python-docx/python-pptx) qmd collection add ~/papers --name papers --mask '**/*.{md,pdf,docx,pptx}' # Remove a collection qmd collection remove mynotes # Rename a collection qmd collection rename
meodai/skill.color-expert/CLAUDE.md
liner is too terse. - `references/techniques/ONLINE-TOOLS.md`, `references/PDFS.md` — Online tool catalogue and primary-source PDF list. - `references/historical/` — Pre-digital color science (Ostwald, Helmholtz, ISCC-NBS, etc.) - `references/contemporary/` — Modern color science (OKLAB, Briggs
aitytech/agentkits-marketing/CLAUDE.md
building` - Brand strategy, voice, positioning - `problem-solving` - Marketing problem-solving techniques - `document-skills` - DOCX, PDF, PPTX, XLSX document creation ### CRO Skills (Conversion Rate Optimization) - `page-cro` - Homepage, landing page, pricing
maxandrews/Epstein-doc-explorer/claude.md
Core Components ### Analysis Pipeline #### 1. Document Extraction (`analysis_pipeline/extract_data.py`) **Purpose:** Extract raw text from PDF documents **Input:** PDF files in `data/documents/` **Output:** JSON files in `analysis_pipeline/extracted/` **Key Features:** - Preserves
lijigang/ljg-skill-xray-paper/CLAUDE.md
该项目不包含传统意义上的源代码,而是一个用于学术论文深度分析的 Claude Code Skill。 ## 核心功能 该 Skill 用于解构学术论文,穿透学术黑话,还原作者最底层的逻辑模型。主要功能包括: 1. **输入支持**:PDF 路径、文本内容或论文链接 2. **认知提取算法**:去噪 → 提取 → 批判 3. **五维分析框架**: - 核心痛点:论文试图解决的具体困难问题 - 解题机制:作者的"灵光一闪"想法
jhaygood86/PeachPDF/CLAUDE.md
PeachPDF Pure .NET HTML → PDF rendering library. No external process dependency (no Puppeteer/wkhtmltopdf/gs) — HTML parsing, CSS cascade, layout, and PDF writing all run in-process. Targets
yuxiaopeng/Github-Ranking-AI/Top100/Claude.md
book-to-skill](https://github.com/virgiliojr94/book-to-skill) | 35099 | 3693 | Python | 7 | Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work
posit-dev/ggsql/CLAUDE.md
resolved `Spec` to an output format: Vega-Lite JSON (the default writer), SVG, PDF or a `.hep` plot document (all default features), or one of the four raster formats
posit-dev/ggsql/ggsql-cli/CLAUDE.md
with `ggsql-jupyter`). ## Features ```toml default = ["duckdb", "sqlite", "vegalite", "parquet", "builtin-data", "odbc", "svg", "pdf", "hep"] ``` Each feature passes through to `ggsql/ `. A writer feature gates only
posit-dev/ggsql/ggsql-jupyter/CLAUDE.md
plain build produces. The vector writers are not features here: `ggsql`'s `svg` and `pdf` are named unconditionally in `[dependencies]`, because the fallback path has to be compiled in whatever
posit-dev/ggsql/src/CLAUDE.md
Lite JSON. Deep-dive: [`writer/vegalite/CLAUDE.md`](writer/vegalite/CLAUDE.md). - **The renderer-backed writers** (seven of them; `svg`, `pdf` and `hep` default, the four raster ones not) — all live in `writer/hephaestus/`, named after
Hainrixz/the-architect/CLAUDE.md
reference site the user shares | | `browser-harness` | Escalation when that site needs a login | | `pdf` | Client-supplied RFPs, specs, brand guides | | `claude-api` | **Before writing any Claude model ID, price
Farzad-R/LLM-Zero-to-Hundred/RAG-GPT/CLAUDE.md
ChromaDB, and Gradio. Run from this directory. ```bash pip install -r requirements.txt # Terminal 1 — PDF file server (port 8000) python src/serve.py # Terminal 2 — Gradio UI (port 7860) python src/raggpt_app.py
Hainrixz/whatsapp-agentkit/CLAUDE.md
Colócalos en la carpeta /knowledge y presiona Enter cuando estén listos" Acepto: PDF, TXT, DOCX, CSV, imágenes, JSON, Markdown Si NO → Continuamos con lo que me has contado PREGUNTA
socfortress/CoPilot/CLAUDE.md
# CLAUDE.md Repository orientation for AI coding assistants and human contributors. The notes below capture
me2resh/apexyard/CLAUDE.md
HTML — boxes-and-arrows with per-page modals | | `/pdf` | Convert markdown / HTML / BPMN to PDF (destination-prompted) | | `/debug` | Structured hypothesis-driven debugging for issues that resisted naïve fixes | | `/update` | Sync
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.