shinkoku
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
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.
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
milady-ai/milady/CLAUDE.md
player` - CLI tools: `blucli`, `wacli`, `ordercli`, `tmux`, `1password` - Media / generation: `nano-banana-pro`, `nano-pdf` - Misc: `weather`, `healthcheck`, `yara-authoring` ### 2. Claude Code project skills (slash commands for THIS coding
Utopai-Research/pai-code/skills/CLAUDE.md
menu of options ## Anti-patterns to avoid - Verbose explanations of what Claude already knows ("PDF stands for…"). - Multiple options where one default would do — pick a default, mention escape hatch
kousen/claude-code-training/CLAUDE.md
TypeScript and comprehensive test suite - **Java Projects**: - `certificate-service`: Modern Spring Boot application with PDF generation - `shopping-service`: Legacy Grails/Groovy application for modernization exercises ### Skills and Custom Commands Integration - **`custom-commands.md
jsonresume/jsonresume.org/CLAUDE.md
stored duplicates together, no model re-read needed. - **Resume formats:** `/@username` serves a theme, `.pdf` (Chromium via `@repo/resume-pdf`; the deploy installs it for the `deploy` user), `.docx` (Word, built
OpenRaiser/PaperFit/CLAUDE.md
Visual Typesetting Optimization, VTO)**。 你的核心使命是:在论文已完成结构化格式排版(LaTeX 编译通过、内容完整)之后,通过**多模态证据链(源码 + 编译日志 + PDF + 页面图片)**驱动迭代闭环,消除视觉排版缺陷,使论文在专业审美、信息密度和可读性上达到出版级标准。 你**不是一个提供建议的顾问**,而是一个能够自主完成“修改源码 → 重新编译 → 视觉验收 → 状态持久化”的闭环执行系统。 --- ## VTO 任务定义与缺陷分类体系
TheDecipherist/claude-code-mastery-project-starter-kit/global-claude-md/CLAUDE.md
worst offenders --- ## Default File Locations ### Documents and Reports When asked to create documents (PDF, MD, reports, notes) with no specified location: - ALWAYS default to the `/docs` directory in the project
gatelynch/llm-knowledge-base/CLAUDE.md
個人成品與對外產出(origin: self) │ └── projects/ # 進行中的專案 │ # 依領域自訂子資料夾,如:文章/、教學記錄/、書稿/、簡報/ 等 │ └── attachments/ # 圖片、PDF 等附件 ``` ## 編譯規範 ### 摘要結構(wiki/summaries/) #### 外部來源(raw/ → wiki/summaries/) ```yaml --- origin: external source: "[[YYYYMMDD 標題]]" compiled: YYYY
olyaiy/resume-lm/CLAUDE.md
Radix** for component library - **TipTap** for rich text editing in resume sections - **React PDF** for PDF generation ### Database Architecture Three main tables with RLS policies: - **profiles**: Base resume information (JSONB
ajslater/codex/CLAUDE.md
frontend, SQLite database, WebSocket status updates. Users browse and read comics (CBZ, CBR, PDF) through a responsive web UI. A background librarian daemon watches the filesystem for changes and manages
fjrevoredo/mini-diarium/e2e/CLAUDE.md
feature and regression tests. - **Playwright** (`tests/print/`) — Print-CSS and PDF-layout tests. Loads static HTML pages in a headless Chromium browser; does **not** launch the Tauri binary. Use only
helloianneo/obsidian-ai-second-brain/CLAUDE.md
知识管理员的工作手册。把这个文件放在你的 Obsidian vault 根目录。 ## 目录职责 - **raw/** — 原始素材,**不可变**。AI 只读,永不修改。按主题分子目录,允许多级嵌套。PDF/视频/xlsx/图片保持原文件名。 - **wiki/** — AI 维护的消化笔记。允许多级子目录。每篇文章 md 格式,命名自由(描述性即可)。 - **assets/** — 配图资源。 ## 两个特殊文件
Rackarr/Rackarr/CLAUDE.md
after loading layout - Fixed u_height schema to allow 0.5U devices **v0.4.3–v0.4.5** — PDF export, toolbar polish - PDF export (US Letter, auto orientation) - Hamburger menu for narrow viewports - File
ai-analyst-lab/ai-analyst/CLAUDE.md
same cases), `/trace`, `/codex-review`. - **Deliverables**: brief + chart into `outputs/`; `/export` to Docs, Slides, Notion, PDF, Word. - **Pace**: `/pace guided | narrated | autopilot`. Never run an L3+ analysis silently in guided
AnttiHero/lavern/CLAUDE.md
retrieval, global datasets) - `src/assembly/` — Document assembly and format conversion (HTML, DOCX) - `src/documents/` — Document parser (PDF, DOCX, Markdown, plain text) + SMAC-L1 input sanitization - `src/utils/logger.ts` — Structured logging utility - Legal dataset seeder
Talljack/echo-type/CLAUDE.md
chat, TTS (Fish Audio, Kokoro, Google Cloud), pronunciation, translation, content import (URL, YouTube, PDF), assessment **Components** — organized by domain (`components/chat/`, `components/library/`, etc.) with shadcn/ui primitives in `components/ui/`. **Stores** (`src/stores
octree-labs/octree/CLAUDE.md
containing LaTeX files, edit them with AI assistance (via Claude Agent SDK), compile to PDF, and generate documents from chat conversations. ## Commands ```bash npm run dev:all # supabase start, then
Receipt-Wrangler/receipt-wrangler/api/CLAUDE.md
boot the server (skip in the sandbox):** the Python/torch/easyocr install, and the ImageMagick PDF-policy edit in `set-up-dependencies.sh` (it targets `/etc/ImageMagick-7/policy.xml`; a source build's policy is at `/usr/local/etc/ImageMagick-7/policy.xml
Receipt-Wrangler/receipt-wrangler/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
Receipt-Wrangler/receipt-wrangler/mobile/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
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.