policyengine-us
PolicyEngine/policyengine-us/CLAUDE.md
source. Do not split a multi-page table into per-page entries. - PDF page numbers are file pages (1-indexed), not printed pages. - One cited page: `#page
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.
PolicyEngine/policyengine-us/CLAUDE.md
source. Do not split a multi-page table into per-page entries. - PDF page numbers are file pages (1-indexed), not printed pages. - One cited page: `#page
AI-WorkDeck/aiworkdeck/CLAUDE.md
里顺手更新对应领域文档**,防止文档腐烂。 - 新增领域时在本表加一行。 ## 编辑器跨格式联查(用户明确,2026-10-26) 对任意编辑器的性能、功能或交互作改动时,必须同时检查 **Word、PPT、Excel、PDF** 的对应路径,不能只验证本次直接修改的格式。先核对各格式实际使用的引擎、共享宿主与专属实现;在一类编辑器发现的重复读取、阻塞、渲染或保存问题,要检查其余三类是否存在同类问题,适用的优化在同一轮落实。 验收记录逐类说明打开、切换/滚动、输入或批注、保存重开等相关体验,以及共享改动的回归结果
Lucasuiii/cumcm-codex-workflow/CLAUDE.md
also runs compileall and JSON Schema validation; tool-dependent skips do not certify Windows PDF delivery. When you add a rule ID, test its failing and passing cases. Completeness checks
healthymind-tech/Taiwan-Health-MCP/CLAUDE.md
Drug pipeline: `drugIndex.ts` (the TFDA `36_2.csv` license index) → `drugEnrichment.ts` (TFDA crawl → MinIO) → `drugAnalysis.ts` (insert PDF → OCR → Analysis LM). OCR goes through `ocrProviders.ts` (`runOcr`: primary provider, then the optional `fallback_provider
javiera-vasquez/claude-code-job-tailor/CLAUDE.md
Claude Code (claude.ai/code) when working with code in this repository. ## Project Overview Dynamic PDF resume generator built with React and `@react-pdf/renderer`. Creates PDF documents using React components
sammcj/agentic-coding/Skills/extract-wisdom/CLAUDE.md
unittest discover -s tests` (stdlib, no network; covers the `frames` quote lookup) When testing PDF functionality during development or debugging avoid reading the raw PDF data in to your context
satoshikawato/gbdraw/CLAUDE.md
content/skew plots and BLAST comparison tracks. - **Version:** 0.14.5 - **Python:** ≥3.10 - **Output formats:** SVG, PNG, PDF, EPS, PS ## Quick Commands ```bash # Run tests (fast, excludes slow tests) pytest tests
owid/etl/CLAUDE.md
read_from_df`, not `Table(pd.DataFrame(...))`.** When you parse rows yourself (XML, HTML, a PDF, a nested JSON), collect them as a list of dicts and pass them to `snap.read
DenRakEiw/scumble/CLAUDE.md
# CLAUDE.md — Scumble (desktop app) Read this first, then `docs/BRIEF.md` (vision, decisions, architecture, phases). `docs/BUGS.md
oaustegard/claude-skills/CLAUDE.md
verb+ing form): - ✅ CORRECT: `creating-mcp-servers`, `processing-pdfs`, `updating-knowledge` - ❌ WRONG: `mcp-creator`, `pdf-processor`, `knowledge-update` These are non-negotiable requirements for all skills in this repository. ### CLAUDE.md
Open-Document-Alliance/PDF-Tools/CLAUDE.md
PDF Toolkit MCP - Development Guide ## Active Kepano / Shannon Work Before continuing the current extraction-improvement tranche, read `docs/handoffs/KEPANO_SHANNON.md`. The crucial starting fact is that Kepano's example is Shannon
HurricaHjz/SecondSelf/CLAUDE.md
articles/ ← web articles, long-form online writing │ ├── 2-papers/ ← academic papers, formal reports (often PDF) │ ├── 3-notes/ ← personal & meeting notes, raw thoughts │ ├── 4-webinfo/ ← docs, reference pages, repos, gists, tool
OWASP/cornucopia/.claude/CLAUDE.md
Converter scripts to convert translations for editions of the Cornucopia game into IDML and PDF files that can be printed. - [/cornucopia.owasp.org](/cornucopia.owasp.org): The Website for OWASP Cornucopia written in Typescript
SerhiiKorniienko/bullshit-detector/CLAUDE.md
captions), an article, a tweet (`https://x.com/naval/status/1002103360646823936` works), and a PDF. The `agents/` directory ships with the Claude Code plugin (auto-discovered) and holds subagents that skills delegate
ZIZKA-AI-SL/ZizkaDB/dashboard/CLAUDE.md
presets + range math live in `lib/report.ts`. Every number is real (no fabricated cost/token/SLA metrics). PDF export is `window.print()` + the `@media print` block in `globals.css` (isolates `.report-print-area`, reveals
HexSleeves/tailscale-mcp/CLAUDE.md
invoke /context-restore - Security audit, OWASP, "is this secure" → invoke /cso - Make a PDF, document, publication → invoke /make-pdf - Launch real browser for QA → invoke /open-gstack-browser - Import cookies for authenticated testing → invoke
watat83/document-chat-system/CLAUDE.md
powered analysis │ │ └── batch-process-documents.ts # Batch processing │ │ │ ├── documents/ # Document management logic │ ├── file-processing/ # File type handlers (PDF, DOCX, images, etc.) │ ├── auth/ # Clerk authentication utilities │ ├── storage/ # Supabase file storage │ ├── db/ # Prisma utilities
AnkitClassicVision/Claude-Code-Deep-Research/CLAUDE.md
Tools to use: 1. WebSearch for academic papers and technical resources 2. WebFetch for PDF extraction and content analysis 3. mcp__filesystem__ tools to save important findings Look for: - Peer
DjangoPeng/agentic-ai/ai-quant-cli/CLAUDE.md
repository. > 本文件只管 `ai-quant-cli/` 子项目。仓库根 `agentic-ai/CLAUDE.md` 是课程总览,与本文件并存。 ## 这个项目是什么 从年报 PDF 造一个本地系统:解析合并三张报表 → **由 Claude Code 亲自做财务风险研判** → 出图 → 生成 HTML 投研报告。构建按 `BUILD_PLAN.md` 的 6 个阶段推进
DjangoPeng/agentic-ai/CLAUDE.md
uploaded attachments into a job workspace. 2. Ingest supported PDF/image documents. 3. Extract native PDF text or OCR text, then parse invoice fields. 4. Validate required fields, confidence, compliance, deduplication
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.