hr-breaker
btseytlin/hr-breaker/CLAUDE.md
generates NEW HTML resume that: - Maximally fits the job posting - Follows guidelines: one-page PDF, no misinformation, etc. - Generated in target language (auto-detected from job/resume, or fixed) 4. System
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.
btseytlin/hr-breaker/CLAUDE.md
generates NEW HTML resume that: - Maximally fits the job posting - Follows guidelines: one-page PDF, no misinformation, etc. - Generated in target language (auto-detected from job/resume, or fixed) 4. System
CSlawyer1985/claude-for-legal-ZH/criminal-legal/CLAUDE.md
使用"[某涉案公司]"、"[某市公安局]"、"[某区检察院]"。 3. **案件编号与特写细节**:禁止包含卷宗编号、起诉书文号、极度特殊的物理位置或无法被普通概括的案件细节。 4. **禁止卷宗照片直传**:拒绝分析未经 OCR 并手动脱敏处理的卷宗照片或 PDF 截图。 **脱敏检查通过后的标准确认语**:"已确认输入完成脱敏。以下分析基于脱敏事实,不接触原始卷宗。" --- ## 公司概况 *团队级背景——与下文刑事专属内容分开存放。如已在其他插件中填充了此段,可复制至此,无需重新输入。* **组织/法人实体:** [PLACEHOLDER — 例如
magicyuan876/mineru-tianshu/CLAUDE.md
Engine routing (`litserve_worker.py::_process_task`) Per-task pipeline: vLLM container switch → legacy Office conversion → PDF split → watermark removal → engine dispatch → normalize → persist. Dispatch is keyed on the task's `backend
riba2534/happyclaw/CLAUDE.md
cache/office-preview/ ├── mcp-servers/{userId}/ ├── plugins/ ├── agent-profile-runtime/ ├── env/ └── extra/ ``` `data/cache/office-preview/` 是 Office 预览的 PDF 缓存:按源文件内容的 sha256 命名、跨用户 共享,总量受 `OFFICE_PREVIEW_CACHE_MAX_MB` 限制,可随时删除。 `data/config/web-push-vapid.json
aayushch/laya/CLAUDE.md
instead of trusting the first PATH hit. **Corpus documents** (`engine/laya/documents/`): user-shared files (PDF, DOCX, Markdown, text, CSV, JSON, HTML) parsed by the `parsers/` registry (one `PARSER` singleton per format
stophobia/deerflow2.0-enhanced/backend/CLAUDE.md
Multi-file upload with automatic document conversion: - Endpoint: `POST /api/threads/{thread_id}/uploads` - Supports: PDF, PPT, Excel, Word documents (converted via `markitdown`) - Rejects directory inputs before copying so uploads stay
tfriedel/claude-office-skills/CLAUDE.md
Repository Overview This is a skills repository for Office document manipulation (PPTX, DOCX, XLSX, PDF). Each skill provides workflows, scripts, and documentation for working with specific file formats. The repository
OSideMedia/higgsfield-ai-prompt-skill/CLAUDE.md
specs (registry: evals/spec-claims.json) ├── repo_walk.py ← Shared repo walk (skips .claude/worktrees and nested repos) ├── generate_user_guide.py ← Release PDF generator (+ validate_user_guide.py, │ sub_skill_descriptions.py) └── build_index.py ← Regenerates INDEX.md + CONTENTS blocks; checks QUICK FACTS anchors specs/ ← Machine-readable
Prismer-AI/Prismer/CLAUDE.md
skills/` — OpenClaw skill management - `config/client/` — Client-side configuration ### Editor Components (`web/src/components/editors/`) Four editor types: `pdf-reader` (PDF + OCR + annotations), `jupyter` (notebook execution), `pisa-editor` (LaTeX via AiEditor), `previews` (component renderers
Prismer-AI/Prismer/web/CLAUDE.md
React 19, and TypeScript. It covers the full research lifecycle: paper discovery, reading (PDF with OCR), data analysis (Jupyter), writing (LaTeX), and AI-assisted peer review. It also supports desktop/mobile
neo4j-labs/create-context-graph/CLAUDE.md
exports from AI chat platforms, and local-file for deterministic ingestion of local Markdown / PDF / HTML / AsciiDoc / Word documents into Document → Section hierarchies), custom domain generation, Neo4j Aura .env import
automateyournetwork/netclaw/CLAUDE.md
installer step) + `fastmcp`/`mcp`, `chromadb>=0.4`, `sentence-transformers>=2.2` (+ `torch` CPU), `rank_bm25`, `pymupdf` (PDF), `beautifulsoup4` + `httpx` (HTML/URL), `python-docx`, `openpyxl`, `python-pptx`, `vsdx` (modern office), LibreOffice headless (`soffice`, optional
shotgun-sh/shotgun/CLAUDE.md
format:** ```python expected_response="""The Router should immediately use file_requests to load the PDF file. Correct behavior: Set file_requests with the PDF path, provide a brief acknowledgment. Incorrect
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
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
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
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.