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.
SterllReads credentialsCLAUDE.mdSterll/claude-terminal/CLAUDE.md
custom UI fields for workflow nodes ├── src/renderer/workflow-triggers/ # 12 trigger types (definition + configurator) ├── src/renderer/viewers/ # PDF viewer + 3D (three.js) viewer ├── src/renderer/i18n/ # EN/FR/ES/ID/zh-CN/pt-BR locales (4452 keys each) └── src/renderer/utils/ # DOM, color, format, paths, icons
GiuseppeDM98Reads credentialsCLAUDE.mdGiuseppeDM98/net-worth-tracker/CLAUDE.md
ResponsiveModal`. doc/guide/dialog.md; DESIGN → The Modal-Is-A-Tile Rule. - **Periodic emails · budget email · PDF export**: verdict first, AI comment second. doc/guide/email-pdf.md; DESIGN → The Out-Of-DOM Token Rule. - **Themes**: twelve
gutomecPipes a download into a shellCLAUDE.mdgutomec/nirvana-os-engine/CLAUDE.md
invoke the harness skill When the user asks for **any concrete artifact** — book, video, PDF, post, copy, design, illustration, brand, code, page, app, report, analysis, research, dataset, audit, anything — invoke
OpenDCAIReads credentialsCLAUDE.mdOpenDCAI/Open-NotebookLM/docs/CLAUDE.md
F43F5E), Newsreader serif headlines, Inter body. ### Source Processing (`fastapi_app/source_manager.py`) `SourceManager` handles file import: PDF (via MinerU), DOCX, PPTX, MD, URL → markdown. Integrates MinerU and SAM3 for document parsing. ### Deep
Benboerba620Reads credentialsCLAUDE.mdBenboerba620/ai-workspace-hub/CLAUDE.md
system/skills/workspace-status.md` + `workspace/review-queue.md` | 只读汇总，不修改判断 | | 升级工作区 | `system/skills/upgrade-workspace.md` | 先预览，确认后只更新受管文件 | | 摄入材料 | `wiki/_schema.md` + `system/integrations/personal-wiki.md`；笔记走 `system/skills/first-ingest.md` 并自动打标签，PDF 走 `system/skills/pdf-ingest.md` | `wiki/` | | 首次股票研究 | `system/skills/first-research.md` + `workspace/research-profile.md` | `output/research/` + 研究偏好 v0.1 | | 后续研究 | `workspace/research-profile.md` + `system/skills/research.md` + 两个知识索引；结束走 `system/skills/research-closeout.md
hashfunctionCLAUDE.mdhashfunction/MarkuprPlus/CLAUDE.md
Document generation and export │ │ ├── MarkdownGenerator.ts # llms.txt-inspired markdown output │ │ ├── ExportService.ts # Multi-format export (MD, PDF, HTML, JSON) │ │ ├── ClipboardService.ts # Clipboard bridge (copies file path) │ │ ├── FileManager.ts # Session file management │ │ └── sessionAdapter.ts # Type conversion
htlin222CLAUDE.mdhtlin222/dotfiles/shellscripts/CLAUDE.md
input. - Run `shellcheck` before committing. Recurring themes: media conversion (ffmpeg), document conversion (pandoc → PDF), tmux popups, Downloads cleanup, OpenAI-via-curl helpers
htlin222CLAUDE.mdhtlin222/dotfiles/zsh/CLAUDE.md
Utilities - `unlock` - Remove macOS app quarantine - `remind ` - Add system reminders - `topdf ` - Convert documents to PDF - `ya` - Yazi file manager integration ## Performance Optimizations The configuration includes several performance features: ### Cached Path
zoharbabinReads credentialsCLAUDE.mdzoharbabin/web-researcher-mcp/CLAUDE.md
SSRF-safe client; link verifier (liveness + Wayback archive) ├── documents/ # PDF, DOCX, PPTX extraction ├── cache/ # Cache interface + hybrid impl (memory L1 + optional Redis L2 + AES-encrypted disk L3) ├── persist/ # Generic
YuanyuanMa03CLAUDE.mdYuanyuanMa03/academic-research-skills/CLAUDE.md
search` — one per platform, sub-workflows in `references/`), 11 `nature-*` writing skills, 1 `scansci-pdf` retrieval bridge (paper download, citations, Zotero push via the scansci-pdf MCP server, MIT). - Literature
roedyrustamCLAUDE.mdroedyrustam/vibes-plug/CLAUDE.md
expert`, `email-notification-expert`, `file-upload-media-expert`, `n8n-automation-expert`, `chatbot-messaging-expert`, `pdf-document-generation-expert` | | 🛠️ Orchestration & Memory | `brainstorming`, `zero-to-prod-orchestrator`, `prd-architect`, `session-memory-manager
terancejiangCLAUDE.mdterancejiang/SKILL_financial_report_download/CLAUDE.md
Notes - Primary source: `stockn.xueqiu.com` (no anti-crawl); fallback: `notice.10jqka.com.cn` (同花顺) - The Python script validates PDF magic bytes and retries with backoff on failure - Supported markets: A-share (SH/SZ), Hong Kong
imdinuCLAUDE.mdimdinu/apple-mail-mcp/CLAUDE.md
FTS5 column; JXA fallback without index) search("deadline", scope="body") # Body only (FTS5) search("pdf", scope="attachments") # By attachment filename (SQL) search("invoice", after="2025-01-01") # Date-range filtering
jaikydotaReads credentialsCLAUDE.mdjaikydota/BullFlow/CLAUDE.md
models/外部存储`。 ### 三大核心管线 **1. RAG 文档管线**（`utils/file_parser.py` + `services/document_pipeline.py`） ``` 上传 → 解析降级链 → 语义分块 → 向量化 → 三库同步 ① PaddleOCR (PDF≤100 页 / 图片) ② Pandoc GFM (DOCX/HTML/EPUB/RTF/ODT…) ③ 原生 (PyMuPDF/python-docx/openpyxl/python-pptx) ④ 二进制拒绝 → status=completed, chunk_count=0, error
marcomoauroCLAUDE.mdmarcomoauro/substack-mcp/CLAUDE.md
# CLAUDE.md MCP server exposing Substack automation to LLM clients. ESM, npm. Development, CI and
the-omega-instituteCLAUDE.mdthe-omega-institute/automath/CLAUDE.md
编译, `sections/generated/` 下的 `.tex` 由 Python 脚本生成 - 单个 `.tex` 文件不超过 800 行, 超过须拆分 - 非明确指定时不自动编译 PDF - 二进制运算使用原生实现, 不用二进制字符串 - Lean 4: 使用 `lake` 构建 ## 语言与格式 - 工作语言默认中文, 英文版文档以 `_en.md` / `_en.tex` 结尾 - 公式只用
babamba2Reads credentialsCLAUDE.mdbabamba2/superclaude-for-sap/CLAUDE.md
preview.{jpg,html}` + `values.json` under the profile artifact base. Read-only. - `/sc4sap:smartform-from-pdf` — SmartForm from a PDF (or screenshot) of a printed form: `read-pdf` (texts / rules / images
longbridgePipes a download into a shellCLAUDE.mdlongbridge/skills/CLAUDE.md
shouldn't try to) do inline — for example: - DOCX / XLSX / PDF generation (`python-docx`, `openpyxl`, etc.) - Chart generation with bilingual fonts (`matplotlib` + CJK font fallback) - A safety-gate runtime check
sunnnybalaCLAUDE.mdsunnnybala/Rstack/CLAUDE.md
/experiment | Python | | `requirements.txt` | /experiment | Text | | `results/run-NNN/` | /experiment | Mixed (metrics.json, figures/, logs) | | `analysis/` | /analyze-results | PNG, PDF, .tex, .json | | `paper.tex` | /write-paper | LaTeX | | `paper.bib` | /write-paper | BibTeX | | `paper.pdf` | /write-paper | PDF | ### Plumbing (.rstack/) | File | Written
rsarverReads credentialsCLAUDE.mdrsarver/stella-decks/CLAUDE.md
PDFs viewer/index.html # Browser-based slide viewer scripts/ export-deck.mjs # Screenshot slides to PNG, compose into PDF export-deck-md.mjs # Export deck content as Markdown generate-image.mjs # Generate images via OpenAI API (optional) DESIGN.md # Design
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.
