retain-pdf
wxyhgk/retain-pdf/CLAUDE.md
retainpdf_api_base::job_loading`)。 只给测试用的小工具(找项目 Python 环境的 `project_venv_bin`、最小 PDF `minimal_pdf_bytes`)也在底座包,挂在 `test-fixtures` 下。 - 读任务请求里的东西用 retainpdf-core `models/job/questions.rs` 的方法(`job.source
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.
wxyhgk/retain-pdf/CLAUDE.md
retainpdf_api_base::job_loading`)。 只给测试用的小工具(找项目 Python 环境的 `project_venv_bin`、最小 PDF `minimal_pdf_bytes`)也在底座包,挂在 `test-fixtures` 下。 - 读任务请求里的东西用 retainpdf-core `models/job/questions.rs` 的方法(`job.source
Akylas/OSS-DocumentScanner/.claude/CLAUDE.md
lives under `app/`: - `app/components/` — all `.svelte` screens/components/modals, grouped by feature (`camera`, `edit`, `list`, `ocr`, `pdf`, `pkpass`, `qrcode`, `security`, `settings`, `view`, `common`, `widgets`). Platform-specific logic uses `.android.ts` / `.ios.ts`. - `app/services/` — domain
AgriciDaniel/claude-blog/CLAUDE.md
category quality scoring (stdlib) scripts/blog_preflight.py # 5-gate delivery contract runner (v1.9.0) scripts/blog_render.py # md -> html -> pdf renderer; XSS-safe JSON-LD (v1.9.0) scripts/blog_hygiene.py # Optional deterministic hygiene: lazy-load imgs + auto
No other project uses it yet
natolambert/rlhf-book/CLAUDE.md
Feedback. **Live site:** https://rlhfbook.com ## Build System - **Pandoc + Make** for multi-format output (HTML, PDF, EPUB, DOCX) - Run `make` to build all formats - Run `make html` for just the HTML
0xMassi/webclaw/CLAUDE.md
client via wreq (BoringSSL). Crawler. Sitemap discovery. Batch ops. # + proxy pool rotation (per-request) # + PDF content-type detection # + document parsing (DOCX, XLSX, CSV) # + layered URL discovery (map) + Serper web search
K-Dense-AI/claude-scientific-writer/CLAUDE.md
verifiable citations. **Default Format:** LaTeX with BibTeX citations unless otherwise requested. **Quality Assurance:** Every PDF is automatically reviewed for formatting issues and iteratively improved until visually clean and professional. **CRITICAL
plutext/docx4j/CLAUDE.md
transitively, which is the point of it. - **docx4j-export-fo** (+ four `-fonts-*` modules) — docx→PDF via XSL-FO/Apache FOP. Other PDF strategies: **docx4j-documents4j-local/-remote** (drive MS Word
Steady18 mentions in 2 weeks
No other project uses it yet
1517005260/graph-rag-agent/CLAUDE.md
SLLPA algorithms - `summary/`: LLM-based community summary generation - **pipelines/ingestion/**: Multi-format document processing (TXT, PDF, MD, DOCX, DOC, CSV, JSON, YAML) - **evaluation/**: 20+ evaluation metrics for answer quality, retrieval performance
zakirkun/deep-eye/CLAUDE.md
info), `url`, `parameter`, `payload`, `evidence`, `remediation`; optional `cve_references`, `fingerprint`, `plugin`, `ai_evidence_summary`. - **PDF:** ReportLab only (not WeasyPrint on Windows). - **OAST:** `scanner.oast_callback_url` or `oast.enabled` local server
jhlee0409/claude-code-history-viewer/CLAUDE.md
search - ✅ Web search results (`type: "web_search_tool_result"`) - ✅ Document content (`type: "document"`) - PDF and plain text - ✅ Search results (`type: "search_result"`) - ✅ MCP tool use (`type: "mcp_tool_use"`) - Model
jgraph/docker-drawio/CLAUDE.md
entrypoint writes into `PreConfig.js`: it tells the editor that no export service exists, so PDF export falls back to the print dialog instead of posting to convert.diagrams.net (which rejects other
tsingyuai/scientify/CLAUDE.md
tools/ │ ├── arxiv-search.ts # ArXiv 搜索工具 │ ├── arxiv-download.ts # ArXiv 下载工具(含速率限制) │ ├── openalex-search.ts # OpenAlex 跨学科搜索 │ ├── unpaywall-download.ts # Unpaywall OA PDF 下载 │ ├── github-search-tool.ts # GitHub 搜索工具 │ └── paper-browser.ts # 论文分页浏览工具 ├── skills/ │ ├── idea-generation/ │ │ ├── SKILL.md │ │ └── references/idea-template.md │ ├── research-collect/SKILL.md # 文献搜索
flyingsaucerproject/flyingsaucer/CLAUDE.md
pure-Java CSS 2.1 renderer that turns well-formed XML/XHTML into Java2D, PDF, or SWT output. It is published to Maven Central under `org.xhtmlrenderer:*`. Java **21+** is required (CI also
Steady11 mentions in 2 weeks
No other project uses it yet
anthropics/cwc-workshops/ship-your-first-managed-agent/CLAUDE.md
memory", "make it remember", "part 3" | Part 3 | | "let it write a postmortem PDF", "add the report", "part 4" | Part 4 | | "next" | The lowest-numbered part that is still
Lumiwealth/lumibot/CLAUDE.md
LumiBot only with generic capabilities that help every strategy: browser use, file downloads, ZIP, PDF and CSV reading, API calls, and look-ahead safety that works for any source. While
deusyu/translate-book/CLAUDE.md
test_*.py' -v python3 -m compileall scripts tests ``` Then test with a small PDF to verify the full pipeline: ```bash python3 scripts/convert.py /path/to/small.pdf --olang zh # then run translation
formio/formio.js/CLAUDE.md
change to component rendering (`Component.render`, theme partials, `Display`) must be exercised through the PDF render path too.** See gotcha [`formio.js/pdf-render-path-diverges-01`](../../docs/gotchas/formio.js.md#pdf-render-path-diverges-01). - **New unit-test
No other project uses it yet
doobidoo/mcp-memory-service/CLAUDE.md
Chunker defaults: 1000 chars with 200 overlap. `semtools_loader.py` is optional and adds LlamaParse for PDF, DOCX and PPTX. ## Test Architecture About 2,400 tests across roughly 216 files. `tests/` mirrors
Steady5 mentions in 2 weeks
No other project uses it yet
ai-that-works/ai-that-works/2026-04-07-sse-streaming/Claude.md
Types ```baml image // for vision models audio // for audio models video // for video models pdf // for document models ``` ### Type Aliases ```baml type Primitive = int | string | bool | float type Graph
ranuts/document/CLAUDE.md
项目概述 基于 OnlyOffice 的本地 Web 文档编辑器,所有处理在浏览器端完成,无需服务器,保护用户隐私。支持 docx、xlsx、pptx、csv、pdf 等格式。 - **线上地址**:https://edit.chaxus.com/ (旧址 https://ranuts.github.io/document/ 已跳转至此) - **GitHub**:https://github.com/ranuts/document - **技术栈**:TypeScript
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.