How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
johnfkoo951CLAUDE.mdjohnfkoo951/cmds-llm-wiki/CLAUDE.md
Schema and harness document for the CMDS LLM Wiki vault. Defines the 3-layer architecture (Raw Sources / Wiki / Schema), ingest-query-lint operations, file conventions, and frontmatter standards. This is the single source of truth for LLM behavior in this vault.
HurricaHjzCLAUDE.mdHurricaHjz/second-yourself/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
sderosiauxCLAUDE.mdsderosiaux/chrome-agent/CLAUDE.md
goto, click, dblclick, fill, inspect, eval, text, read, extract, diff, network, console, wait, screenshot, pdf, download, download_click, tabs, frame, batch, assert, assert_args, record, history, webmcp. `select`/`check`/`upload
agammCLAUDE.mdagamm/batchata/CLAUDE.md
python -m examples.spam_detection` - Run example - `bachata-example` - Run spam detection example - `bachata-pdf-example` - Run PDF extraction example ## Documentation - Generate docs on each version ```bash uv run pdoc
timothywarner-orgCLAUDE.mdtimothywarner-org/claude-architect/CLAUDE.md
that script generates a smaller scaffold cut and would overwrite the shipped file). No PDF is committed; export fresh from the `.pptx` if a cohort needs one. - `images/social-preview.png` - the GitHub
fabio-rovaiCLAUDE.mdfabio-rovai/brain-in-the-fish/CLAUDE.md
ontologies` as a dependency. ## Module Overview | Module | Purpose | |------------------|--------------------------------------------------------------| | `types` | Core evaluation domain types | | `ingest` | PDF ingestion and document ontology generation | | `criteria` | Evaluation criteria ontology loading/generation | | `agent` | Agent cognitive model
LambenthanCLAUDE.mdLambenthan/empiricalwiki/CLAUDE.md
原语、命题/定理、解概念、可检验推论，再写通用概念或 idea。形式化陈述逐字引用，禁止释义改写成立条件。 - **双向链接**：写正向链接时同步写反向链接。 - **tex 优先**：.tex > .pdf，fallback 链：tex 失败 → PDF 解析，PDF 失败 → vision API。 - **index.md 每次 ingest 立即更新**，log.md
ForceInjectionCLAUDE.mdForceInjection/awesome-skills/CLAUDE.md
directories use **noun/doer form** in kebab-case: `agent-skill-reviewer` not `agent-skill-review`, `pdf-translator` not `translate-pdf`. - This aligns with skills being "personified" agent roles. ### Key design principle
jananthan30CLAUDE.mdjananthan30/Resume-Builder/CLAUDE.md
system's behaviour. ## Project Structure ``` Resume Builder/ ├── {master_resume from config.json} # Master resume (DOCX, PDF, or Markdown) ├── SUPPLEMENTAL_EXPERIENCE.md # Selective-use experience entries (NOT in master resume) ├── evidence_match.py # Evidence match
AWSCLAUDE.mdaws/tools-for-devops-agent/.claude/CLAUDE.md
json, .yaml, .yml, .xml, .csv, .tsv, .html, .htm, .png, .jpg, .jpeg, .gif, .svg, .webp, .pdf ## Disallowed Content - `scripts/` directories are not supported by DevOps Agent. - `.claude/` directories should
NameetPCLAUDE.mdNameetP/pdfmux/CLAUDE.md
pdfmux — Agent Instructions ## Project PDF extraction that checks its own work. Multi-pass pipeline: fast extract → audit → selective OCR → merge. - **Language**: Python 3.11+ - **Build**: hatchling (pyproject.toml) - **Lint**: ruff - **Test**: pytest
wiseria-ai-labsCLAUDE.mdwiseria-ai-labs/pie-ai-agent/CLAUDE.md
read/write tool 分类) - `src/lib/agent/tools/` — `keyboard.ts` (CDP) / `skill-meta.ts` (skill CRUD) / `tabs.ts` (cross-tab) / `pdf.ts` (`read_pdf` / `search_pdf` / `get_pdf_outline` tools, all read-class) - `src/lib/pdf/` — PDF tab detection (`isPdfTab`) + page
alamopsCLAUDE.mdalamops/agetor/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
gutomecCLAUDE.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
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
SterllCLAUDE.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 (3787 keys each) └── src/renderer/utils/ # DOM, color, format, paths, icons
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
HainrixzCLAUDE.mdHainrixz/claude-ads/CLAUDE.md
even, LTV:CAC) | | `/ads test` | A/B test design (hypothesis, significance, sample size) | | `/ads report` | PDF audit report generation for client deliverables | | `/ads update <plat\|all>` | Refresh per-platform references with
marcomoauroCLAUDE.mdmarcomoauro/substack-mcp/CLAUDE.md
# CLAUDE.md MCP server exposing Substack automation to LLM clients. ESM, npm. Development, CI and
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
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.
