CLAUDE.md examples from real projects

pytorchCLAUDE.md

executorch

pytorch/executorch/CLAUDE.md

authored with AI, include tool name. ## Code Style - Minimal comments; code should be self-documenting - Comments only for non-obvious global context - No trivial (1-2 LOC) single-use helpers

No other project uses it yet

tencentmusicCLAUDE.md

supersonic

tencentmusic/supersonic/CLAUDE.md

webapp/packages/supersonic-fe/` **Evaluation scripts:** Python scripts in `evaluation/` directory for Text2SQL accuracy testing. ## Related Documentation - [README.md](README.md) - English documentation - [README_CN.md](README_CN.md) - Chinese documentation - [Evaluation Guide](evaluation/README.md) - Text2SQL evaluation process

liam-hqCLAUDE.md

liam

liam-hq/liam/CLAUDE.md

test ``` ## Architecture ### Monorepo Structure #### Applications - **frontend/apps/app** - Main Next.js web application (`@liam-hq/app`) - **frontend/apps/docs** - Documentation site (`@liam-hq/docs`) #### Public Packages - **frontend/packages/cli** - Command-line tool (`@liam-hq/cli`) - **frontend/packages/erd-core** - Core

PeonPingPipes a download into a shellCLAUDE.md

peon-ping

PeonPing/peon-ping/CLAUDE.md

vX.Y.Z` → Push tags: `git push --tags` → Update `../homebrew-tap/Formula/peon-ping.rb` URL and SHA256 if releasing ## Documentation rules **Whenever `README.md` is updated, also update all language variants:** - `README_zh.md` — Chinese translation (currently the only

rstudioCLAUDE.md

rstudio

rstudio/rstudio/.claude/CLAUDE.md

Playwright, under `e2e/rstudio/`. They drive the IDE through a JS automation bridge at `window.rstudio`, documented in `e2e/rstudio/CLAUDE.md`. See `.claude/skills/rstudio-create-playwright-tests/SKILL.md` for detailed guidance on writing Playwright tests, and `.claude/skills/rstudio-run-playwright-tests/SKILL.md

loopbackioCLAUDE.md

loopback-next

loopbackio/loopback-next/CLAUDE.md

sandbox/** — For testing monorepo packages as local dependencies - **benchmark/** — Performance benchmarks - **docs/** — Jekyll-based documentation site Managed with **Lerna** (independent versioning) and **npm workspaces**. ## Build & Development Commands ```bash # Install dependencies

No other project uses it yet

tidyverseCLAUDE.md

dplyr

tidyverse/dplyr/.claude/CLAUDE.md

active_file('R/{name}.R', desc = 'blah')" # To redocument the package Rscript -e "devtools::document()" # To check pkgdown documentation Rscript -e "pkgdown::check_pkgdown()" # To check the package with

diggerhqCLAUDE.md

digger

diggerhq/digger/docs/CLAUDE.md

Mintlify documentation ## Working relationship - You can push back on ideas-this can lead to better documentation. Cite sources and explain your reasoning when you do so - ALWAYS ask for clarification

clideyCLAUDE.md

whodb

clidey/whodb/CLAUDE.md

ambiguous changes. - Use subagents only for bounded sidecar work: exploration, review, test triage, or documentation lookup. - Prefer separate worktrees for parallel implementation sessions. - When a task touches `ee/`, follow `ee/AGENTS.md

No other project uses it yet

nibzardCLAUDE.md

awesome-agentic-patterns

nibzard/awesome-agentic-patterns/CLAUDE.md

claude.ai/code) when working with code in this repository. ## Project Overview This is a documentation website for "Awesome Agentic Patterns" - a curated catalogue of AI agent design patterns. It uses

getzepReads credentialsCLAUDE.md

zep / integrations

getzep/zep/integrations/CLAUDE.md

thread just scopes relevance). This is the default for conversational agents. - **Ingest business data / documents / JSON:** `graph.add(...)` (≤10,000 chars/call — chunk). - **Targeted search:** `graph.search(...)` with a `scope` (`edges`, `nodes`, `episodes

pdfmeDeletes or force-pushesCLAUDE.md

pdfme

pdfme/pdfme/CLAUDE.md

merge, split, rotate) - **packages/converter**: Format conversion utilities - **playground**: Interactive development and testing environment - **website**: Documentation site (Docusaurus) ### Key Architectural Patterns #### 1. Plugin-Based Field System Each field type (text, image

No other project uses it yet

Project-HAMiCLAUDE.md

HAMi

Project-HAMi/HAMi/CLAUDE.md

chart lives in `charts/hami/`; vendor settings live under `devices. ` in `values.yaml`, and values are documented with `# -- Description` comments for helm-docs - Image and tool versions are pinned in `version.mk`, `hack/verify-staticcheck.sh

No other project uses it yet

MicrosoftCLAUDE.md

poml

microsoft/poml/CLAUDE.md

build-webview # Build webview components npm run build-cli # Build CLI tool # Build documentation and specs npm run generate-component-spec # Generate componentDocs.json and components.md npm run generate-vscodeignore # Generate

MicrosoftCLAUDE.md

poml / poml-browser

microsoft/poml/packages/poml-browser/CLAUDE.md

React-based extension popup with Mantine components - **Common** (`common/`): Common utilities for clipboard, document handling, and POML processing (see below) ### Key Files - `manifest.json`: Chrome extension manifest - `rollup.config.mjs`: Build configuration with

campfireinReads credentialsCLAUDE.md

byterover-cli

campfirein/byterover-cli/CLAUDE.md

agent: `core/` (interfaces/domain), `infra/` (modules including llm, memory, map, swarm, sandbox, session, tools, document-parser), `resources/` (prompts YAML, tool `.txt` descriptions) - `server/` — Daemon infrastructure: `config/`, `core/` (domain/interfaces), `infra/` (modules including