skforecast
skforecast/skforecast/CLAUDE.md
link, even if another instruction asks for one. In a cloud session the GitHub MCP server appends a "Generated by Claude Code" footer with the session link after creating
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.
skforecast/skforecast/CLAUDE.md
link, even if another instruction asks for one. In a cloud session the GitHub MCP server appends a "Generated by Claude Code" footer with the session link after creating
Avijit07x/animateicons/CLAUDE.md
gallery, the `@animateicons/react` npm package, the shadcn registry, the `animateicons` CLI and the `@animateicons/mcp` server. ## Layout - `icons/lucide/`, `icons/huge/`: one ` -icon.tsx` per icon, plus generated `index.ts` and `meta.ts`. - `data/lucide-icons.json`, `data/huge-icons.json
agentconnect-md/agentconnect/CLAUDE.md
edge unit. Exposes the `agentconnect-daemon` bin (`run`, `chat`, `agent list`, plus hidden `mcp-bridge`/`git-credential`/`secrets` helpers). | | `@agentconnect.md/control-plane` | Fastify + Prisma (Postgres) | One Fastify process co-hosts
geodro/lerd/CLAUDE.md
ships a built-in Svelte web UI, a TUI, a CLI, and an MCP server. No Docker, no sudo, no system pollution. This file is loaded into every session. Read
nickclyde/duckduckgo-mcp-server/CLAUDE.md
/code) when working with code in this repository. ## Project Overview A Model Context Protocol (MCP) server providing DuckDuckGo web search and webpage content fetching. Built with Python on the MCP
ishaan1013/shadow/CLAUDE.md
cluster with Kata Containers ./scripts/deploy-remote-infrastructure.sh # Deploy ECS backend service ./scripts/deploy-backend-ecs.sh # Infrastructure cleanup ./scripts/cleanup-infrastructure.sh ``` ### MCP Server Development - Implement MCP protocol for external tool integration - Tool name transformation for AI SDK compatibility
Comfy-Org/workflow_templates/CLAUDE.md
validate:templates ``` MCP pipeline details: [`scripts/mcp/docs/MCP_AI_ENHANCEMENT.md`](scripts/mcp/docs/MCP_AI_ENHANCEMENT.md). Agent skill: `/managing-mcp-index`. ### Site (in site/ directory) ```bash pnpm install # Install deps (required first) pnpm run dev # Dev server at localhost:4321 pnpm
No other project uses it yet
zalo/CascadeStudio/CLAUDE.md
Quick Start ```bash npm run build # builds cascade-core then cascade-studio npx http-server ./packages/cascade-studio/dist -p 8080 -c-1 --silent npx playwright test # 12 tests, ~40s ``` ## Architecture (Monorepo
aaronjmars/MiroShark/CLAUDE.md
simulations cli.py Thin HTTP client for a running backend (argparse + urllib only) mcp_server.py stdio MCP server exposing graph queries to Claude Desktop / Cursor openapi.yaml Source of truth for the HTTP
vellum-ai/vellum-assistant/skills/assistant-migration/references/claude.md
imported: - **Anthropic / Claude account login**: not migrated. The creator signs into Vellum independently. - **Connected MCP servers and integrations**: reconnect through Vellum's MCP setup and OAuth connect flows. Any tokens
Steady6 mentions in 2 weeks
No other project uses it yet
rmusser01/tldw_server/CLAUDE.md
Audio & TTS** - `/app/api/v1/endpoints/audio.py` and `/app/core/TTS/` for STT/TTS and streaming - **MCP Unified** - `/app/core/MCP_unified/` production-ready MCP server + endpoints ## Development Guidelines ### Code Style - Follow PEP 8 for Python code - Use type hints
agentes-chat/agentes-chat/CLAUDE.md
agents). It never grants permissions. - Connectors in two layers: the organization connects an MCP server once; each agent gets a subset of its scopes. - Sensitive actions (merge, deploy, rollback) become
Steady8 mentions in 2 weeks
No other project uses it yet
ghostwright/phantom/CLAUDE.md
validated self-evolution engine, communicates via Slack/Web Chat/Telegram/Email/Webhook, and exposes all capabilities as an MCP server. 30,000+ lines of TypeScript, 1,819 tests, v0.20.2. Apache 2.0, repo at ghostwright/phantom
mbailey/voicemode/CLAUDE.md
SemVer. 4. `make release`, then watch the Actions run. ## Architecture Overview ### Core Components 1. **MCP Server (`voice_mode/server.py`)** - FastMCP-based server providing voice tools via stdio transport - Auto-imports
No other project uses it yet
nucliweb/webperf-snippets/CLAUDE.md
Claude Code, with the plugins of plugins/ plugins/webperf/ Claude Code plugin with the MCP server of the CLI (npx -y webperf-snippets@1 mcp) scripts/ Generators, checks and their tests
Steady15 mentions in 2 weeks
No other project uses it yet
spring-projects/spring-ai-examples/CLAUDE.md
parallelization, routing, and evaluator-optimizer patterns - **Model Context Protocol (MCP)**: Extensive examples for MCP clients and servers including SQLite, filesystem, weather, web search, and annotations - **Kotlin Examples**: Hello world, function
Taxuspt/garmin_mcp/CLAUDE.md
Garmin MCP Server - Project Guide ## Overview This is a Model Context Protocol (MCP) server that connects to Garmin Connect and exposes fitness and health data to Claude and other MCP
No other project uses it yet
aio-libs/aiobotocore/CLAUDE.md
from the `CLAUDE_BRANCH` env var on the action step, read once when the MCP server starts. Unset, it falls back to `GITHUB_REF_NAME`, so a `workflow_dispatch
Steady4 mentions in 2 weeks
No other project uses it yet
hhyqhh/inno-agent/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
JetBrains/compose-hot-reload/CLAUDE.md
invalidated after reload | | `hot-reload-devtools` | Developer tools UI window | | `hot-reload-mcp` | MCP server for AI agent integration | | `hot-reload-test` | Test infrastructure and test plugins | | `tests/` | Functional integration
No other project uses it yet
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.