The-Prompt-Shelf

# Repository Guidelines

- Repo: https://github.com/openclaw/openclaw
- In chat replies, file references must be repo-root relative only (example: `extensions/bluebubbles/src/channel.ts:80`); never absolute paths or `~/...`.
- GitHub issues/comments/PR comments: use literal multiline strings or `-F ...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

This is a **Claude Code plugin** - a collection of production-ready agents, skills, hooks, commands, rules, and MCP configurations. The project provides battle-te...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Detected stack
- Languages: Rust.
- Frameworks: none detected from the supported starter markers.

## Verification
- Run Rust verification from `rust/`: `cargo fmt`, `cargo clippy ...

# CLAUDE.md

> Quick reference for Claude Code when working on prompts.chat

## Project Overview

**prompts.chat** is a social platform for AI prompts built with Next.js 16 App Router, React 19, TypeScript, and PostgreSQL/Prisma. It allows users to share, discover, and collect prompts.

For detailed...

# Next.js Development Guide

> **Note:** `CLAUDE.md` is a symlink to `AGENTS.md`. They are the same file.

## Codebase structure

### Monorepo Overview

This is a pnpm monorepo containing the Next.js framework and related packages.

```
next.js/
├── packages/           # Published npm packages
├── t...

# Superpowers — Contributor Guidelines

## If You Are an AI Agent

Stop. Read this section before doing anything.

This repo has a 94% PR rejection rate. Almost every rejected PR was submitted by an agent that didn't read or didn't follow these guidelines. The maintainers close slop PRs within hours...

# Global development guidelines for the LangChain monorepo

This document provides context to understand the LangChain Python project and assist with development.

## Project architecture and context

### Monorepo structure

This is a Python monorepo with multiple independently versioned packages th...

# CLAUDE.md

## Project Structure

Excalidraw is a **monorepo** with a clear separation between the core library and the application:

- **`packages/excalidraw/`** - Main React component library published to npm as `@excalidraw/excalidraw`
- **`excalidraw-app/`** - Full-featured web application (exc...

IMPORTANT: Ensure you’ve thoroughly reviewed the [AGENTS.md](AGENTS.md) file before beginning any work.
...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

This is a **Claude Code plugin** - a collection of production-ready agents, skills, hooks, commands, rules, and MCP configurations. The project provides battle-te...

# Deno Development Guide

## Table of Contents

- [Git workflow](#git-workflow)
- [High Level Overview](#high-level-overview)
- [Quick Start](#quick-start)
- [Commands](#commands)
- [Testing](#testing)
- [Development Workflows](#development-workflows)
- [Debugging](#debugging)
- [Codebase Navigation...

Firecrawl is a web scraper API. The directory you have access to is a monorepo:
 - `apps/api` has the actual API and worker code
 - `apps/js-sdk`, `apps/python-sdk`, `apps/rust-sdk` and `apps/java-sdk` are various SDKs

When making changes to the API, here are the general steps you should take:
1. W...

# CLAUDE.md

This file provides guidance to Claude Code when working with code in this repository.

## Project Overview

Official MCP reference server implementations. This is an npm workspaces monorepo containing 7 servers (4 TypeScript, 3 Python) under `src/`. Each server is a standalone package p...

Skills are organized into bucket folders under `skills/`:

- `engineering/` — daily code work
- `productivity/` — daily non-code workflow tools
- `misc/` — kept around but rarely used
- `personal/` — tied to my own setup, not promoted
- `in-progress/` — drafts not yet ready to ship
- `deprecated/` —...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Browser-Use is an async python >= 3.11 library that implements AI browser driver abilities using LLMs + CDP (Chrome DevTools Protocol). The core architecture enables AI agents to auto...

# FastAPI — CLAUDE.md

## Project Overview

FastAPI is a modern, fast (high-performance) web framework for building APIs with Python based on standard Python type hints.

## Development

```bash
# Install dev dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Run with coverage
pytest --cov=...

# Rust coding guidelines

* Prioritize code correctness and clarity. Speed and efficiency are secondary priorities unless otherwise specified.
* Do not write organizational or comments that summarize the code. Comments should only be written in order to explain "why" the code is written in some way ...

# Prompt Engineering Guide

## Project Overview
Open-source prompt engineering guide at promptingguide.ai. Built with Next.js (Nextra theme).

## Project Learnings
Read and follow the project learnings in `Prompt-Engineering-Guide-notes/learnings/` before starting work. These are distilled from past...

# Supabase — CLAUDE.md

## Monorepo Structure

This is a Turborepo monorepo. Key packages:

- `apps/www` — Marketing site (Next.js)
- `apps/studio` — Supabase Studio dashboard (Next.js)
- `packages/ui` — Shared UI components
- `packages/shared-data` — Shared TypeScript types/data

## Setup

```bash
...

# Project Agent Instructions

Python environment:

- Always use the backend Poetry virtualenv (`backend-py3.10`) for Python commands.
- Preferred invocation: `cd backend && poetry run <command>`.
- If you need to activate directly, use Poetry to discover it in the current environment:
  - `cd backen...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

Antigravity Kit is an AI-powered design intelligence toolkit providing searchable databases of UI styles, color palettes, font pairings, chart types, and UX guide...

# Claude Code Configuration — WiFi-DensePose + Claude Flow V3

## Project: wifi-densepose

WiFi-based human pose estimation using Channel State Information (CSI).
Dual codebase: Python v1 (`v1/`) and Rust port (`v2/`).
### Key Rust Crates
| Crate | Description |
|-------|-------------|
| `wifi-dense...

# gstack development

## Commands

```bash
bun install          # install dependencies
bun test             # run free tests (browse + snapshot + skill validation)
bun run test:evals   # run paid evals: LLM judge + E2E (diff-based, ~$4/run max)
bun run test:evals:all  # run ALL paid evals regardless...

# Claude Code Configuration - Ruflo v3.5

> **Ruflo v3.6** (2026-04-29) — Stable release with agent federation and comms-first coordination.
> 6,000+ commits, 314 MCP tools, 16 agent roles + custom types, 19 AgentDB controllers, 21 native plugins.
> Packages: `@claude-flow/[email protected]`, `claude-flow@...

# Astro Framework — CLAUDE.md

## Project Overview

Astro is a web framework that generates fast, content-focused websites. Key innovations:
- **Island Architecture**: Partial hydration — only interactive components ship JavaScript.
- **Content Collections**: Type-safe content management with Zod sc...

# Claude-Mem: AI Development Instructions

Claude-mem is a Claude Code plugin providing persistent memory across sessions. It captures tool usage, compresses observations using the Claude Agent SDK, and injects relevant context into future sessions.

## Architecture

**5 Lifecycle Hooks**: SessionSt...

# AI Assistant Guide

This file provides guidance to AI coding assistants when working with code in this repository. Adherence to these guidelines is crucial for maintaining code quality and consistency.

## Guiding Principles (MUST FOLLOW)

- **Keep it clear**: Write code that is easy to read, main...

# agent-skills

This is the agent-skills project — a collection of production-grade engineering skills for AI coding agents.

## Project Structure

```
skills/       → Core skills (SKILL.md per directory)
agents/       → Reusable agent personas (code-reviewer, test-engineer, security-auditor)
hooks/...

# CLAUDE.md - PyTorch Image Models (timm)

## Build/Test Commands
- Install: `python -m pip install -e .`
- Run tests: `pytest tests/`
- Run specific test: `pytest tests/test_models.py::test_specific_function -v`
- Run tests in parallel: `pytest -n 4 tests/`
- Filter tests: `pytest -k "substring-to-...

# CLAUDE.md

AI-powered penetration testing agent for defensive security analysis. Automates vulnerability assessment by combining reconnaissance tools with AI-powered code analysis.

## Commands

**Prerequisites:** Docker, Anthropic API key in `.env`

```bash
# Setup
cp .env.example .env && edit .e...

# Project: claude-agents

Claude Code plugin marketplace — 72 focused plugins, 112 agents, 146 skills, 79 tools.

## Repository Structure

```
claude-agents/
├── .claude-plugin/marketplace.json   # Registry of all plugins
├── plugins/                          # All 72 plugins
│   ├── <plugin-name>/
...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## CockroachDB Development Environment

CockroachDB is a distributed SQL database written in Go. We use Bazel as a build
system but most operations are wrapped through the `./dev` too...

# Financial Services Plugins

Cowork plugins and Claude Managed Agent templates for financial services. Each named agent ships two ways from one source.

## Repository Structure

```
├── plugins/
│   ├── agent-plugins/               #   named agents — one self-contained plugin each
│   │   └── <slug...

# CLAUDE.md

This file provides guidance to Claude Code when working with this repository.

## Project Overview

Node.js CLI tool for managing Claude Code components (agents, commands, MCPs, hooks, settings) with a static website for browsing and installing components. The project includes Vercel AP...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Repository Overview

This is a best practices repository for Claude Code configuration, demonstrating patterns for skills, subagents, hooks, and commands. It serves as a reference ...

# QMD - Query Markup Documents

Use Bun instead of Node.js (`bun` not `node`, `bun install` not `npm install`).

## Commands

```sh
qmd collection add . --name <n>   # Create/index collection
qmd collection list               # List all collections with details
qmd collection remove <name>      # Re...

# CLAUDE.md

Before you start working on this repository, read the AGENTS.md file and follow all the instructions.
...

{
  "permissions": {
    "allow": [
      "Bash(cargo insta:*)",
      "Bash(grep:*)",
      "Bash(find:*)",
      "Bash(just:*)",
      "Bash(cargo test:*)",
      "Bash(cargo check:*)",
      "Bash(cargo run:*)",
      "WebFetch(domain:github.com)",
      "WebFetch(domain:typescript-eslint.io)",
 ...

# Drizzle ORM — CLAUDE.md

## Philosophy

Drizzle is "SQL for TypeScript" — if you know SQL, you know Drizzle. The API mirrors SQL syntax rather than abstracting it away.

## Schema Definition

```typescript
// db/schema.ts
import { pgTable, uuid, text, timestamp, integer } from 'drizzle-orm/pg-core...

# CLAUDE.md

Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.

**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.

## 1. Think Before Coding

**Don't assume. Don't hide confusion. Surface trad...

# Instructions for AI Agents Working on Beads

> **Reading order**: Architecture → `docs/CLAUDE.md` | Workflow → `AGENT_INSTRUCTIONS.md` | PR maintenance → `PR_MAINTAINER_GUIDELINES.md` | Quick ref → `AGENTS.md`
>
> Run `bd prime` for AI-optimized context. Run `bd memories` to see persistent learnin...

When contributing to this repository, you must strictly follow all guidelines outlined in the AGENTS.md file.
...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Development Commands

**Essential Commands (use these exact commands):**
- `uv run poe format` - Format code (BLACK + RUFF) - ONLY allowed formatting command
- `uv run poe type-che...

# Hono — CLAUDE.md

## Overview

Hono is a fast, lightweight web framework for the Edges. Runs on Cloudflare Workers, Fastly Compute, Deno, Bun, Vercel, Netlify, AWS Lambda, and Node.js.

## Basic App

```typescript
import { Hono } from 'hono'

const app = new Hono()

app.get('/', (c) => c.text('Hel...

# CLAUDE.md — caveman

## README is a product artifact

README = product front door. Non-technical people read it to decide if caveman worth install. Treat like UI copy.

**Rules for any README change:**

- Readable by non-AI-agent users. If you write "SessionStart hook injects system context," invi...

# CLAUDE.md / AGENTS.md

This file provides guidance when working with code in this repository.

## Project Overview

NeMo Speech — toolkit for training/deploying speech models (ASR, TTS, Speech LLM). Active collections: `asr`, `tts`, `audio`, `speechlm2`, `common`. No Megatron / Megatron Core / Tra...

# Claude Quickstarts Development Guide

## Legal

- When changes are made to files that have a copyright notice add them to that subdirectory's CHANGELOG.md file.

## Computer-Use Demo

### Setup & Development

- **Setup environment**: `./setup.sh`
- **Build Docker**: `docker build . -t computer-use...

# Career-Ops -- AI Job Search Pipeline

## Origin

This system was built and used by [santifer](https://santifer.io) to evaluate 740+ job offers, generate 100+ tailored CVs, and land a Head of Applied AI role. The archetypes, scoring logic, negotiation scripts, and proof point structure all reflect ...

{
  "hooks": {
    "SessionStart": [
      {
        "hooks": [
          {
            "type": "command",
            "command": ".claude/hooks/session-start.sh"
          }
        ]
      }
    ]
  }
}
...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

**Skill Seekers** converts documentation from 17 source types into production-ready formats for 24+ AI platforms (LLM platforms, RAG frameworks, vector databases,...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

# Instructor Development Guide

## Commands
- Install deps: `uv pip install -e ".[dev,anthropic]"` or `poetry install --with dev,anthropic`
- Run tests: `uv run pytest tests/ -n auto`...

# Deno Fresh — CLAUDE.md

## Overview

Fresh is a next-generation web framework for Deno. Key features:
- Zero client-side JavaScript by default (Island Architecture).
- No build step — just-in-time rendering.
- File-based routing.
- Built on Preact for the component model.

## Project Structure

``...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

This is the **Portkey AI Gateway** - a fast, reliable AI gateway that routes requests to 250+ LLMs with sub-1ms latency. It's built with Hono framework for TypeSc...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Build & Test Commands

```sh
pnpm install         # Install all workspace dependencies

pnpm build:all       # Build all packages
pnpm lint:all        # Run ESLint + Prettier check...

# OpenAI Agents SDK — CLAUDE.md

## Core Concepts

- **Agent**: An LLM configured with instructions, tools, and handoffs.
- **Tool**: Python function the agent can call. Decorated with `@function_tool`.
- **Handoff**: Transfer control to another specialized agent.
- **Runner**: Executes the agent lo...

# Langfuse — CLAUDE.md

## Overview

Langfuse is an open-source LLM engineering platform. Features:
- **Tracing**: Full observability of LLM calls, chains, agents.
- **Prompt Management**: Version-controlled prompts with A/B testing.
- **Evaluations**: Human annotation + LLM-as-judge + automated eva...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Purpose

This is a **comprehensive skills library** for Claude AI and Claude Code - reusable, production-ready skill packages that bundle domain expertise, best practices, ...

# Workflow

```bash
# Lint and style
# Check for issues and fix automatically
python -m ruff check src/ tests/ --fix
python -m ruff format src/ tests/

# Typecheck (only done for src/)
python -m mypy src/

# Run all tests
python -m pytest tests/

# Run specific test file
python -m pytest tests/test_...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Development Commands

```bash
# Start development server
npm run dev

# Build static site for production
npm run build

# Start production server (after build)
npm start

# Lint th...

# OpenLLMetry Repository Guide

## Repository Structure
This repository contains multiple PyPI-publishable packages organized and orchestrated using Nx workspace management.

### Nx Workspace Commands
```bash
# Run tests across all packages
nx run-many -t test

# Run linting across all packages
nx r...

# Guardrails — contributor guidance for Claude

## Dependency strategy (IMPORTANT — always follow)

This repo separates **compatibility** (what users are allowed to install) from
**security** (what we actually ship and test against). The two live in different
files and must be managed differently:

...

# CLAUDE.md

## Commands

```bash
bun test                # Run tests
bun run typecheck       # TypeScript type checking
bun run format          # Format with prettier
bun run format:check    # Check formatting
```

## What This Is

A GitHub Action that lets Claude respond to `@claude` mentions on i...

# CLAUDE.md

## Commands

```bash
bun test                # Run tests
bun run typecheck       # TypeScript type checking
bun run format          # Format with prettier
bun run format:check    # Check formatting
```

## What This Is

A GitHub Action that lets Claude respond to `@claude` mentions on i...

# Stripe Node.js SDK — CLAUDE.md

## Overview

This is the official Stripe Node.js library. It provides convenient access to the Stripe REST API from Node.js and browser environments.

## Development Setup

```bash
npm install
npm run build
npm test
```

## Code Style

- TypeScript strict mode is en...

# Anthropic Python SDK — CLAUDE.md

## Overview

The official Python library for the Anthropic API. Supports Claude claude-opus-4-5, Claude claude-opus-4-5, and all Claude models.

## Installation

```bash
pip install anthropic
```

## Basic Usage

```python
import anthropic

client = anthropic.Anth...

# CLAUDE.md - Kaneo

Self-hosted project management platform. pnpm monorepo: Hono backend + React frontend.

**Key Philosophy:** Features exist to solve real problems, not to impress. Avoid over-engineering.

## Commands
```bash
pnpm dev              # Start all services
pnpm build            # Buil...

# awesome-ChatGPT-repositories — Claude Code Guide

This repository is a curated list of 2500+ open-source GitHub repositories related to ChatGPT and LLMs. It includes a searchable skill for Claude Code.

## Repository structure

```
awesome-ChatGPT-repositories.json   ← main data (all 2500+ repos, ...

# Agentation

Monorepo containing:

1. **npm package** (`package/`) - See `package/CLAUDE.md`
2. **Website/docs** (`package/example/`) - See `package/example/CLAUDE.md`

## What is Agentation?

A floating toolbar for annotating web pages and collecting structured feedback for AI coding agents.

## D...

# Claude Code Ultimate Guide - Project Context

## Purpose

This repository is the **comprehensive documentation for Claude Code** (Anthropic's CLI tool). It teaches users how to use Claude Code effectively through guides, examples, and templates.

**Meta-note**: This repo documents Claude Code, so ...

{
  "permissions": {
    "allow": [
      "Bash(mkdir:*)",
      "Bash(pnpm test:*)",
      "Bash(pnpm changeset:*)",
      "Bash(/dev/null)",
      "Bash(pnpm build:*)",
      "Bash(pnpm typecheck:*)"
    ],
    "deny": ["Read(./.env)", "Read(./.env.*)"],
    "additionalDirectories": ["../workflow-...

# Learning Opportunities

Last verified: 2026-03-03

## What This Is

A Claude Code plugin packaging science-based learning exercises for deliberate skill development during AI-assisted coding. Author: Dr. Cat Hicks. License: CC-BY-4.0.

## Project Structure

- `.claude-plugin/marketplace.json` - Ma...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## What this is

A single-file writing skill (`SKILL.md`) that audits and rewrites content to remove AI writing patterns. No build system, no dependencies, no tests — the skill is a m...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Build Commands

```bash
# Install dependencies
pnpm install

# Build all packages (uses Turborepo)
pnpm build

# Type-check all packages
pnpm typecheck

# Check all packages (linti...

# Temporal TypeScript SDK — CLAUDE.md

## Key Concepts

- **Workflow**: Durable, fault-tolerant function. Must be deterministic.
- **Activity**: Non-deterministic I/O (API calls, DB queries). Called from workflows.
- **Worker**: Process that executes workflows and activities.
- **Signal**: Async mes...

# SceneView — Claude Code guide

## Project purpose

SceneView is an **AI-first SDK**: its primary goal is to enable Claude (and other AI
assistants) to help developers build 3D and AR apps in Jetpack Compose. Every design
decision — API surface, documentation, samples, `llms.txt` — should be optimi...

# CLAUDE.md - Developer Guide

This file provides guidance to Claude Code and developers working with this repository.

## Project Overview

iOS Simulator Skill is a production-ready Agent Skill providing 21 scripts for iOS app building, testing, and automation. It wraps Apple's `xcrun simctl` and F...

- Think before acting. Read existing files before writing code.
- Be concise in responses but thorough in reasoning.
- Prefer editing over rewriting whole files.
- Do not re-read files you have already read.
- No sycophantic openers or closing fluff.
- No em dashes, smart quotes, or Unicode characte...

## General

Do not tell me I am right all the time. Be critical. We're equals. Try to be neutral and objective.

Do not excessively use emojis.

Prefer using browser agent skill over using playwright directly.

## Coding Standards
When working with Laravel/PHP projects, always use the php-guidelines...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

This is an MCP (Model Context Protocol) server that provides Next.js development tools for AI coding assistants. The server exposes tools, prompts, and resources ...

# Claude Code Instructions for Skills Marketplace Development

**Repository:** claude-skills-marketplace
**Purpose:** Development guidelines for creating high-quality Claude Code skills and plugins

---

## 🎯 Repository Context

This is the **Claude Skills Marketplace** - a collection of reusable s...

# CLAUDE.md

## Overview
Go microservice following clean architecture principles.

## Project Structure
```
cmd/           - Application entrypoints
internal/
  domain/      - Business entities and interfaces
  usecase/     - Business logic (depends only on domain)
  adapter/     - Interface adapter...

# oh-my-agent v2.x — Claude Code Integration

## 프로젝트 정체성
- **oh-my-agent**: 멀티 에이전트 오케스트레이션 프레임워크
- **SSOT**: `.agents/` 디렉토리 (직접 수정 금지)
- **응답 언어**: 한국어 (`.agents/config/user-preferences.yaml` → `language: ko`)

## 아키텍처
- **13 도메인 Skills**: `.agents/skills/` (심링크로 `.claude/skills/`에 노출)
- **11 Wor...

## Push PR to GitHub workflow
This workflow should be initiated only if asked by the user.

### 1. Ensure current branch
- The remote origin/main branch is not writeable, so if there are changes on the main branch, create a new one and work over there

### 2. Preliminary TypeScript checks
The follow...

# EDDI Backend — AI Agent Instructions

> **This file is automatically loaded by AI coding assistants. Follow ALL rules below.**

## 1. Project Context

**EDDI** (Enhanced Dialog Driven Interface) is a multi-agent orchestration middleware for conversational AI. This repo is the **Java/Quarkus backen...

## PRE-OUTPUT GATE (mandatory, every response, no exceptions)

Before sending ANY response, run this check:

1. Scan every sentence for "?" that offers to take an action.
2. If found: **DELETE the sentence. Execute the action. Include the results instead.**
3. This is a blocking check. The response ...

# CLAUDE.md

> 本文件为 Claude Code CLI 提供项目特定配置和指导。

## 项目概述

**awesome-cursorrules-zh** 是一个 Cursor AI 编辑器规则集合网站，提供精选的 `.cursorrules` 规则文件。

## 技术栈

| 技术 | 版本 | 用途 |
|------|------|------|
| Node.js | >=20.0.0 | 运行时 |
| VitePress | ^1.6.4 | 静态站点生成 |
| markdownlint-cli2 | ^0.22.1 | Markdown 检查 |

## 常用命...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

This is **awesome-claude-md** - a curated collection of high-quality `CLAUDE.md` files from public GitHub repositories. The goal is to showcase best practices for...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. Detailed conventions, testing patterns, and architecture decisions are in `.claude/rules/`.

## What is Domscribe?

Domscribe is a pixel-to-code development tool that lets developers c...

# Markdown to EPUB Skill - Development Guide

## Project Overview

A Claude agent skill that converts markdown documents into professional EPUB3 ebook files. This is a custom skill implementation demonstrating how to build Claude Code skills with file generation capabilities.

## Quick Start

### Se...

# CLAUDE.md — Caliber

## What Is This

`@rely-ai/caliber` — CLI that fingerprints projects and generates AI agent configs (`CLAUDE.md`, `.cursor/rules/`, `AGENTS.md`, skills). Supports Anthropic, OpenAI, Google Vertex AI, OpenAI-compatible endpoints, Claude Code CLI, and Cursor ACP.

## Commands

`...

# vercel-plugin Development Guide

## Quick Reference

- **Build hooks**: `bun run build:hooks` (compiles `hooks/src/*.mts` → `hooks/*.mjs` via tsup)
- **Build manifest**: `bun run build:manifest` (generates `generated/skill-manifest.json` from SKILL.md frontmatter)
- **Build from skills**: `bun run...

@AGENTS.md
@CONTEXT.md

## Claude Code

- Skills live in `.claude/skills/<skill-name>/SKILL.md` - auto-discovered as slash commands
- Memory & learnings: `.claude/MEMORY.md` (update after non-obvious decisions)
- Codex discovers skills via `.agents/skills/` symlink. Cursor discovers `SKILL.md` files...

# Skills — Workflow Guide

This directory contains life sciences **skills** in two flavors: **code-centric** (pipeline/toolkit/database) and **prose-centric** (guide).
Claude Code uses this guide to author new entries when given a topic.

## Directory Layout

```
├── CLAUDE.md              ← you are...

# Claude AI Assistant Guidelines for Percolate Development

## Test Organization

Set envs to whatever .e.g if you add an env script like below run tests in that env with poetry
```
source set_res_env.sh && poetry run python -m pytest
```

### Test Directory Structure

All Python tests for the Perco...

# skills-for-humanity

A structured thinking toolkit delivered as Claude Code skills. Each skill encodes a complete reasoning methodology — not just instructions, but the full technique: when to apply it, when not to, how to sequence the steps, and what rigorous output looks like.

## Structure

```...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Commands

```bash
uv sync                                          # Install/update dependencies
uv run pytest                                    # Run all tests
uv run pytest test...

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## What this repo is

kstack is a **skill pack** (not an app) distributed to Claude Code and other agent CLIs. The shipped artifacts are `SKILL.md` files plus a handful of helper shel...

<frontend_aesthetics>
You tend to converge toward generic, "on distribution" outputs. In frontend design, this creates what users call the "AI slop" aesthetic. Avoid this: make creative, distinctive frontends that surprise and delight. Focus on:

Typography: Choose fonts that are beautiful, unique, ...

# Claude Code Best Practices (Official)

## CLAUDE.md Writing Guidelines
- Keep under 200 lines per file
- Write in imperative form (commands, not descriptions)
- Include only what Claude cannot infer from code
- Use bullet points, not paragraphs

## What to Include
- Build, test, deploy commands
- ...

# DataFlow Pipeline - CLAUDE.md

## Tech Stack
- Python 3.12 with FastAPI and Celery
- PostgreSQL for data warehousing, Redis as message broker
- Analytics: Polars (prefer over Pandas for performance) and DuckDB
- Package manager: uv (prefer over Poetry for speed)

## Commands
- Install deps: uv syn...

You are a Flutter expert specializing in building cross-platform mobile applications with Flutter 3+ and Dart.

Architecture
- Follow clean architecture: domain, data, and presentation layers.
- Use feature-based project structure.
- Implement dependency injection with get_it or injectable.
- Use re...

# Go Expert Subagent

You are a Go expert specializing in building efficient Go 1.21+ applications with idiomatic patterns, error handling excellence, and production-ready code.

## Concurrency & Performance
- Goroutine lifecycle management: always ensure goroutines can be stopped.
- Channel pattern...

# Flutter App Configuration Skill

This skill helps configure and develop Flutter applications with proper architecture and best practices.

## When to Use
- Setting up a new Flutter project
- Configuring app architecture and routing
- Creating reusable widget patterns
- Setting up state management
...

# Data Analyst Subagent

You are a data analysis expert specializing in extracting insights from structured and unstructured data using Python, SQL, and modern analytics tools.

## Core Skills
- Pandas/Polars for data manipulation and transformation
- SQL for database queries (PostgreSQL, BigQuery, ...