By mesca
Opinionated Python development standards: project scaffolding, coding conventions, spec-driven development, testing, security, and automated audits
Audit project code against development guidelines and skills conventions. Use when checking codebase compliance, verifying code quality standards, checking testing coverage, or validating configuration files.
Scaffold a new Python project with the standard structure, tooling configuration, and a CLI that outputs project name and version. Use when starting a new project from scratch.
Simplifies and refines Python code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Project coding conventions covering code quality, structure, typing, logging, and style. Always apply when writing, reviewing, or modifying Python code.
Generate and maintain project documentation using Material for MkDocs and mkdocstrings. Use when creating API references, building documentation sites, or writing user guides.
Follow git commit conventions and branching strategies. Use when committing changes, creating branches, or writing commit messages.
Apply performance optimization best practices. Use when profiling slow code, optimizing memory usage, implementing caching, handling large datasets, or improving database queries.
Detect and provide the project name from package.json or pyproject.toml. Use when you need the project name, package name, or module name for imports, paths, or documentation.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Opinionated Python development standards for Claude Code. Scaffolds projects, enforces coding conventions, and audits compliance automatically.
Core principles injected at every session start. Non-negotiable.
Development loop — always follow this sequence, never skip steps:
contract → models → tests → implementation → simplify → documentation → audit
Interface design — every interface (CLI, API, web) must be designed from the end-user perspective: obvious mental model, simple, intuitive, consistent, explicit.
User-invokable slash commands that run as autonomous subagents.
| Command | Description |
|---|---|
/wf:init <name> [desc] | Scaffold a new Python project with full structure and tooling |
/wf:audit [category] | Audit codebase compliance against development guidelines |
/wf:simplifier [scope] | Refine Python code for clarity and consistency |
Usage examples:
/wf:init my-tool "A CLI tool for data processing"
/wf:simplifier
/wf:audit security
/wf:audit code testing
These skills are applied automatically by Claude when relevant:
| Skill | Purpose |
|---|---|
| conventions | Python coding standards: structure, typing, logging, style |
| simplifier | Code refinement for clarity and consistency |
| spec-driven | Contracts-first development with OpenAPI/OpenRPC/docopt and models-first workflow |
| tdd | Test-driven development: red-green-refactor with pytest |
| security | Secrets management, input validation, injection prevention |
| performance | Profiling, caching, memory optimization, async patterns |
| documentation | Material for MkDocs setup and API doc generation |
| git-workflow | Commit conventions, branch naming, pre-commit checks |
| project-name | Detects and normalizes ${PROJECT_NAME} from pyproject.toml |
| Hook | Event | Description |
|---|---|---|
load-constitution.sh | SessionStart | Injects constitution into every session |
notify.sh | Notification | Sends alerts to Telegram, Discord, and/or Slack |
Projects scaffolded by /wf:init follow this layered structure:
src/<package>/
contracts/ # API schemas (OpenAPI 3.1, OpenRPC 1.3, docopt) — single source of truth
core/ # Infrastructure only: logger, config, exceptions
models/ # Shared Pydantic domain models
services/ # Business logic (framework-agnostic)
interfaces/ # Thin wrappers: cli/ (Typer), rest/ (FastAPI), rpc/ (JSON-RPC/WebSocket)
| Aspect | Tool |
|---|---|
| Python version | 3.13+ |
| Package manager | uv |
| Build system | Hatchling + hatch-vcs |
| Linter/Formatter | Ruff |
| Type checker | Pyright (strict) |
| Test framework | pytest |
| Property-based testing | hypothesis |
| Documentation | Material for MkDocs + mkdocstrings |
| CLI framework | Typer |
| REST API | FastAPI + uvicorn |
| JSON-RPC / WebSocket | jsonrpc-websocket, websockets |
| Simple websites | FastAPI + Jinja2 + HTMX |
| Logging | loguru |
macOS (via Homebrew):
brew install node uv
Linux (Debian/Ubuntu):
# Node.js (via NodeSource)
curl -fsSL https://deb.nodesource.com/setup_lts.x | sudo -E bash -
sudo apt-get install -y nodejs
# uv
curl -LsSf https://astral.sh/uv/install.sh | sh
Linux (Fedora/RHEL):
sudo dnf install nodejs
curl -LsSf https://astral.sh/uv/install.sh | sh
Verify installations:
node --version && npx --version && uv --version && uvx --version
Install from the official Anthropic Claude Plugins marketplace (run inside Claude Code):
/plugin install serena@claude-plugins-official
/plugin install context7@claude-plugins-official
/plugin install github@claude-plugins-official
/plugin install playwright@claude-plugins-official
/plugin install claude-md-management@claude-plugins-official
/plugin install ralph-loop@claude-plugins-official
These plugins configure their MCP servers automatically.
The github plugin requires a GITHUB_PERSONAL_ACCESS_TOKEN environment variable:
~/.zshrc or ~/.bashrc):
export GITHUB_PERSONAL_ACCESS_TOKEN="ghp_..."
source ~/.zshrc) before launching Claude Code.The notify.sh hook sends alerts when Claude Code needs attention (permission prompts, idle, etc.). Set any combination of these environment variables in your shell profile (~/.zshrc or ~/.bashrc):
export NOTIFY_TELEGRAM="bot_token|chat_id"
export NOTIFY_DISCORD="https://discord.com/api/webhooks/..."
export NOTIFY_SLACK="https://hooks.slack.com/services/..."
npx claudepluginhub mesca/claude-plugins --plugin wfOpinionated Python 3.11+ engineering system. Establishes strong defaults (SOLID, typing policy, testing standards, code smell detection) and routes to specialist skills for TDD, CLI, web, data/science, and constrained environments.
AI-powered development workflow automation - Phase-based planning, implementation orchestration, preflight code quality checks with security scanning, ship-it workflow, and development principles generator for CLAUDE.md
Python-specific validation, patterns, and expert agents
Universal Claude Code workflow with specialized agents, skills, hooks, and output styles for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
PROJECT.md-first autonomous development with hybrid auto-fix documentation. 8-agent pipeline, auto-orchestration, docs auto-update on commit (true vibe coding). Knowledge base system with 90% faster repeat research. Strict mode enforces SDLC best practices automatically. Works for ANY Python/JavaScript/TypeScript/Go project.
Use Claude Code As Is - native plugin leveraging built-in architecture