Set up Claude Code rules in a project by symlinking from the rbw-claude-code templates. Use this skill when users want to add Python coding standards, anti-slop rules, or other shared rules to their projects.
/plugin marketplace add RBozydar/rbw-claude-code/plugin install core@rbw-claude-codeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
scripts/setup-rules.shThis skill helps you set up Claude Code rules in your project by creating symlinks to shared rule templates. This allows you to maintain consistent coding standards across multiple projects.
Comprehensive Python coding standards extracted from best practices:
| Rule | Description |
|---|---|
asyncio.md | Structured concurrency, TaskGroup, fault isolation |
typing.md | Modern type hints, Protocols, TypeVar |
architecture.md | SOLID principles, dependency injection |
testing.md | TDD, pytest patterns, fixtures |
prohibited.md | Banned practices checklist |
| Rule | Description |
|---|---|
anti-slop.md | Prevent AI-generated code slop |
# Create .claude/rules directory in your project
mkdir -p .claude/rules
# Get the path to rbw-claude-code (adjust as needed)
RBW_CLAUDE_CODE="${HOME}/.claude/plugins/marketplaces/rbw-claude-code"
# Symlink all Python rules
for rule in asyncio typing architecture testing prohibited; do
ln -sf "${RBW_CLAUDE_CODE}/templates/rules/python/${rule}.md" .claude/rules/
done
# Optionally add anti-slop
ln -sf "${RBW_CLAUDE_CODE}/templates/rules/anti-slop.md" .claude/rules/
mkdir -p .claude/rules
RBW_CLAUDE_CODE="${HOME}/.claude/plugins/marketplaces/rbw-claude-code"
# Just asyncio and typing
ln -sf "${RBW_CLAUDE_CODE}/templates/rules/python/asyncio.md" .claude/rules/
ln -sf "${RBW_CLAUDE_CODE}/templates/rules/python/typing.md" .claude/rules/
bash ${CLAUDE_PLUGIN_ROOT}/skills/setup-rules/scripts/setup-rules.sh
The script will interactively guide you through selecting which rules to install.
If you prefer to customize rules per-project:
mkdir -p .claude/rules
RBW_CLAUDE_CODE="${HOME}/.claude/plugins/marketplaces/rbw-claude-code"
# Copy rules (can be modified)
cp "${RBW_CLAUDE_CODE}/templates/rules/python/"*.md .claude/rules/
cp "${RBW_CLAUDE_CODE}/templates/rules/anti-slop.md" .claude/rules/
Check your rules are properly linked:
ls -la .claude/rules/
You should see symlinks pointing to the template files, or copied files if you chose that option.
your-project/
├── .claude/
│ └── rules/
│ ├── asyncio.md -> /path/to/templates/rules/python/asyncio.md
│ ├── typing.md -> /path/to/templates/rules/python/typing.md
│ ├── architecture.md -> ...
│ ├── testing.md -> ...
│ ├── prohibited.md -> ...
│ └── anti-slop.md -> /path/to/templates/rules/anti-slop.md
├── src/
└── ...
When rules are updated in rbw-claude-code:
# Remove specific rule
rm .claude/rules/asyncio.md
# Remove all rules
rm -rf .claude/rules/
The target path may have changed. Re-run the setup:
rm .claude/rules/*.md
# Re-run setup commands
ls .claude/rules/ls -la .claude/rules/file .claude/rules/*Copy just that rule instead of symlinking:
# Remove symlink
rm .claude/rules/asyncio.md
# Copy and customize
cp "${RBW_CLAUDE_CODE}/templates/rules/python/asyncio.md" .claude/rules/
# Edit .claude/rules/asyncio.md as needed
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.