creating-claude-rules

$npx mdskill add AgentWorkforce/relay/creating-claude-rules

Generate correct Claude rules with proper paths and no Cursor fields.

  • Creates .claude/rules/ files using paths instead of globs.
  • Excludes Cursor-specific fields like alwaysApply from output.
  • Applies correct frontmatter syntax for path-scoped rules.
  • Supports both single and multi-pattern path configurations.

SKILL.md

.github/skills/creating-claude-rulesView on GitHub ↗
---
name: creating-claude-rules
description: Use when creating or fixing .claude/rules/ files - provides correct paths frontmatter (not globs), glob patterns, and avoids Cursor-specific fields like alwaysApply
---

# Creating Claude Rules

## Overview

Rules in `.claude/rules/` are modular instructions scoped to specific files via glob patterns. They load automatically with same priority as `CLAUDE.md`.

## When to Use

- Creating new rules in `.claude/rules/`
- Fixing rules that use wrong frontmatter (`globs` instead of `paths`)
- Migrating Cursor rules to Claude format
- Organizing project-specific conventions

## Quick Reference

| Field | Claude | Cursor |
|-------|--------|--------|
| Path patterns | `paths` | `globs` |
| Always apply | Omit `paths` | `alwaysApply: true` |
| Description | Not documented | `description` |

## Frontmatter

### Path-Scoped Rules

```yaml
---
paths:
  - "src/api/**/*.ts"
  - "tests/**/*.test.ts"
---
```

Or single pattern:

```yaml
---
paths: src/**/*.{ts,tsx}
---
```

### Global Rules

Omit frontmatter entirely - applies to all files:

```markdown
# TypeScript Conventions

Use .js extensions in imports.
```

## Common Mistakes

```yaml
# ❌ WRONG - globs is Cursor format
---
globs:
  - "**/*.ts"
---

# ✅ CORRECT - Claude uses paths
---
paths:
  - "**/*.ts"
---
```

```yaml
# ❌ WRONG - alwaysApply is Cursor-only
---
alwaysApply: true
---

# ✅ CORRECT - just omit paths for global rules
# (no frontmatter needed)
```

```yaml
# ❌ WRONG - unquoted patterns
---
paths:
  - **/*.ts
---

# ✅ CORRECT - quote glob patterns
---
paths:
  - "**/*.ts"
---
```

## Directory Structure

```
.claude/rules/
├── testing.md          # Path-scoped or global
├── typescript.md
└── frontend/           # Subdirectories supported
    └── react.md
```

Files discovered recursively. Use subdirectories to organize.

## Glob Patterns

| Pattern | Matches |
|---------|---------|
| `**/*.ts` | All .ts files anywhere |
| `src/**/*` | Everything under src/ |
| `*.md` | Markdown in root only |
| `**/*.{ts,tsx}` | .ts and .tsx files |
| `{src,lib}/**/*.ts` | .ts in src/ or lib/ |

## Reference

https://code.claude.com/docs/en/memory#modular-rules-with-claude/rules/

More from AgentWorkforce/relay

SkillDescription
adding-swarm-patternsUse when adding new multi-agent coordination patterns to agent-relay - provides checklist for types, schema, templates, and docs updates
agent-relayUse when you need Codex to coordinate multiple agents through Relaycast for peer-to-peer messaging, lead/worker handoffs, or shared status tracking across sub-agents and terminals.
agent-relay-orchestratorRun headless multi-agent orchestration sessions via Agent Relay. Use when spawning teams of agents, creating channels for coordination, managing agent lifecycle, and running parallel workloads across Claude/Codex/Gemini/Pi/Droid agents.
browser-testing-with-screenshotsUse when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality
choosing-swarm-patternsUse when coordinating multiple AI agents and need to pick the right orchestration pattern - covers 10 patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) with decision framework and reflection protocol
creating-agent-skills-skillUse when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io specification with frontmatter constraints, directory structure, and validation rules
creating-claude-agentsUse when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and validation against schema.
creating-claude-hooksUse when creating or publishing Claude Code hooks - covers executable format, event types, JSON I/O, exit codes, security requirements, and PRPM package structure
creating-skillsUse when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimization, and real examples
debugging-websocket-issuesUse when seeing WebSocket errors like "Invalid frame header", "RSV1 must be clear", or "WS_ERR_UNEXPECTED_RSV_1" - covers multiple WebSocketServer conflicts, compression issues, and raw frame debugging techniques