Thanks for wanting to contribute. This repo is meant to be a community resource for Claude Code users.
New agents that handle specific tasks well:
- Language-specific reviewers (Python, Go, Rust)
- Framework experts (Django, Rails, Laravel, Spring)
- DevOps specialists (Kubernetes, Terraform, CI/CD)
- Domain experts (ML pipelines, data engineering, mobile)
Workflow definitions and domain knowledge:
- Language best practices
- Framework patterns
- Testing strategies
- Architecture guides
- Domain-specific knowledge
Slash commands that invoke useful workflows:
- Deployment commands
- Testing commands
- Documentation commands
- Code generation commands
Useful automations:
- Linting/formatting hooks
- Security checks
- Validation hooks
- Notification hooks
Always-follow guidelines:
- Security rules
- Code style rules
- Testing requirements
- Naming conventions
New or improved MCP server configs:
- Database integrations
- Cloud provider MCPs
- Monitoring tools
- Communication tools
git clone https://github.com/YOUR_USERNAME/everything-claude-code.git
cd everything-claude-codegit checkout -b add-python-reviewerPlace files in the appropriate directory:
agents/for new agentsskills/for skills (can be single .md or directory)commands/for slash commandsrules/for rule fileshooks/for hook configurationsmcp-configs/for MCP server configs
Agents should have frontmatter:
---
name: agent-name
description: What it does
tools: Read, Grep, Glob, Bash
model: sonnet
---
Instructions here...Skills should be clear and actionable:
# Skill Name
## When to Use
...
## How It Works
...
## Examples
...Commands should explain what they do:
---
description: Brief description of command
---
# Command Name
Detailed instructions...Hooks should include descriptions:
{
"matcher": "...",
"hooks": [...],
"description": "What this hook does"
}Make sure your config works with Claude Code before submitting.
git add .
git commit -m "Add Python code reviewer agent"
git push origin add-python-reviewerThen open a PR with:
- What you added
- Why it's useful
- How you tested it
- Keep configs focused and modular
- Include clear descriptions
- Test before submitting
- Follow existing patterns
- Document any dependencies
- Include sensitive data (API keys, tokens, paths)
- Add overly complex or niche configs
- Submit untested configs
- Create duplicate functionality
- Add configs that require specific paid services without alternatives
- Use lowercase with hyphens:
python-reviewer.md - Be descriptive:
tdd-workflow.mdnotworkflow.md - Match the agent/skill name to the filename
Open an issue or reach out on X: @affaanmustafa
Thanks for contributing. Let's build a great resource together.