Slash commands, hooks, MCP servers, skills, and plugins — making Claude Code truly yours
Use → to reveal tips • ← to go back • ↓ next slide • ↑ previous slide
Reusable prompt templates that your whole team shares.
.claude/commands/name.md (project-shared) or ~/.claude/commands/name.md (personal). The filename becomes the /name command.
# .claude/commands/review-security.md Perform a security review of the current changes: 1. Check for SQL injection, XSS, CSRF vulnerabilities 2. Verify all user inputs are validated with Zod 3. Ensure no secrets are hardcoded 4. Check auth middleware is applied to protected routes Focus on: $ARGUMENTS
# .claude/commands/new-endpoint.md Create a new API endpoint following our conventions: 1. Add the OpenAPI spec to api/openapi.yaml 2. Generate the route in src/routes/ 3. Create the service in src/services/ 4. Write tests covering 200, 400, 401, 404 Endpoint: $ARGUMENTS
$ARGUMENTS. E.g., /review-security the auth middleware.
--- allowed-tools: Read, Grep, Glob model: opus --- Deep analysis prompt here...
.claude/commands/ to your repo. Everyone gets the same commands. Personal variants go in ~/.claude/commands/.
Unlike CLAUDE.md (advisory), hooks are guaranteed to run. Use them for things that must happen every time.
.claude/settings.json. They run your scripts at specific points.
SessionStart (session begins), PreToolUse (before a tool runs), PostToolUse (after a tool completes), Stop (agent finishes), Notification, PostCompact.
// .claude/settings.json
{ "hooks": { "PostToolUse": [
{ "matcher": "Write|Edit",
"hooks": [{ "type": "command",
"command": "npx eslint --fix $CLAUDE_FILE_PATH",
"timeout": 15 }] }
] } }
// PreToolUse hook: exit code 2 = BLOCK the action
{ "matcher": "Bash",
"hooks": [{ "type": "command",
"command": "echo $CLAUDE_TOOL_INPUT | grep -qE 'rm -rf|drop table' && exit 2 || exit 0" }] }
{ "matcher": "Write|Edit",
"hooks": [{ "type": "command",
"command": "npm test -- --related $CLAUDE_FILE_PATH",
"timeout": 60 }] }
0 = allow, 2 = block the action (Claude gets notified why). Any other code = error.
Model Context Protocol servers give Claude access to external tools and data sources.
.claude/settings.json or ~/.claude/settings.json:
{
"mcpServers": {
"browser": {
"command": "npx",
"args": ["@anthropic-ai/mcp-server-browser"]
},
"postgres": {
"command": "npx",
"args": ["@anthropic-ai/mcp-server-postgres", "postgresql://..."]
}
}
}
"Query the users table for accounts created this week" — Claude calls the database tool directly.
More powerful than slash commands: skills bundle prompts, scripts, and resources together.
SKILL.md, helper scripts, reference files, and configuration. Use skills when the task needs more than a prompt.
.claude/skills/
deploy-checker/
SKILL.md # Main instructions
scripts/
check-deploy.sh # Helper script
reference/
deploy-checklist.md # Reference doc
--- description: "Verify deployment readiness for Lambda services" allowed-tools: Bash, Read, Grep model: sonnet --- # Deploy Checker Before deploying, verify: 1. All tests pass (npm test) 2. No TODO/FIXME in changed files 3. OpenAPI spec is up to date ...
/deploy-checker. They can also be triggered by Claude automatically when their description matches the task.
.claude/skills/ to your repo for team skills. Use ~/.claude/skills/ for personal ones. Skills can also be distributed via plugins.
api-scaffold (new endpoint from OpenAPI), lambda-debug (analyse CloudWatch logs), rn-screen (new React Native screen), vue-component (new Vue component with tests).
Plugins bundle skills, commands, hooks, and MCP configs into a single installable package.
/plugin install anthropic/code-review /plugin install anthropic/memory
code-review — automated PR review with specialised agents. memory — persistent facts across sessions. todo — task tracking.
my-team-plugin/ plugin.json # Plugin manifest commands/ # Slash commands skills/ # Skills with SKILL.md hooks/ # Hook scripts settings.json # MCP servers + permissions
Official docs, free courses, video tutorials, and community guides to deepen your Claude Code skills.
Sub-agents, multi-agent orchestration, the Claude Code SDK, CI/CD automation, and scheduled tasks — building autonomous systems.
Master the tools. Now orchestrate them.