By extractumio
Blocks macOS secret exfiltration, prompt injection, persistence, and self-tampering in Claude Code via PreToolUse/PostToolUse hooks that monitor and restrict tool calls.
A curated collection of production-ready skills, agents, and automation tools for Claude Code, created by the Extractum Team.
This repository contains reusable skills and resources that extend Claude Code's capabilities. Skills are structured procedures that Claude can invoke to perform complex, multi-step operations — from DevOps automation and agent scaffolding to domain-specific research and analysis workflows.
The collection is organized into categories (general-purpose, domain-specific, DevOps, computer-use, agents, and more) and is continuously evolving. Browse the directories to discover what's available.
Skills are structured knowledge documents that give Claude step-by-step guidance for performing specific tasks. They can include documentation, reference templates, executable scripts, and hook configurations. Each skill follows a standard format with frontmatter metadata (name, description) and markdown instructions.
Skills may also ship with supporting scripts, command definitions, or configuration files — whatever is needed to get the job done.
Copy any skill into your project's .claude/skills/ directory. Claude Code will automatically detect and use it:
cp -r <skill-directory> /path/to/your/project/.claude/skills/
Clone the repo and browse for skill templates, patterns, and examples to adapt to your own workflows:
git clone https://github.com/extractum-io/claude-skills.git
See CONTRIBUTING.md for guidelines on adding or improving skills.
MIT License — see LICENSE for details.
Maintained by: Extractum
Author: Gregory Zemskov
Contact: [email protected]
Matches all tools
Hooks run on every tool call, not just specific ones
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
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 claimnpx claudepluginhub extractumio/extractum-skills --plugin harden-macos-claudeTeaches design patterns for workflow-based Claude Code skills and provides a review agent for auditing existing skills
Security guardrails - credential protection, destructive command blocking, write scope enforcement, supply chain control, browser restrictions
Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns
Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns
Specialized security review subagent
Custom commands, skills, agents, rules, hooks, and output styles for Claude Code - session continuity and modern CLI tooling for real-world development workflows