Agent Skills

Grill (Adversarial Code Challenge)

specialist-agent

Performs adversarial stress-testing of code to find edge cases, race conditions, security holes, and logical flaws before deployment.

Issue Triage & PR Review

gsd-skill-creator

Autonomously triage GitHub issues, submit fixes as PRs, and perform adversarial PR reviews to find security and quality problems.

Medusa v2 Payments

agentic-commerce-skills-plugins

Guides implementation of Medusa v2 payment module and provider integrations (Stripe, PayPal): sessions, authorization/capture/refund lifecycle, webhooks, and be

Code Reviewer

TerminalSkills Skills Library

Perform structured, prioritized code reviews that find correctness, security, performance, reliability, and testing issues and provide concrete fix suggestions.

Threat Hunter — SecOps Hunt

mcp-security

Expert, tool-aware guidance for proactive threat hunting: formulate SIEM/UDM queries, iterate searches, enrich findings, and produce case or report outputs.

OWASP Security Best Practices

claude-skill-registry

Security review and best-practice guidance for web apps and agentic AI systems covering OWASP Top 10:2025, ASVS 5.0, and agent security patterns.

AI Factory (aif)

ai-factory

Set up agent project context: analyze tech stack, install or generate skills, and configure MCP servers with mandatory security scanning for external skills.

ArcKit — French Public Procurement (fr-marche-public)

arc-kit

Generates French public procurement (Dossier de Consultation des Entreprises) drafts aligned with the Code de la Commande Publique, UGAP frameworks, and DINUM d

Rust Development (Modern Practices)

claude-plugins

Provides expert guidance for modern Rust systems programming: cargo workflows, ownership, async/concurrency (Tokio), testing, profiling, and tooling best practi

Security Hygiene

gsd-skill-creator

Security hygiene guidelines for self-modifying agent systems: path sanitization, safe YAML handling, data poisoning checks, and staging/quarantine practices to

Stronghold of Security (SOS)

solana-vibes-kit

Phase-based adversarial security audit pipeline for Solana/Anchor codebases: scan, analyze, strategize, investigate, and report with parallel auditors and a str

Inertia Rails Authentication & Authorization

inertia-rails-skills

Practical guide for adding authentication and authorization to Inertia + Rails apps — covers Devise, has_secure_password, session sharing, permission props, and

Frappe Core Permissions

frappe_claude_skill_package

Guidance and deterministic patterns for implementing Frappe/ERPNext permissions: roles, user permissions, perm levels, hooks, and data masking.

Secure Code Guardian

claude-skills

Provides concrete guidance and code examples to implement authentication, authorization, input validation, and other defenses against OWASP Top 10 vulnerabiliti

radar — Smart Contract AST & Security Analysis

auditware

Multi-framework AST generator and static analysis tool for smart contracts (Rust/Anchor/Stylus and Solidity/Foundry) with a template DSL for writing detection r

File Organizer MCP — Development Guide

file-organizer-mcp

Developer guide and patterns for building and testing the File Organizer MCP server: secure path validation, tools, tests, and safe file operations.

MITRE ATT&CK T1098 — Account Manipulation

mitre-attack-agent-skills

Defensive analysis and guidance for MITRE ATT&CK technique T1098 (Account Manipulation): detection, triage, hunting, and mitigation planning for enterprise envi

OpenClaw Security Monitor

openclaw-security-monitor

Proactive security monitoring, threat scanning and automated remediation for OpenClaw deployments.

Vercel Blob (Object Storage)

droid-tings

Integrate Vercel Blob for secure file uploads, client-side presigned uploads, multipart transfers, and CDN-delivered assets in Next.js projects.

GitHub Actions

claude-skills

Guides creation, configuration, publishing, and security best practices for GitHub Actions (JavaScript, Docker, and composite).

1Password CLI

solana-clawd

Instructions and guardrails for installing and using the 1Password CLI (`op`) safely inside a managed tmux session, with recommended workflows to avoid leaking

Bug Hunter — Adversarial Bug Finding

bug-hunter

Run an adversarial, sequential-first pipeline (Recon → Hunter → Skeptic → Referee) to find, verify, and optionally auto-fix runtime bugs and security issues acr

NPM Package Manager Skill

pi

Manage Node.js packages and common npm workflows: install, run scripts, versioning, publish, and audits with safe dry-run guidance.

Code Security Review

claude-code-security-skills

Three-phase code security audit: broad audit, false-positive filtering, and a concise report with prioritized fixes and confidence-scored findings.

KIT — Known Issue Triager

K.I.T (Known Issue Triager)

Consolidate audit reports into a canonical known-issues.json register, extend existing registers, or check whether a reported issue is already known.

Bagman — Secure Key Management

openclaw-master-skills

Secure key-management patterns and operational guardrails for AI agents that need to handle private keys, session keys, and secrets safely.

Security Threat Model (Repository-grounded)

awesome-omni-skills

Generate an evidence-backed, repository-specific threat model that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and prioritized miti

Anthropic Security Basics

skillshub

Practical security practices for Anthropic Claude integrations: API key management, input validation, prompt-injection defenses, and output scanning.

MCP Sentinel — Security Monitor for Skills & MCP Servers

claude-mcp-sentinel

Security monitoring and runtime protection for Claude Skills and MCP servers: static scans, update-diff analysis, threat intelligence, and an optional PreToolUs

API Integration Patterns

autonomous-dev

Patterns and safe templates for calling external APIs and CLI tools: subprocess safety, retries, auth handling, and rate-limit management.