No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by OneWave-AI · Claude Skill · ★ 302
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claude-skills safe to install? View the security audit →
Claude Skills Library Production-ready skills for Claude Code. Built and maintained by OneWave AI -- AI consulting for small and mid-size businesses. 172 skills across three pillars: business (sales, marketing, consulting, ops), everyday life (personal finance, travel, fitness, job hunting), and coding (engineering, design, AI agent architecture). Featured: /agent-army Deploy 3 to 50+ independent Claude agents in parallel, each with its own 1M token context window. Each agent spawns sub-agents underneath. The system runs in waves -- execute, audit, propagate -- and checks its own work between each. Built for tasks where one agent isn't enough: large refactors, full-site audits, bulk content generation, codebase migrations. Battle-tested on 60+ concurrent agents in a single session. View agent-army Getting Started Each skill is a self-contained file that Claude Code loads as a system prompt. No dependencies, no build step. Categories AI Agent Architecture Skills for building, orchestrating, and managing autonomous AI agents. 2-layer parallel agent h
| Stars | 302 |
| Forks | 52 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 67.119610209852/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-23 |
| Created | 2025-10-22 |
| Platforms | claude-code, python |
| Est. Tokens | ~16k |
Looking for a claude-skills alternative? If you're comparing claude-skills with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
Claude Code Skills Marketplace: plugins, skills for ADR-driven development, DevOps automation, ClickHouse mana
Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p
The complete guide to Claude Code: CLAUDE.md, hooks, skills, MCP servers, and commands
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca
Explore other popular claude skill tools:
claude-skills is 200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture. Built and maintained by OneWave AI.. It is categorized as a Claude Skill with 302 GitHub stars.
claude-skills is primarily written in Python. It covers topics such as agent-skills, ai-agents, anthropic.
You can find installation instructions and usage details in the claude-skills GitHub repository at github.com/OneWave-AI/claude-skills. The project has 302 stars and 52 forks, indicating an active community.
claude-skills is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to claude-skills on Agent Skills Hub include claudepro-directory, claude-emporium, cc-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: