Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
agent-guard
SkillsScan AI agent skills, plugins, MCP servers, and CLI tools (npm/PyPI/Go, cargo, release binaries, curl|bash installers) for malicious code before installation - one scan, every agent (Claude Code, Codex, Gemini, Hermes, OpenClaw). Powered by NVIDIA SkillSpector, Cisco mcp-scanner, Datadog GuardDog, VirusTotal + malcontent.
git clone https://github.com/elliottwaves-20/agent-guard.git -
SkillsGuard
SkillsStatic security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.
git clone https://github.com/Teycir/SkillsGuard.git -
Claude-Red
Skillsclaude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.
git clone https://github.com/SnailSploit/Claude-Red.git -
awesome-claude-video-skills
SkillsOpen-source skills and toolkits that let Claude Code, Codex and other coding agents make video. 180 repos by type, each security-graded. English / 中文.
git clone https://github.com/zhuyansen/awesome-claude-video-skills.git -
magpie
SkillsAgent-assisted maintainership and development framework for Apache projects — Triage, Mentoring, Drafting (agent-authored fixes with human review), and Pairing (developer-side dev-cycle) skills shipping; Agentic Autonomous (auto-merge) on the roadmap.
git clone https://github.com/apache/magpie.git -
awesome-llm-observability
Skills50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.
git clone https://github.com/ContextJet-ai/awesome-llm-observability.git -
agent-skills
SkillsThe definitive collection of cross-platform Agent Skills. Compatible with Claude Code, Codex, Cursor, OpenClaw, Gemini CLI, Copilot, Hermes. Curated weekly. Higher quality than any alternative.
git clone https://github.com/JPeetz/agent-skills.git -
rolecraft
SkillsThe security-first skill manager for AI agents — every install runs a security scan. Manage skills & MCP servers across 90 agents. Zero-dependency CLI.
git clone https://github.com/rolecraft-sh/rolecraft.git -
little-canary
SkillsDetects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
git clone https://github.com/hermes-labs-ai/little-canary.git -
security-best-practices
SkillsPerform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.
$skill-installer <skill-name> -
grcskills
SkillsOpen GRC skills for AI agents. By ISMS Copilot.
git clone https://github.com/better-isms/grcskills.git -
awesome-agent-skills
SkillsSkills for AI coding agents: code review, debugging, security audits, refactoring, cleaning up AI-written code and text, and more.
git clone https://github.com/khasky/awesome-agent-skills.git -
fresh-eyes-review
SkillsMandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests
git clone https://github.com/2389-research/fresh-eyes-review.git -
cyhber-deploy
SkillsSecurity Skill ( Claude , Codex , Gemini )
git clone https://github.com/DevCop95/cyhber-deploy.git -
praetor
SkillsAgentic pentest & red-team harness via Burp Suite MCP toolkit
git clone https://github.com/TyrusRC/praetor.git -
Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP, GDPR, HIPAA, NIST CSF, PCI DSS, EU AI Act, ISO 42001, ISO 27701, DORA, CSRD, India's DPDPA, CMMC 2.0, NIST AI Risk, SWIFT, CCPA/CPRA, and others. Benchmark 92% (with skills) vs 53% (without skills). Updated Monthly.
git clone https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance.git -
launchworthy
SkillsA Claude Code skill that plays bouncer at the door of production: audits AI-built apps (Lovable, Bolt, v0, Cursor) across 5 domains and hands you a scored punch list with copy-paste fixes. MIT.
git clone https://github.com/Wunderlandmedia/launchworthy.git -
js-reverse-ops
SkillsProduction-grade JavaScript reverse-engineering skill: evidence-driven workflows, verbatim sandbox harnesses, 19 battle-tested playbooks, 136 scripts, public benchmarks
git clone https://github.com/DQmyth/js-reverse-ops.git -
alirezarezvani
SkillsAlireza Rezvani CTO and AI enthusiast - Addicted to Claude Code and Openclaw
git clone https://github.com/alirezarezvani/alirezarezvani.git -
maruda
SkillsAI with a harness. Agent skills, rules, CI and security gates for AI-assisted development.
git clone https://github.com/northraystudio/maruda.git -
skillcask
SkillsLockfile-first package manager for AI agent skills (SKILL.md), backed by Composer repositories
git clone https://github.com/GetResponse/skillcask.git -
velric-agent
SkillsAgent 自主渗透测试工具: SPA/MPA 接口枚举、运行时流量捕获、权限树还原、参数矩阵合并。
git clone https://github.com/ikooky/velric-agent.git -
Bug-Bounty-Skills
SkillsEvery great bug bounty skill on GitHub, one repo, refreshed daily — auto-harvested, deduplicated, and credited to every source author
git clone https://github.com/S1N6H/Bug-Bounty-Skills.git -
seo-audit-skill
SkillsA comprehensive SEO audit command-line tool with 332 audit rules across 20 categories. Analyze any website for SEO best practices, Core Web Vitals, security headers, structured data, accessibility, and more.
git clone https://github.com/seo-skills/seo-audit-skill.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.