Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Integrate Arcjet Guard into Python Claude Managed Agents — screen user.message with guard_events before sessions.events.send, and gate custom tools on agent.custom_tool_use with guard_custom_tool. Use when asked to add Arcjet to hosted Claude Managed Agents, anthropic beta sessions, rate limit custom tools, or block prompt injection on hosted sessions. Not Claude Agent SDK local query() / PreToolUse.
Integrate Arcjet Guard into Python Strands Agents — wrap authored @tool with guard_tool, and put guard_hooks on Agent(hooks=) for unwrapped / MCP tools via BeforeToolCallEvent.cancel_tool. Use when asked to add Arcjet to strands / strands-agents, rate limit those tools, screen inbound messages, or block prompt injection / PII. This is Python strands, not JS @strands-agents/sdk.
Guidance for Microsoft Intune device management — enrollment, configuration, compliance, and security baselines across Windows, macOS, iOS/iPadOS, and Android. Covers Autopilot vs corporate-vs-BYOD enrollment, compliance policies that feed Conditional Access, Intune security baselines, update rings / Autopatch, and using filters and ring-based rollouts to avoid lockouts. WHEN: Microsoft Intune, MDM, device enrollment, Autopilot, Apple ABM, Android Enterprise, compliance policy, security baseline, configuration profile, settings catalog, manage devices, device compliance for Conditional Access, endpoint management, Windows Autopatch, update rings. DO NOT USE for app-only protection on BYOD (use intune-app-protection), endpoint detection / EDR (use defender-for-endpoint), or disk encryption only (use bitlocker-design).
Guides the design and assessment of RBAC and ABAC authorization models against the NIST RBAC model (Sandhu et al.) and NIST SP 800-162 (ABAC guide). Auto-invoked when designing role hierarchies, evaluating permission boundaries, implementing ABAC policy patterns, performing role mining, or preventing role explosion. Produces architecture recommendations with framework-grounded rationale.
Review Bun runtime security audit patterns. Use for auditing Bun-specific vulnerabilities including shell injection, SQL injection, server security, and process spawning. Use proactively when reviewing Bun apps (bun.lockb, bunfig.toml, or bun:* imports present). Examples: - user: "Review this Bun shell script" → audit `$` usage and argument injection - user: "Check my bun:sqlite queries" → verify `sql` tagged template usage - user: "Audit my Bun.serve() setup" → check path traversal and request limits - user: "Is my Bun.spawn() usage safe?" → audit command injection and input validation - user: "Review WebSocket security in Bun" → check authentication before upgrade
Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems. Use when implementing auth systems, securing APIs, or debugging security issues.
Guide for implementing DefectDojo - an open-source DevSecOps, ASPM, and vulnerability management platform. Use when querying vulnerabilities, managing findings, configuring CI/CD pipeline imports, or working with security scan data. Includes MCP tools for direct API interaction.
Deploys Cloudflare Access with Cloudflare Tunnel for zero trust access to self-hosted apps, configuring identity-aware policies, device posture checks, and WARP client enrollment as a VPN replacement. Use when replacing VPN with Cloudflare One, exposing internal apps without open inbound ports, or securing contractor/third-party access to specific applications.
Guidance for Docker Scout — image vulnerability scanning, SBOM generation, and policy evaluation. Covers scout quickview for CVEs, scout cves for detailed vulnerability analysis, scout sbom for software bill of materials, policy evaluation with custom rules, CI/CD integration (GitHub Actions/Jenkins), and remediation guidance. Use when the user asks about docker scout, vulnerability scanning, CVE, SBOM, image analysis, security vulnerabilities, or needs to scan Docker images for security issues. 使用场景：docker scout、漏洞扫描、CVE、SBOM、镜像安全分析、安全漏洞、软件物料清单.
Continuous integration for Go projects: GitHub Actions pipelines, caching, golangci-lint setup, test/coverage gates, vulnerability scanning, SAST (CodeQL, gosec), Dependabot, action pinning, build matrices, Makefile targets. Use when: "set up CI", "GitHub Actions for Go", "add lint to the pipeline", "CI is slow", "coverage gate", "build matrix", "write a Makefile", "run govulncheck in CI". Not for: commit conventions (git-commit), choosing or auditing dependencies (go-dependency-audit), writing the tests themselves (go-test-quality), releases and signing (go-build-release).
Integrate Arcjet Guard into Python LangChain — wrap a BaseTool you call with guard_tool, put ArcjetMiddleware + ToolPolicy on create_agent, or observe a chain with ArcjetCaptureHandler. Use when asked to add Arcjet to LangChain, create_agent, langchain-core tools, rate limit those tools, screen inbound messages, or block prompt injection / PII. This is Python LangChain, not LangChain JS createAgent and not LangGraph JS.
Use this skill whenever the user asks about NetExec (nxc) — a network exploitation and post-exploitation tool for Active Directory environments. Triggers include: any mention of 'nxc', 'netexec', 'crackmapexec' successor questions, AD enumeration, SMB/LDAP/WinRM/MSSQL/SSH/RDP/VNC/WMI/FTP/NFS protocol attacks, password spraying, credential dumping (SAM, NTDS, LSASS, DPAPI), Kerberoasting, ASREPRoasting, lateral movement, BloodHound collection, module usage, or any pentest workflow involving Windows domain environments. This skill covers ALL protocols, ALL modules, and ALL core features of NetExec. Always provide full command examples with correct flags and options.
Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.
Run a comprehensive multi-perspective code review on current changes. Activates the Review Council (security, quality, documentation, domain review) and runs automated security scanning. Use before creating a pull request or when you want a thorough review of your work.
Design Roblox admin tools and observability systems. Use for safe grant/revoke tools, moderation commands, audit logs, live diagnostics, economy inspection, player support, operational dashboards, and abuse-resistant admin workflows.
With the explicit OK of whoever is using the computer, installs a commit alarm (git pre-commit hook) that refuses the commit when it finds a CPF or CNPJ with a valid check digit, a passwords file (.env), a certificate with a private key (.pfx, .p12, .pem), or a new spreadsheet, explains why and how to fix it, cites git commit --no-verify, and says how to uninstall. Use when the user wants to protect the repository against customer data or an A1 certificate going into git, when preparing the office machine to work with SDD, or when a commit is refused by this alarm. Does not apply to deadlines (it neither consults the norm nor calculates). It does not fix git history, does not revoke a certificate, does not read a .xlsx spreadsheet internally, and does not give an opinion on LGPD or professional secrecy; to diagnose the environment without installing anything, use sdd-checar-ambiente.
Apply secure coding practices when writing, reviewing, or refactoring code in Java Spring/Spring Boot, Django, Flask, FastAPI, Ruby on Rails, React, Vue, Angular, Go, ASP.NET, C, C++, TypeScript, C#, or Terraform. Use this skill whenever the user adds a new endpoint, handles user input, writes a query, sets up authentication/authorization, configures CORS or session cookies, processes file uploads, calls an external URL, renders user-controlled HTML, deserializes data, builds login flows, writes systems/memory-managed code (C/C++), defines infrastructure (Terraform), or asks for a security review of code in any of these languages or frameworks — even when they don't explicitly say "secure" or "security". Also use when reviewing PRs, modifying middleware/filters/interceptors, configuring framework security settings (Spring Security, Django settings, Rails initializers, ASP.NET Identity), tightening tsconfig/compiler flags, writing code that touches secrets, crypto, subprocess execution, raw pointers, or HTTP headers, or defining cloud resources, IAM policies, or security groups in HCL.
Authentication, authorization, and API security implementation. Use when building user systems, protecting APIs, or implementing access control. Covers OAuth 2.1/OIDC, JWT patterns, sessions, Passkeys/WebAuthn, RBAC/ABAC/ReBAC, policy engines (OPA, Casbin, SpiceDB), managed auth (Clerk, Auth0), self-hosted (Keycloak, Ory), and API security best practices.
Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk. Use when evaluating a third-party skill before installing, enabling, updating, publishing, or distributing it; reviewing an untrusted SKILL.md, agent configuration, MCP integration, archive, or repository; comparing a package with a known-good version; or investigating unexpected tool, network, credential, or filesystem behavior.
Per-project key provisioning for git signing and authentication. Invoke to configure git signing, set up keys for this project, bypass 1Password for git operations, add a key to GitHub or Forgejo, troubleshoot signing prompts, or check key status. Generates ed25519 SSH keys (GitHub) or GPG keys (Forgejo), configures git signing, registers keys on the forge, and sets up SSH host aliases to bypass global agents.
Use when reviewing or scoring AI-generated business/application code quality in any language, especially when a numeric score, risk level, or must-fix checklist is requested, or when C++ code must comply with OpenHarmony C++ and security standards
Perform code review on staged changes or a pull request. Checks for bugs, security issues, performance problems, and best practices. Use when user says "review code", "check my code", "review PR", or "is this code okay". The +check flag validates findings via a fresh-context subagent; validation also runs automatically when the review produced confidence markers.
This skill should be used when the user asks to "analyze code for security issues", "check for OWASP vulnerabilities", "review code against CWE Top 25", "find injection vulnerabilities", "do a security code review", or needs manual security analysis against OWASP Top 10, API Top 10, Mobile Top 10, or CWE/SANS frameworks.
Enforces database integrity for PostgreSQL and Prisma systems. Use when designing schemas, writing migrations, or configuring Row-Level Security. Use for type-safe SQL, naming alignment, constraint validation, zero-trust RLS policies, UUIDv7 primary keys, and zero-downtime deployments.
This skill should be used when the user asks to "find hardcoded secrets", "audit for credential leaks", "check for API keys in code", "review secret scanning alerts", "rotate a leaked secret", or needs to detect hardcoded credentials, review secret handling patterns, or remediate exposed secrets.
Use this skill whenever the user needs a risk- or safety-first check for a token, address, or project. Covers contract risk, address compliance labels, and project incidents via gate-cli. Triggers: is this coin safe, honeypot, sanctioned, compliance. Info primary; news auxiliary. Delegate: gate-info-research, gate-info-web3 (on-chain), gate-news-intel (events). v0.7.6+ uses info +token-risk shortcut for token_risk; legacy fallback below 0.7.6. check-address-risk not shipped—use get-address-info for address_risk.
Reverse engineer compiled software and app internals for authorized security research, CTFs, malware analysis, interoperability and debugging. Use whenever the user wants to understand, decompile, disassemble, unpack or trace an artifact they own or may study: native binaries (ELF/PE/Mach-O, .so/.dll/.dylib), Android APK/AAB/DEX, iOS/macOS apps, .NET or Java bytecode, JavaScript/Electron/WASM bundles, Python/Go/Rust/Flutter/React Native/Unity builds, installers, firmware images, or an app's network API or file format. Trigger on phrases like "what does this binary do", "decompile this APK", "crackme", "CTF reversing", "analyze this sample", "extract this firmware", "recover the file format", "what API does this app call", or "how does this app work", even when reverse engineering is not named. Includes triage, tool-detection, headless decompiler export and endpoint-extraction scripts, plus per-platform playbooks.
Expert Kubernetes specialist mastering container orchestration, cluster management, and cloud-native architectures. Specializes in production-grade deployments, security hardening, and performance optimization with focus on scalability and reliability.
Reviews agentic AI systems against the OWASP Top 10 security risks for autonomous AI agents. Auto-invoked when reviewing multi-agent architectures, AI agent deployments, or systems where LLMs have tool access and act autonomously. Covers permission models, tool security, memory integrity, trust boundaries, and human oversight. Produces a structured assessment with risk ratings and architectural recommendations.
Give cited, advisory-only Splunk alert, scheduled-report action, Enterprise Security finding/notable, and risk-workflow readiness guidance from supplied evidence. Use for schedule, trigger, suppression, action, recipient, downstream, ownership, escalation, entitlement, and post-change validation decisions. Route SPL authoring and execution to Splunk Search, broad permissions and object lifecycle to Knowledge Object Governance, and active service incidents to platform operations.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.