Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Configure GitLab project security scan profiles with glab. Use when enabling, disabling, or checking GitLab security scan profiles such as SAST, dependency scanning, secret detection, container scanning, or dependency-scanning auto-remediation. Triggers on GitLab security config, security scan profile, enable SAST, dependency scanning, secret detection, glab security.
Chooses and applies the correct Kubernetes Pod Security Standard (Privileged, Baseline, Restricted) for a workload: what each profile forbids, how to map existing workloads to a profile, which securityContext fields must change, and how to plan a PodSecurityPolicy-to-PSS migration without breaking running pods. Use when deciding which pod security profile a namespace or workload should run under, auditing which workloads would fail Restricted, planning a PSP migration, or mapping pod security posture to a compliance control. Keywords: Pod Security Standards, PSS, Privileged, Baseline, Restricted, securityContext, runAsNonRoot, drop ALL capabilities, seccomp RuntimeDefault, PSP migration. Do not use for configuring the admission controller that enforces these profiles - use implementing-pod-security-admission-controller.
Fix JavaScript package security vulnerabilities or upgrade outdated npm/yarn/pnpm/bun dependencies. Use when the user wants to patch CVEs, resolve npm audit findings, bump package versions, modernize node_modules, or update specific packages across a JS project or monorepo. Handles any project with package.json files. Also triggers for "/js-deps" with or without specific package names or glob patterns. Not for non-JS ecosystems, adding brand-new packages, creating package.json from scratch, switching package managers, or debugging runtime errors.
PHP web source code file upload audit tool. Identifies upload entry points and save paths, file name handling and validation logic, detects arbitrary file upload/path traversal/executable upload risks, and outputs exploitability ratings, PoC and remediation advice (omission not allowed).
Guidance for designing baseline Microsoft Purview Data Loss Prevention (DLP) policies across Exchange, SharePoint, OneDrive, Teams, and Endpoint. Covers locations, conditions (SITs/labels/classifiers), severity-tiered actions, simulation mode, exception handling, Endpoint DLP onboarding, and tuning. WHEN: Purview DLP, data loss prevention policy, prevent data exfiltration, Endpoint DLP, DLP rule conditions, DLP simulation mode, block sensitive sharing, policy tips, DLP across Microsoft 365, tune DLP false positives.
DevSecOps, secure software development lifecycle (SSDLC), and application security (AppSec) practices covering secret handling, input validation, dependency hygiene, authentication/authorization, and CI/CD security tooling (SAST, SCA, DAST, secret scanning, IaC scanning). Use when writing code that handles credentials, user input, database queries, or authentication, when setting up a CI/CD pipeline, or when reviewing code or infrastructure for security issues.
Introduce TDIR, route requests by domain, and define shared contracts for authentication, output, exit codes, write-operation confirmation, safety, and statistical conventions. Use when the user asks how to get started or choose capabilities across domains. Does not handle specific business data queries or write-backs.
Guidance for the Microsoft unified security operations platform that brings Microsoft Sentinel, Microsoft Defender XDR, Security Copilot, Threat Intelligence, and Microsoft Security Exposure Management together in the Microsoft Defender portal. Covers prerequisites, onboarding Sentinel, unified incident queue, advanced hunting across SIEM+XDR, and RBAC. WHEN: unified SecOps, onboard Sentinel to Defender portal, single SOC pane of glass, unified incident queue, connect Sentinel workspace to Defender XDR, exposure management, unified portal, merge Sentinel and Defender XDR, reduce context-switching for analysts, single pane of glass, move off the Azure Sentinel portal. DO NOT USE for Sentinel-only workspace design (use sentinel) or Defender XDR-only incident investigation (use defender-xdr).
Writing optimized, secure, multi-stage Dockerfiles with language-specific patterns (Python, Node.js, Go, Rust), BuildKit features, and distroless images. Use when containerizing applications, optimizing existing Dockerfiles, or reducing image sizes.
Must be used when the user requests AI/Agent security assessment, blue-team exercises, AI security review, prompt injection testing, MCP/Skill/plugin/code package audits, Agent toolchain abuse testing, or needs to generate Markdown/HTML resembling a penetration test report. This skill turns the Agent into an AI security expert from an authorized blue-team perspective, conducting security exercises against AI products, Agents, MCP Servers, Skills, code repositories, and AI infrastructure. Prefer first-principles reasoning and real evidence over mechanically running a payload library; scripts are used only for deterministic auxiliary tasks such as HTTP fingerprinting, evidence aggregation, and report rendering.
Guidance for designing BitLocker drive encryption for Windows endpoints managed via Microsoft Intune — encryption policy, silent enablement, recovery key escrow to Entra ID, TPM, pre-boot authentication trade-offs, and BitLocker To Go for removable media. Covers compliance integration with Conditional Access and recovery workflows. WHEN: BitLocker, disk encryption, Windows encryption policy, BitLocker recovery key, silent BitLocker enablement, Intune disk encryption, TPM 2.0, escrow recovery key, encrypt endpoints, XTS-AES, BitLocker To Go, pre-boot authentication, removable drive encryption. DO NOT USE for general Intune device management (use intune-device-mgmt), Linux/macOS encryption (use intune-device-mgmt FileVault), or Azure disk encryption (use azure-key-vault).
Integrate Arcjet Guard into Microsoft Agent Framework for Go (github.com/microsoft/agent-framework-go). Wrap a functool or MCP tool with GuardTool, guard every tool an agent can see and screen inbound text with GuardMiddleware, or guard any Go function with arcjet.GuardAction. Use when asked to add Arcjet to a Go agent built on Microsoft Agent Framework, rate limit its tools, block prompt injection, or fail closed on tool calls. This is the Go framework, not the .NET or Python Microsoft Agent Framework.
Generate penetration test reports in a standard format, including a project information table, a vulnerability findings list, vulnerability details (with an attribute table, description, reproduction steps, evidence screenshots, and remediation recommendations), and appendices (risk level definitions, CVSS explanations, and a glossary). Use this skill when the user asks to generate a penetration test report, security test report, or vulnerability report. Strictly follow the standard format in the project template directory.
Security audit tool for Laravel framework-specific behavior. Performs white-box static auditing of common Laravel framework features such as authentication, CSRF, Session, model filling, and Blade rendering, and maps the risks to your existing general vulnerability taxonomy (AUTH/CSRF/LOGIC/XSS/CFG, etc.).
Symfony framework feature security audit tool. Performs white-box static auditing of common Symfony framework mechanisms such as security.yaml, CSRF, Twig/Twig raw, expressions and access control, and maps risks to a general vulnerability taxonomy (AUTH/CSRF/CFG/XSS/TPL/LOGIC, etc.).
Guidance for designing public key infrastructure (PKI) and certificate management on Azure and hybrid environments. Covers CA strategy (offline root + issuing CAs, AD CS vs managed/third-party vs public CA), Azure Key Vault certificates, HSM key protection, Entra certificate-based authentication (CBA), certificate lifecycle (issuance, renewal, rotation, revocation), and Intune SCEP/PKCS distribution. WHEN: PKI design, certificate authority, root CA offline, issuing CA, certificate management, Key Vault certificates, certificate-based authentication, CBA, certificate lifecycle, issue and rotate certificates, mTLS certificates, code signing, CRL OCSP, certificate expiry, certificate rotation, AD CS, HSM, Managed HSM. DO NOT USE for Entra ID identity model (use entra-id) or Key Vault secrets/keys only (use azure-key-vault).
Guidance for applying Microsoft Purview data security and compliance across Microsoft 365 workloads (Exchange, SharePoint, OneDrive, Teams) - coordinating labels, DLP, retention, and Copilot data protection per workload with each workload's distinct behaviour. WHEN: Purview for Microsoft 365, protect SharePoint and Teams data, M365 compliance, labels and DLP across Office, retention for Exchange, Teams data security, OneDrive governance, Microsoft 365 data protection, per-workload Purview.
Security-first visual testing combining URL validation, PII detection, and visual regression with parallel viewport support. Use when testing web applications that handle sensitive data, need visual regression coverage, or require WCAG accessibility compliance.
Review Sui Move code that integrates OpenZeppelin Contracts for Sui against the library's own patterns and conventions. Use this when a developer wants their integration checked before shipping. Triggers: \"review my Sui Move code\", \"am I using OpenZeppelin correctly\", \"check this integration\", \"is this idiomatic\", \"review before audit\". Checks correct use of OZ primitives, deviations from examples/doc-comments, upheld invariants, test coverage, and code-quality/style. This is an AI code review, not a formal security audit.
Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or automating code vulnerability detection.
Perform language- and framework-specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best-practice 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.
Guidance for designing and operating Microsoft Sentinel, the cloud-native SIEM and SOAR delivered through the Defender portal. Covers workspace design, data connectors, ingestion tiers (Analytics/Basic/Auxiliary/ADX), analytics rules, hunting, watchlists, automation playbooks, and cost/commitment-tier optimisation. WHEN: deploy Microsoft Sentinel, design SIEM, onboard data connectors, write analytics rule, KQL detection, Sentinel playbook, SOAR automation, Sentinel cost optimization, log ingestion tiers, commitment tier, Sentinel workspace design, how do I set up a SIEM, collect logs from third-party tools, ingest firewall or Linux syslog into Azure, write a detection rule, automate incident response, how much does Sentinel cost, Auxiliary logs, Basic logs, ADX archive, codeless connector. DO NOT USE when the goal is correlating Microsoft 365 XDR alerts into incidents (use defender-xdr) or onboarding Sentinel into the unified Defender portal (use unified-secops-platform).
Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.
Query endpoint details, historical insights and assessment conclusions, compromised endpoints, behavior profiles, and process trees, and link machine_id to alerts, insights, and hunts. Use when the user asks about a single endpoint or compromised endpoints. Do not treat the compromised field in an insight as an endpoint conclusion.
Query stored TDIR entity profiles for IPs, domains, URLs, hashes, and other entities; entity ↔ insight ↔ endpoint associations within the platform; and threat intelligence operations summaries (entities summary). Write back human analyst verdicts for entities (entities verdict update) only after explicit user confirmation. Use tdir-investigation-enrichment for standalone real-time BTI intelligence requests. Does not handle threat detection, causal proof, or endpoint compromise determination.
ABP Framework cross-cutting patterns including authorization, background jobs, distributed events, multi-tenancy, and module configuration. Use when: (1) defining permissions, (2) creating background jobs, (3) publishing/handling distributed events, (4) configuring modules.
Decompile Android APK, XAPK, JAR, and AAR files using jadx or Fernflower/Vineflower. Reverse engineer Android apps, extract HTTP API endpoints, trace call flows from UI to network layer, and analyze runtime behavior with Frida, network capture, JNI/SO inspection, and signature generation. Use when the user wants to decompile, analyze, hook, inspect network traffic, bypass SSL pinning for analysis, locate crypto or signing logic, or follow call flows in Android packages.
Audits a self-hosted CockroachDB cluster against the CIS CockroachDB Benchmark v1.0.0 Level 1 controls. Supports two audit depths — quick automated scans and full CIS audit procedures. Produces a structured PASS/FAIL/MANUAL report covering installation, system hardening, logging, user access, data protection, and CockroachDB settings. Use when preparing for CIS compliance assessments, hardening self-hosted deployments, or validating security posture against industry benchmarks.
Reasoning skill for designing AWS GenAI and ML architectures for healthcare and life sciences workloads. Use when the user asks to choose between SageMaker and Bedrock, design a RAG system over medical literature, architect clinical NLP or medical imaging inference, plan genomics or drug discovery pipelines on AWS, address HIPAA/PHI compliance in ML systems, design MLOps for regulated clinical models, or optimize cost for HCLS ML workloads. Triggers include "AWS architecture", "SageMaker vs Bedrock", "HIPAA ML", "clinical RAG", "medical imaging inference", "genomics on AWS", "PHI training", "MLOps healthcare", "Bedrock guardrails", "HealthLake", "HCLS cloud architecture", "BAA compliance", "SageMaker endpoint", "Bedrock knowledge base", "clinical NLP on AWS", "FDA SaMD on AWS".
Use when a Power Apps mobile project needs dependency updates or an npm audit review. Checks the mobile-app plugin first, then updates the native host, other Microsoft packages, and all remaining direct npm packages in order with validation and rollback.
Scans a repo's GitHub Actions workflows for the ten critical CI/CD attack vectors — template injection, fork code executed with privileges (pwn requests), cache poisoning, impostor action SHAs, secrets dumps, GITHUB_ENV hijack, write-token untrusted triggers, credentials in caches/artifacts, unverified remote code execution (curl|bash and mutable fetch-and-run), and dependency install scripts running in a job that holds secrets — reports every finding with a plain-English attacker scenario, plus pass/fail config hygiene checks, and fixes selected findings via per-finding subagents. Deliberately NOT comprehensive — critical exploit-chain checks only (references/why-these-ten.md). Use when: the user asks to audit or review CI/CD or GitHub Actions security posture, "is my CI secure", "audit my CI security", or names ci-secure / /ci-secure. Do NOT trigger for: CI speed, cost, or wall-clock audits ("why is CI slow") — use ci-speedup; CI config best-practices grading ("grade my CI", "CI score") — use ci-score.
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.