Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers on incident response, production incident, outage, service down, site down, P0, P1, severity, downtime, on-call, incident commander, status page, postmortem prep. Also triggers when something is actively broken in production and the user is figuring out what to do.
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Use when the user asks to threat model a codebase or path, enumerate threats or abuse paths, or perform AppSec threat modeling. Do NOT use for general architecture summaries, code review, security best practices (use security-best-practices), or non-security design work.
Use this skill when the user asks to "automate SQL injection testing," "enumerate database structure," "extract database credentials using sqlmap," "dump tables and columns from a vulnerable database," or "perform automated database penetration testing." It provides comprehensive guidance for using SQLMap to detect and exploit SQL injection vulnerabilities.
Expert AWS Cloud Advisor for architecture design, security review, and implementation guidance. Leverages AWS MCP tools for accurate, documentation-backed answers. Use when user asks about AWS architecture, security, service selection, migrations, troubleshooting, or learning AWS. Triggers on AWS, Lambda, S3, EC2, ECS, EKS, DynamoDB, RDS, CloudFormation, CDK, Terraform, Serverless, SAM, IAM, VPC, API Gateway, or any AWS service. Do NOT use for non-AWS cloud providers or general infrastructure without AWS context.
Integrates react-native-nitro-google-signin (Nitro Universal Google Sign-In) in React Native and Expo apps. Use when adding Google Sign-In, One Tap sign-in, GoogleOneTapSignIn, Credential Manager, SHA-1 OAuth setup, google-services.json, GoogleService-Info.plist, Expo config plugin, DEVELOPER_ERROR, or webClientId autoDetect.
Use when the user is hardening a Spree 6 app, reviewing a PR or finding for security issues, managing secrets and API keys, configuring CORS/CSP, securing the dashboard or /jobs, handling GDPR data requests, or asking about Spree-specific risks (publishable vs secret keys, scope minimization, IDOR on carts/orders, rich-text XSS, webhook HMAC and SSRF, encrypted columns, PCI scope). Common phrasings include "Spree security", "leaked secret key", "rotate API key", "CORS", "Allowed Origins", "CSP", "XSS in product description", "IDOR", "cross-store data leak", "mass assignment", "permitted attributes", "webhook signature", "SSRF", "Active Record encryption", "GDPR", "anonymize customer", "PCI", "Mission Control password". For roles, permission keys and login strategies use spree-auth-permissions.
Expert advisor on Vietnam Personal Data Protection Law (PDPL) compliance for Law No. 91/2025/QH15 and implementing Decree 356/2025/ND-CP (effective January 1, 2026). Use this skill for gap analysis against the Vietnam PDPL, data subject rights fulfilment workflows, cross-border data transfer impact assessments, privacy notices and internal policies, breach notification procedures, sector-specific obligations (finance, AI, cloud, blockchain), and DPO qualification reviews. Trigger whenever a user mentions Vietnam data privacy, VN-PDPL, Nghị định 356, Vietnamese personal data, or cross-border transfers involving Vietnamese citizens' data.
This skill should be used when the user asks to “test for XSS vulnerabilities”, “perform cross-site scripting attacks”, “identify HTML injection flaws”, “exploit client-side injection vulnerabilities”, “steal cookies via XSS”, or “bypass content security policies”. It provides comprehensive techniques for detecting, exploiting, and understanding XSS and HTML injection attack vectors in web applications
Security threat modeling, attack surface mapping, and trust boundary analysis on a codebase. Triggers on 'threat model', 'security review', 'attack surface', 'trust boundaries', or when assessing a project's security posture. Also trigger when the user is about to build security-sensitive features (auth, crypto, file I/O, network services, native bridges) and needs to understand the threat landscape first — even if they don't explicitly say "threat model." Also triggers on 'what changed' or 'diff analysis' for incremental security review of recent commits.
Examine NTFS slack space, MFT entries, the USN Change Journal, and Alternate Data Streams (ADS) to recover hidden or residual data, reconstruct deleted-file metadata, and reconstruct available file-system change activity from USN records. Use during deep forensic analysis of an NTFS image when standard file recovery is insufficient, such as hunting for data hidden in ADS.
Configure a GitLab CI/CD pipeline that embeds SAST (Semgrep, SpotBugs, Gosec, Bandit, NodeJsScan), DAST, container scanning, dependency scanning, and secret detection via GitLab's managed security templates. Use when building a shift-left DevSecOps pipeline in GitLab, adding automated vulnerability scanning stages to .gitlab-ci.yml, or triaging scanner findings with GitLab Duo AI before deployment.
Plan and execute a comprehensive, MITRE ATT&CK-aligned red team engagement spanning threat modeling, reconnaissance, initial access, and post-exploitation to evaluate an organization's detection, prevention, and response against APT-style behavior. Use when scoping or running a full-scope, objective-based engagement, or purple-teaming against a specific threat actor's TTPs.
Performs initial binary triage by surveying memory layout, strings, imports/exports, and functions to quickly understand what a binary does and identify suspicious behavior. Use when first examining a binary, when the user asks to triage, survey, or analyze a program, or wants an overview before deeper reverse engineering.
Runs Didit's standalone passive liveness check on a single selfie image (POST /v3/passive-liveness/). Use when checking that a person is physically present, detecting spoofing or presentation attacks (printed photos, screen replays, masks, deepfakes), adding anti-spoofing to a selfie step, or screening a selfie against the face blocklist and earlier approved faces. Returns a 0-100 liveness score, an Approved/Declined status against a configurable decline threshold, face quality and luminance, and blocklist and duplicate-face warnings.
Expert New Zealand Information Security Manual (NZISM) advisor for NZ government agencies and their supply chains. Use for NZISM control guidance, gap analysis, agency security obligations, classification framework (Unclassified through Top Secret), security risk management, system certification, and GCSB/NCSC NZ compliance. Triggers on: NZISM controls, NZ government security, GCSB compliance, agency cybersecurity obligations, NZ classification markings, Restricted/Confidential/Secret system scoping, agency security policies, third-party supplier security, Certification and Accreditation (C&A), and any question about NZ government information security requirements or the NZISM framework
Expert-level application security, OWASP Top 10, penetration testing, and security best practices. Use when the user mentions OWASP, pentesting, appsec, vulnerability, encryption, or authentication, or when the task involves Security Principles, OWASP Top 10, Security Domains, or Broken Access Control.
Guidance for threat modelling using STRIDE and the Microsoft Security Development Lifecycle (SDL). Covers data-flow diagrams, trust boundaries, the STRIDE categories, mitigation mapping, and tooling (Microsoft Threat Modeling Tool). WHEN: threat modeling, STRIDE, data flow diagram, trust boundary, identify threats, SDL threat modeling, security design review, threat model a system, mitigation mapping, Microsoft Threat Modeling Tool, secure design review, design-time security. DO NOT USE for org-wide security architecture (use security-architecture) or for runtime detection (use sentinel / defender-xdr).
Use this skill to find and fix the security holes that AI-built apps most often ship with: 'is my app secure,' 'security check,' 'check my app for security holes,' 'can users see each other's data,' 'did I leak my API keys,' or 'I'm worried about hackers.' Claude runs the audit on the codebase: exposed keys, data isolation between users, auth on every route, webhook signatures, rate and spend limits, and dependencies. Not for the full pre-launch checklist (use go-live) or for privacy policy and legal terms (use legal).
This skill should be used when the user asks to "attack Active Directory", "exploit AD", "Kerberoasting", "DCSync", "pass-the-hash", "BloodHound enumeration", "Golden Ticket", "Silver Ticket", "AS-REP roasting", "NTLM relay", or needs guidance on Windows domain penetration testing.
Audit MCP servers for tool poisoning, tool shadowing, rug pulls, SSRF, and unauthenticated exposure using Invariant Labs' mcp-scan for static/runtime scanning plus manual SSRF/auth checks and description pinning. Use before adding a new MCP server to an agent stack, when reviewing an internal MCP server, detecting rug pulls, or investigating an agent's unexpected tool-driven behavior.
Integrate the Didit AML Screening standalone API to screen people or companies against sanctions, PEP, warning and adverse-media watchlists. Use when the user wants to run AML or KYC/AML compliance checks, screen against OFAC/UN/EU sanctions lists, check PEP status, search adverse media, tune match and risk scoring, review AML hits (Confirmed Match, False Positive, Inconclusive), or turn on ongoing AML monitoring using Didit. Covers POST /v3/aml/ (1,300+ watchlists, fuzzy name matching, configurable weights and thresholds, idempotent retries) and the AML hit review endpoints.
Orienta sobre a Lei Geral de Proteção de Dados (LGPD – Lei 13.709/2018) do Brasil. Use quando o usuário mencionar LGPD, proteção de dados no Brasil, privacidade de dados, bases legais, direitos do titular, ANPD, dados sensíveis, consentimento ou conformidade com a lei brasileira de dados.
Grants, requests, audits and removes access to data assets in an AWS data catalog (the Amazon SageMaker Catalog supported by Amazon DataZone) through catalog subscriptions over published listings. Covers requesting a subscription, approving or rejecting requests with a recorded decision, sharing a listing with a project, revoking one or many subscriptions, and confirming grant settlement. Triggers on: give another team access to a table, request access to a dataset, approve or reject an access request, share a listing with a project, who has access to this table, revoke access, bulk revoke, is the access actually gone, subscription grant status. Not for: IAM roles, policies or STS (use aws-iam), S3 bucket policies (use securing-s3-buckets), Clean Rooms permissions (use aws-cleanrooms), or writing catalog metadata, glossaries and forms, publishing listings, or retiring or deleting an asset that other teams are subscribed to and the order of operations that needs (use managing-data-catalog)
Alibaba Cloud KMS Secret Management Skill. Used for managing secrets in KMS, supporting create, delete, update, query operations, version management, and rotation policy configuration. Trigger words: "KMS secret", "secret management", "create secret", "delete secret", "secret rotation", "get secret value"
Use when a Node.js or Python server authenticates to Google: OAuth 2.0, ID token checks, service accounts, ADC, Workload Identity, and API keys. Not for end-user web sign-in (google-signin). Opt out: no wiring, без обвязки. Triggers: “google-auth-library,” “service account,” “сервисный аккаунт.”
Design, implement, and review Supabase solutions — Postgres, Auth, Row Level Security, Storage, Realtime, Edge Functions, and local environments. Use when `supabase/config.toml`, Supabase migrations, or `@supabase/*` clients are involved; do not use as a substitute for in-depth Postgres analysis of schemas, indexes, or plans — combine with `specsfy-specialist-postgres` for that.
Secure Twilio applications against common attacks. Covers credential management (API keys vs auth tokens), request validation (webhook signature verification), PCI DSS compliance, HIPAA account requirements, SMS pumping prevention, geo-permissions, and account isolation patterns. Use this skill when developers are building or deploying Twilio apps.
Use when adding or auditing crypto checkout, crypto top-ups, or payment webhooks: invoice states, signed callbacks, idempotency, and underpayment. Not for card billing (stripe-billing). Opt out: no wiring, без обвязки. Triggers: “crypto payment,” “webhook signature,” “оплата криптой,” “вебхук платежа.”
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.