Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Give an AG2 `Agent` the ability to run shell commands. Covers `SandboxShellTool` (client-side `subprocess` via `LocalEnvironment`, works with any provider) and the provider-native `ShellTool` (OpenAI Responses execution). Use when the user wants the Agent to execute commands, build/test code, manage files, or operate on a workspace. Always pair with sandboxing — `allowed`, `blocked`, `ignore`, or `readonly`.
This skill should be used when the user asks to "test API security", "fuzz APIs", "find IDOR vulnerabilities", "test REST API", "test GraphQL", "API penetration testing", "bug bounty API testing", or needs guidance on API security assessment techniques.
Expert knowledge for Azure Enclave development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and deployment. Use when building Azure Enclave apps with AVD/AKS, RBAC/managed identities, CMK encryption, Bicep/ARM, or ExpressRoute, and other Azure Enclave related development tasks. Not for Azure Confidential Computing (use azure-confidential-computing), Azure Attestation (use azure-attestation), Azure Cloud Hsm (use azure-cloud-hsm), Azure Dedicated HSM (use azure-dedicated-hsm)
Guide for convex-helpers library patterns including Triggers, Row-Level Security (RLS), Relationship helpers, Custom Functions, Rate Limiting, and Workpool. Use when implementing automatic side effects, access control, relationship traversal, auth wrappers, or concurrency management. Activates for triggers setup, RLS implementation, custom function wrappers, or convex-helpers integration tasks.
Expert UK Cyber Essentials and Cyber Essentials Plus advisor — the NCSC-owned, IASME-delivered baseline certification. Covers the current Danzell question set (Requirements for IT Infrastructure v3.3, mandatory for assessment accounts from April 27, 2026) and the Willow transition, the five control themes (firewalls, secure configuration, security update management, user access control, malware protection), scoping rules for cloud services, BYOD and home working, the 14-day critical-update rule, mandatory MFA for cloud services and the new auto-fail questions, CE Plus technical audits, pricing, annual renewal, the included cyber liability insurance, and procurement mandates (PPN 014, MoD Defence Cyber Certification, NHS). Use this skill whenever a user mentions Cyber Essentials, CE Plus, IASME, the UK government cyber certification, Danzell or Willow question sets, UK public-sector or MoD supply-chain security requirements, or wants a readiness gap assessment.
Detect DCSync attacks (MITRE T1003.006) where adversaries abuse Active Directory replication privileges to extract password hashes, by auditing Event ID 4662 for the DS-Replication-Get-Changes GUIDs and flagging non-domain-controller accounts issuing DsGetNCChanges RPC calls. Use when hunting for credential theft via Mimikatz lsadump::dcsync or Impacket secretsdump, investigating lateral movement with domain admin credentials, or auditing AD replication permissions.
Use when assessing or reviewing Kubernetes workloads running on Amazon EKS for best practice compliance, including pod configuration, security posture, observability, networking, storage, image security, and CI/CD practices. Requires kubectl and awscli access to the target cluster. Triggers on "assess my EKS workloads", "check k8s best practices", "assess container workloads", "evaluate pod security", "workload compliance check", "EKS workload assessment", "检查 K8s 工作负载", "评估容器最佳实践", "审计 EKS 应用", "检查 Pod 配置", "容器安全评估", "工作负载合规检查".
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Create, edit, audit, and speed up GitHub Actions workflows using Bret Fisher's opinionated DevOps rules. Use it when the user asks to create a workflow or CI/CD pipeline, edit or add a job to an existing `.github/workflows/*` file (even a one-line change), review or harden a workflow for security, speed up slow CI, publish a container image from CI, automate releases, or mentions GHA, action pinning, or findings from gasa, zizmor, poutine, pinact, or actionlint, even if they don't say "GitHub Actions".
Implements supply chain integrity verification for container builds with the in-toto framework: generating signing keys, defining a supply chain layout, recording pipeline steps as signed link metadata, verifying before deployment, enforcing at Kubernetes admission, and integrating with SLSA. Use when attesting CI/CD pipeline steps, proving an image followed the approved build process, or enforcing provenance at admission. Keywords: in-toto, layout, link metadata, step, inspection, SLSA, provenance, admission. Do not use for signing and verifying images with Cosign - use implementing-image-provenance-verification-with-cosign.
Design, implement, review, and troubleshoot secure Easypaisa merchant payment integrations for Pakistani websites, mobile apps, and commerce platforms. Covers Easypaisa Mobile Account and OTC flows, approved hosted or direct integration methods, callbacks/postbacks, transaction verification, reversals, settlement, merchant reporting, plugins, reconciliation, onboarding, and production rollout. Use when adding Easypaisa payments, repairing an existing Easypay/Easypaisa gateway, migrating outdated code, or preparing a merchant integration for certification and launch.
Guidance for managing AI agents at enterprise scale with Microsoft Agent 365 - the control plane that lets admins observe, govern, and secure every agent (Microsoft, Copilot Studio, and third-party) from a single registry, using Microsoft Entra Agent ID for identity, Microsoft Purview for data security, and Microsoft Defender for runtime threat protection. WHEN: Microsoft Agent 365, Agent 365, manage agents at scale, agent control plane, agent registry, agent map, observe govern secure agents, Entra Agent ID, agent identity lifecycle, third-party agent governance, secure AI agents tenant-wide, agent sprawl, agent inventory. DO NOT USE for Purview-only data controls on a single agent (use purview-agent-365-security) or end-user Copilot oversharing (use purview-copilot-oversharing).
Detects and extracts hidden data embedded in images, audio, and other media files using steganalysis tools such as StegDetect, zsteg, stegsolve, binwalk, steghide, and OpenStego to uncover covert communication channels. Use when investigating suspected data hiding or exfiltration via media files, espionage/insider-threat cases, or anomalies in media file properties found during standard file analysis.
Use when implementing SpacetimeDB authentication or authorization, including SpacetimeAuth, Auth0, Clerk, OIDC, auth claims, subject/issuer checks, custom claims, roles, row-level security, and rejecting client connections. Triggers on: auth, authentication, authorization, SpacetimeAuth, Auth0, Clerk, OIDC, claims, RLS, row-level security.
Implement, harden, or review defensive security controls for REST APIs, including authentication and authorization boundaries, validation, rate limiting, abuse prevention, resource limits, SSRF defenses, safe errors, logging, and security tests. Use when API security, endpoint hardening, threat review, rate limiting, token handling, or sensitive business-flow protection is an explicit concern. Do not use for ordinary endpoint logic without meaningful security scope or for offensive exploitation
Audit GitHub Actions action usage across an org. Searches for a specific action (incident mode) or sweeps all workflow files for non-compliant action references (audit mode). Produces a read-only report of findings with compliance status and resolved SHAs. Does not modify any files. <example> User: We need to check if any repos are using tj-actions/changed-files Action: Trigger action-audit in incident mode for that action </example> <example> User: Can you find all unpinned actions across the org? Action: Trigger action-audit in audit mode </example>
Comprehensive backend development workflow that orchestrates expert analysis, architecture design, implementation, and deployment using the integrated toolset. Handles everything from API design and database architecture to security implementation and DevOps automation.
Reference for all Bitwarden workflow linter (bwwl) rules. Covers all 10 linter rules split into two categories: mechanical rules that can be applied automatically (name_capitalized, permissions_exist, pinned_job_runner, step_pinned, underscore_outputs, job_environment_prefix, check_pr_target) and judgment rules requiring user input (name_exists, step_approved, run_actionlint). Use the workflow-audit skill to run the linter and report findings, and the workflow-fix skill to apply fixes. <example> User: What does the step_pinned rule check for? Action: Consult this skill for the rule definition and fix procedure </example> <example> User: How do I fix a permissions_exist finding? Action: Consult this skill for the fix procedure </example>
Confirmation gate before any bulk delete, cleanup, or destructive operation that could result in data loss — shell-level (rm -rf, git rm, bulk sed) or brain-level (bulk forget, delete sweeps, purge-deleted, source removal, raw-SQL truncation). Presents a recoverability card and requires an explicit "yes" from the user before proceeding. Routing convention, not an operation-boundary enforcement.
Detect AI-generated deepfake audio used in voice phishing (vishing) by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with machine learning models, supporting batch audio analysis, confidence scoring, and forensic reporting. Use for deepfake voice detection, vishing investigations, AI-generated speech analysis, voice cloning detection, or audio authenticity verification.
Deploy and configure Zeek (formerly Bro) to passively analyze network traffic, generate structured connection/DNS/HTTP/SSL/file logs, detect anomalous behavior, and write custom scripts for organization-specific threats. Use for passive monitoring at network choke points, feeding SIEM/threat hunting with protocol metadata, or retrospective log analysis during incident response; not a substitute for inline IDS/IPS or host agents.
Query and manage Huawei Cloud HSS (Host Security Service) for daily security inspection and incident response. Covers host assets, vulnerabilities, security baselines, intrusion alerts (trojan/brute-force), login audit logs, risk scoring, and alert handling status updates. Read-only queries plus alert status marking — no isolation or antivirus actions. Use this skill when the user needs to inspect host security risks, investigate suspected intrusion, review vulnerability/baseline reports, or handle security alerts. Triggers include: 主机安全, HSS, Host Security Service, 安全巡检, 漏洞查询, 安全基线, 入侵告警, 木马检测, 暴力破解, 登录审计, 告警处置, 风险诊断, host security inspection, vulnerability scan, baseline check, intrusion alert, trojan detection, brute force, login audit, alert handling, risk diagnosis, security event response.
Operating production Kubernetes clusters effectively with resource management, advanced scheduling, networking, storage, security hardening, and autoscaling. Use when deploying workloads to Kubernetes, configuring cluster resources, implementing security policies, or troubleshooting operational issues.
Authentication and authorization security assessment for sessions, tokens, MFA, account takeover, IDOR, BOLA, BFLA, privilege escalation, tenant isolation, and identity boundary validation. Hands off to recon, input/protocol, access-control deep dive, exploit, or reporting workflows when those become the owner phase.
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.