Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions.
Review new or changed dependencies for supply-chain compromise before they enter a project — malicious install scripts (preinstall/postinstall), binding.gyp/node-gyp install-time execution (June 2026 worm), self-propagating worms (Shai-Hulud, binding.gyp), credential harvesting and exfiltration, obfuscated payloads, typosquatting, slopsquatting (AI-hallucinated package names), dependency/namespace confusion, maintainer account takeover, and unpinned or unverified versions. Reads manifests, lockfiles, install scripts, and dependency diffs offline across npm, PyPI, Go, Cargo, RubyGems, Maven, NuGet, and Composer, and reports each risk at file:line with a concrete fix — no install, no execution, no phoning home. Trigger when adding or upgrading a dependency, reviewing a PR that changes package.json / requirements.txt / go.mod / a lockfile, deciding whether a package is safe to install, or when the user mentions Shai-Hulud, binding.gyp, a compromised or malicious package, typosquatting, dependency confusion, or asks "is this dependency safe to add?".
Triage inbound vulnerability reports - GitHub Advisories (GHSA/CVE), bug bounty submissions, HackerOne/Bugcrowd/Intigriti exports, or a researcher's issue - to decide whether a finding is real, by-design, or noise. Reads the report offline, cross-references the project's documented intent and threat model (SECURITY.md, README, code, closed issues), statically audits any PoC without executing it, and emits a structured markdown triage report with a P0-P3 / By-Design severity and a recommended action. Use whenever the user asks to triage, assess, or score a vulnerability report, advisory, CVE, GHSA, or bug bounty submission, or asks "is this a real finding or by-design?".
Architecting solutions at the team level while staying coherent with Bitwarden's holistic architecture. Covers security mindset, architectural judgment, Bitwarden-specific constraints, and working with the architecture group. Use when designing or planning a solution, reviewing architecture within a team's scope, assessing change impact, evaluating trade-offs in different implementations, or deciding whether a choice needs architecture group input.
Use when adding DPoP (Demonstrating Proof-of-Possession) token binding to protect API calls with device-bound, sender-constrained access tokens that cannot be replayed if stolen. Also use when a user says "bind tokens to the client", "prevent token theft", or "sender-constrained tokens".
Plan static inspection of unknown binary files with a deterministic CLI whose Ghidra operations are currently unimplemented and fail closed. Use when you need to inspect a PE, ELF, or Mach-O file — triage suspicious binaries, map imported APIs, decompile functions, trace call paths, or produce structured evidence reports. Do not use for runtime analysis (debugging, dynamic tracing, sandbox execution), for modifying or patching binaries, or for binaries you already know everything about. The skill owns planning, hypothesis formation, and evidence synthesis; the CLI owns all deterministic operations.
Configure, maintain, or troubleshoot Claude Code local network protection: Claude/Anthropic HTTP(S) traffic goes through a dedicated inbound and fixed outbound; single node by default, or explicitly configure one primary and one backup node for fail-closed automatic failover; shells, scripts, and remote databases are not intercepted. Verify the wrapper, Clash/Mihomo dedicated inbound, proxy chaining, dynamic residential IPs, network hooks, the macOS sandbox, and Camoufox. Also used for explicitly authorized account residue scanning or cleanup. Use when the user mentions claude-code-guard, Claude account-ban prevention, blocked remote databases, Seatbelt EPERM, proxy disconnection blocking, node drift, or primary/backup failover; it cannot guarantee no account bans, no leakage whatsoever, or that different accounts cannot be linked.
Load PROACTIVELY when task involves reviewing code, auditing quality, or validating implementations. Use when user says "review this code", "check this PR", "audit the codebase", or "score this implementation". Covers the 10-dimension weighted scoring rubric (correctness, security, performance, architecture, testing, error handling, type safety, maintainability, accessibility, documentation), automated pattern detection for anti-patterns, and structured review output with actionable findings.
Deploys and monitors ransomware canary files using Python's watchdog library, placing decoy files mimicking high-value targets (financial records, credentials, database exports) where ransomware enumerates first, and alerting via email, Slack, or syslog on any read/modify/rename/delete. Use for early-warning ransomware detection on file servers, NAS, or endpoints, or to supplement EDR where agents can't be deployed.
Docker containerization expert: Dockerfile optimization, multi-stage builds, security hardening, Docker Compose orchestration, and production deployment. Use for Dockerfile creation/review, image size issues, container security, networking, and orchestration.
Implement and maintain compliance with SOC 2, HIPAA, PCI-DSS, and GDPR using unified control mapping, policy-as-code enforcement, and automated evidence collection. Use when building systems requiring regulatory compliance, implementing security controls across multiple frameworks, or automating audit preparation.
Integrate Arcjet Guard into Python Google ADK — assign guard_tool to LlmAgent(before_tool_callback=), put guard_plugin first on Runner(plugins=) so a deny dict with arcjetDenied skips the tool, and read a caller-owned id via google_adk_context. Use when asked to add Arcjet to google-adk, Google ADK Python, rate limit those tools, screen inbound messages, or block prompt injection / PII. This is Python google-adk 2.x, not JS @google/adk and not @google/genai.
Guidance for remediating oversharing across Microsoft 365 (SharePoint, OneDrive, Teams, Exchange) using the Secure & Governed Data Foundation blueprint - a three-pillar program (remediate oversharing, set up guardrails, meet regulations) built on SharePoint Advanced Management data access governance, sensitivity and container labels, secure-by-default labelling, Restricted Access Control, and Microsoft Purview. WHEN: Microsoft 365 oversharing, M365 oversharing, secure and governed data foundation, oversharing blueprint, too many people have access to SharePoint, EEEU everyone except external users, tighten permissions, data access governance report, restricted content discovery, secure by default labels, prepare data foundation, reduce sharing link sprawl, governed data estate. DO NOT USE for Copilot-specific readiness framing only (use purview-copilot-oversharing) or building a broad DLP program (use purview-dlp-policy).
Simulates and detects software supply chain attacks: typosquatting detection via Levenshtein distance against popular PyPI package names, dependency confusion testing against private registries, SHA-256 package hash verification, and known-CVE scanning with pip-audit. Use when auditing a project's dependencies for malicious or confused packages, or when assessing package-registry supply-chain risk.
Consolidate all SAST vulnerability results from the sast/ folder into a single final report ranked by severity and confidentiality impact. Reads all *-results.md files and produces sast/final-report.md. Run after all vulnerability detection skills complete. Use when asked to generate a final report, consolidate findings, or summarize security results.
Detect Server-Side Request Forgery (SSRF) vulnerabilities in a codebase using a three-phase approach: recon (find outbound call sites), batched verify (trace user input to destinations in parallel subagents, 3 sites each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/ssrf-results.md. Use when asked to find SSRF or server-side request forgery bugs.
Continuous security vulnerability scanning for OWASP Top 10, common vulnerabilities and insecure patterns. Use when reviewing code, before deployments or on file changes. Scans for SQL injection, XSS, secrets exposure and auth issues. Triggers on file changes, security mentions and deployment prep
Comprehensive security and compliance scanning for AWS CDK projects. Use when running security audits, checking license compliance, scanning container vulnerabilities, or running aggregated SAST/IaC/secret analysis before deployment.
Expert third-party risk management (TPRM) advisor — a vendor risk analyst for the full lifecycle: risk-based vendor tiering, tailored due-diligence questionnaires (SIG-style or mapped to ISO 27001, SOC 2, DORA, NIS2, HIPAA), SOC 2 Type II report review (exceptions, carve-outs, CUECs, bridge letters), DPA and sub-processor review under GDPR Art. 28, contract security addenda (DORA Art. 30 provisions), ongoing monitoring programmes, and vendor offboarding. Use this skill whenever a user mentions vendor risk, supplier due diligence, third-party assessments, security questionnaires, reviewing a vendor's SOC 2 report, vendor tiering, fourth parties or sub-processors, supply chain security requirements, DORA ICT third-party rules, business associate agreements, or exit/termination of a vendor. Also trigger for 'a customer sent us a questionnaire' and 'how do I assess this vendor' style requests.
Configure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables. Use when users mention Better Auth, betterauth, auth.ts, or need to set up TypeScript authentication with email/password, OAuth, or plugin configuration.
Deploys anomaly detection for OT/ICS environments using machine learning on OT network baselines, physics-based process models, and Modbus/DNP3/OPC UA traffic analysis to flag deviations, rogue devices, and mismatches against historian data. Use for continuous OT monitoring, baselining deterministic SCADA polling, or investigating alerts from Nozomi Guardian/Dragos needing deeper protocol analysis.
Set up Claude Code hooks that intercept dangerous Git commands (push, reset --hard, clean, branch -D, etc.) before they run. Use when the user wants to prevent destructive Git operations, add Git safety hooks, or block git push/reset in Claude Code.
Inspect customer database keys and perform explicitly requested, confirmation-gated Helix Cloud tenant or database-key mutations through the hosted Admin MCP server. Use only for create/delete tenant and create/revoke database-key operations. Never expose operational keys, bypass durable confirmation, or expand into excluded Cloud lifecycle surfaces.
Hunt for data exfiltration by analyzing Zeek and Suricata network telemetry for unusual data flows, DNS tunneling via large/frequent TXT queries, uploads to personal cloud storage, and encrypted-channel abuse, correlated against threat intel on destination domains. Use when hunting for data theft in a compromised environment, investigating unusual outbound data volumes, or determining what data was stolen during incident response.
Installs Calico as the cluster CNI and writes standard Kubernetes NetworkPolicy under it, covering default-deny baselines, policy ordering and precedence, service-account-based selectors, and verifying that policy is genuinely being enforced. Use when adopting Calico as the enforcement CNI, establishing a default-deny baseline, or debugging why a NetworkPolicy is not taking effect under Calico. Keywords: Calico CNI, NetworkPolicy, default deny, policy order, Felix, service account selector. Do not use for Calico-only CRDs such as GlobalNetworkPolicy or DNS egress - use implementing-container-network-policies-with-calico; for CNI-agnostic policy use implementing-network-policies-for-kubernetes.
Configure IndyKite Agent Gateway (IAG) in front of agent-to-agent (A2A) workflows or MCP servers, optionally with the self-hosted IndyKite Token Service (ITS) that mints the delegation token carried in `X-IK-Token` so multi-hop chains grow hop by hop. Use when wiring up A2A or MCP policy enforcement, modeling workflows in the IKG, configuring `JARVIS_*` / `config.yaml` (including `token_service`), running the Token Service, reading IAG audit records, or debugging IAG 401/403 responses.
Author an IndyKite ContX IQ (CIQ) policy plus its Knowledge Query that creates a brand-new node in the IndyKite Graph (IKG), then run it via `POST /contx-iq/v1/execute`. Use when ingesting a new entity through CIQ - no relationship creation, no updates to existing nodes, no deletes.
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.