Assess a Kubernetes cluster from the attacker viewpoint when an agent needs exposure-focused findings instead of a general cluster scanner listing.
Score 70/100
Run automated red-team and failure scans against an LLM or RAG app before users find the breakage.
Score 70/100
Run a thorough TLS preflight against a host before launch, certificate renewal, or incident review.
Score 70/100
Processes STIX 2.1 threat intelligence bundles delivered via TAXII 2.1 servers, normalizing objects into platform-native
Score 70/100
Procore security basics — construction management platform integration. Use when working with Procore API for project management, RFIs, or submittals.
Score 70/100
Audit procurement and procure-to-pay systems for spend analytics (Pareto analysis, tail spend visibility), supplier consolidation opportunities, Kraljic matrix category…
Score 70/100
Comprehensive pre-deployment validation ensuring code is production-ready. Runs complete audit pipeline, performance benchmarks, security scan, documentation check, and generates…
Score 70/100
Develops comprehensive threat actor profiles for APT groups, criminal organizations, and hacktivist collectives
Score 70/100
Run a comprehensive audit on any Claude Code project. Scores 10 categories from 0-10 (total /100), identifies gaps, and generates a prioritized fix kit with copy-pasteable…
Score 70/100
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages).
Score 70/100
Red-team an Agentforce agent against prompt-injection and jailbreak attacks; codify test cases and guardrails.
Score 70/100
Use when writing skills, CLAUDE.md files, agent prompts, or any directives that involve shell commands, environment variables, API credentials, file creation, or git operations -…
Score 70/100
Prompt injection testing. USE WHEN prompt injection, jailbreak, LLM security, AI security assessment, pentest AI application, test chatbot vulnerabilities.
Score 70/100
Configure Cedar policy enforcement and Ed25519 signed receipts for Claude Code tool calls. Use when setting up projects that need cryptographic audit trails, policy-gated tool…
Score 70/100
Comprehensive techniques for capturing, analyzing, and documenting network protocols for security research, interoperability, and debugging.
Score 70/100
Create Microsoft Entra Agent Identity blueprints, principals, and agent identities with the right beta Graph permissions, sponsor rules, and sidecar-based auth patterns.
Score 70/100
Audit a government or public services system for compliance, fraud risk, and security — chains benefits processing review, fraud detection analysis, regulatory compliance check…
Score 70/100
Purificar agua de fuentes silvestres usando ebullición, filtración, desinfección química y destilación solar.
Score 70/100
Queries the PyPI JSON API and the libraries.io API to analyze Python package metadata, dependency trees, and version histories.
Score 70/100
Guidelines for building Python cybersecurity tools with secure coding practices, async scanning, and structured security testing.
Score 70/100
Python-based threat modeling using pytm library for programmatic STRIDE analysis, data flow diagram generation, and automated security threat identification.
Score 70/100
Formal Quality Assurance Checklist before every Merge/Deploy. 6-phase validation with Build Verification, Test Suite, No-Touch Zones, Region Check, Security Review, and QA Report…
Score 70/100
Run comprehensive quality checks including linting, type checking, tests, and security audits before commits or deployments
Score 70/100
Deep code review with web research to verify against latest ecosystem. Use when user says 'double check against latest', 'verify versions', 'check security', 'review against…
Score 70/100
Query token security audit to detect scams, honeypots, and malicious contracts before trading. Returns comprehensive security analysis including contract risks, trading risks, and…
Score 70/100
Auto-fill security questionnaires (SIG Lite, CAIQ, Enterprise) using scan data and policy documents.
Score 70/100
Analyzes vendor security questionnaire responses. Identifies red flags, gaps, and areas requiring follow-up. Supports SIG, CAIQ, and custom questionnaires.
Score 70/100
Use when implementing new features in Quetrex. Ensures TDD, TypeScript strict mode, Next.js App Router patterns, ShadCN UI components, and security best practices are followed.
Score 70/100
Lightning-fast quality check using parallel command execution. Runs theater detection, linting, security scan, and basic tests in parallel for instant feedback on code quality.
Score 70/100
QuickNode security basics — blockchain RPC and Web3 infrastructure integration. Use when working with QuickNode for blockchain development.
Score 70/100
Ramp security basics — corporate card and expense management API integration. Use when working with Ramp for card management, expenses, or accounting sync.
Score 70/100
Rclone is an open-source command-line program to sync files and directories to and from over 70 cloud storage providers including Google Drive, S3, Dropbox, Azure, OneDrive, and…
Score 70/100
Use when configuring reCAPTCHA on Web-to-Case, Web-to-Lead, Experience Cloud forms, or Headless Identity flows, or when designing bot-mitigation strategies for Salesforce…
Score 70/100
Recettix : compétence de recette et validation des livrables d'une application métier TypeScript. Couvre : Plan de Recette contractuel, critères d'acceptance Gherkin, jeux de…
Score 70/100
Austrian social security law analysis — health insurance (ASVG/GSVG/BSVG), pension (Pensionsrecht), unemployment benefits (AlVG), care allowance (BPGG), accident insurance, and…
Score 70/100
Austrian social security appeals — challenging Bescheide from ÖGK/PVA/AMS/SVS, Klage to Arbeits- und Sozialgericht (ASG), pension disputes, Pflegestufe appeals, and AMS sanctions…
Score 70/100
Security reconnaissance. USE WHEN recon, reconnaissance, bug bounty, attack surface. SkillSearch('recon') for docs.
Score 70/100
Automated full-scope reconnaissance starting from a domain or domain list. Performs subdomain enumeration, port scanning, technology fingerprinting, OSINT correlation, Google…
Score 70/100
Recon-ng is a full-featured modular reconnaissance framework written in Python, designed to conduct web-based open source intelligence (OSINT) gathering quickly and thoroughly.
Score 70/100
Network reconnaissance and security auditing using Nmap for port scanning, service enumeration, and vulnerability detection.
Score 70/100
Comprehensive knowledge about network reconnaissance and service enumeration. Provides methodologies for port scanning, service fingerprinting, web directory discovery, and…
Score 70/100
Diagnose why a user can or cannot see/edit a record: UserRecordAccess SOQL, Why Can a User Access This Record debug log, OWD, role hierarchy, sharing rules, manual/team/apex…
Score 70/100
Executes structured recovery from a ransomware incident following NIST and CISA frameworks, including environment
Score 70/100
Use when planning or executing authorized red team engagements, attack path analysis, or offensive security simulations.
Score 70/100
Run local adversarial attack passes against agents, RAG pipelines, and chatbots to surface concrete failure classes before production rollout.
Score 70/100
Interactively prepares a targeted Red Team Review package. It conducts a brief discovery interview to determine the threat model, generates a strict security auditor prompt,…
Score 70/100
(Industry standard: Review and Critique Pattern) Primary Use Case: Iterative generation paired with adversarial review, continuing until an 'Approved' verdict is reached.
Score 70/100
Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.
Score 70/100
Implement proven methodologies and tool workflows from top security researchers for effective reconnaissance, vulnerability discovery, and bug bounty hunting.
Score 70/100
Adversarial verification for AI-generated legal content with systematic fact-checking, source validation, and quality control.
Score 70/100
AI pressure redirection — handling conflicting demands, tool failures, and competing constraints by blending with incoming force then reframing.
Score 70/100
Spawn a one-shot red-team subagent to challenge a milestone result. Calibrated to return "nothing substantive" when the work is sound — does not invent issues to seem thorough.
Score 70/100
Audit codebases for cross-industry regulatory compliance across SOX, GDPR, HIPAA, PCI-DSS, CCPA/CPRA, FedRAMP, FISMA, COPPA, and FERPA.
Score 70/100
Audit an existing CI/CD pipeline for slowness, security issues, and reliability gaps. Use when asked to "audit pipeline", "why is CI slow", "pipeline review", or "deployment…
Score 70/100
Pre-release verification checklist. Validates features, tests, docs, security, and quality gates before shipping. Delegates to the Centinela (QA) agent.
Score 70/100
Sequential release gate validating build success, test suite, security checks, type checking, manifest counts consistency, and changelog presence.
Score 70/100
Senior developer-level release review for macOS/iOS apps. Identifies security, privacy, UX, and distribution issues with actionable fixes.
Score 70/100
Manages release preparation including validation, version bumping, documentation verification, and security checks.
Score 70/100
RemoFirst security basics — global HR, EOR, and payroll platform integration. Use when working with RemoFirst for global employment, payroll, or compliance.
Score 70/100
Use when configuring Remote Site Settings to allow Apex callouts to external URLs, or when distinguishing Remote Site Settings from CSP Trusted Sites for Lightning component…
Score 70/100