Claude Skills

This Claude Skill performs comprehensive security auditing by combining static code analysis, dynamic testing, dependency vulnerability scanning, secrets detection, and OWASP compliance checking. It uses coordinated agents in a sequential workflow with validation gates between analysis phases. Use this skill when you need to conduct security audits, vulnerability scans, or penetration tests.

The sandbox-configurator skill automatically configures Claude Code sandbox security settings with file system and network isolation boundaries. It specializes in setting up secure execution environments by managing permissions, network policies, and access controls. Use this skill when you need to establish secure isolation boundaries for your code execution sandbox.

This research-driven planning skill performs comprehensive requirements analysis and risk mitigation using multi-agent consensus and 5x pre-mortem cycles. It generates validated, risk-mitigated plans with <3% failure confidence for parallel implementation teams. Use it when starting new features or projects requiring evidence-based technology selection and thorough planning before development begins.

ReasoningBank Intelligence enables AI agents to implement adaptive learning by recording experiences, recognizing patterns, and optimizing their strategies over time. Use this skill when building self-learning agents, optimizing complex workflows, or implementing meta-cognitive systems that require continuous improvement. It provides persistent learning capabilities through integrations like AgentDB.

This skill implements ReasoningBank adaptive learning using AgentDB's high-performance vector database for building self-improving AI agents. It provides trajectory tracking, verdict judgment, memory distillation, and pattern recognition capabilities to optimize decision-making. Use it when creating self-learning agents or implementing experience replay systems that require fast memory access and pattern retrieval.

This Claude Skill performs rapid code quality checks by executing theater detection, linting, security scans, and basic tests in parallel. It provides developers with instant, actionable feedback on their code in under 30 seconds. Use it for fast, essential quality assurance during development to catch issues early.

The prompt-architect skill is a framework for creating, analyzing, and refining prompts for AI systems like Claude and ChatGPT. It applies evidence-based techniques, including structural optimization and anti-pattern detection, to improve prompt effectiveness. Use it when developing new prompts or optimizing existing ones for language models.

This Claude Skill performs comprehensive pre-deployment validation to ensure code is production-ready. It runs a complete audit pipeline including security scans, performance benchmarks, and documentation checks. Use it as a final deployment gate to generate a deployment checklist and verify all production requirements are met.

This enterprise-grade PowerPoint generation skill creates professional presentations requiring consistent visual quality and accessibility compliance. It implements an html2pptx workflow with spatial layout optimization and validation gates for complex, multi-source data integration. Use it for generating 30+ slide decks like board reports and analyses with enforced workflow constraints.

This performance profiling skill helps developers identify and optimize application bottlenecks across CPU, memory, I/O, and network dimensions. It provides comprehensive analysis through baseline measurement, bottleneck detection, and root cause investigation phases. Use this skill when you need systematic performance optimization with tools like perf, Instruments, or clinic.js integration.

This skill provides comprehensive performance analysis and bottleneck detection for Claude Flow swarms. It identifies optimization opportunities and delivers actionable recommendations to improve system performance. Use it when you need to profile workflows, analyze metrics, and benchmark your swarm's efficiency.

This skill provides comprehensive performance analysis and bottleneck detection for Claude Flow swarms. It identifies issues across communication, processing, memory, and network layers while offering AI-powered optimization recommendations. Use it for real-time monitoring, profiling swarm operations, and generating detailed performance reports.

This META-SKILL orchestrates parallel implementation by dynamically compiling Loop 1 plans into executable agent+skill graphs. It selects optimal agents from an 86-agent registry and coordinates a 9-step swarm process with theater detection and reality validation. Use it for adaptive, theater-free execution that bridges research planning and intelligent recovery systems.

This Claude Skill enables AI-assisted pair programming with driver/navigator role management and automatic switching. It provides real-time code verification, quality monitoring, and supports TDD, debugging, and refactoring workflows. Use it for collaborative coding sessions with continuous security scanning and performance optimization.

This skill configures network isolation for Claude Code sandboxes by enabling trusted domain whitelisting and custom access policies. It helps developers secure their sandbox environments against prompt injection attacks while managing corporate proxies and internal registries. Use this when you need to control network access and implement zero-trust security for AI code execution.

The micro-skill-creator rapidly generates atomic, single-purpose skills optimized with evidence-based prompting and specialist agents. It produces highly focused components using patterns like self-consistency and plan-and-solve, validated through systematic testing. This makes it ideal for developers building reliable, composable workflow elements in Claude Code.

This diagnostic tool analyzes prompt quality to detect anti-patterns, identify token waste, and provide optimization recommendations. Developers should use it before publishing new skills, when prompts exceed token budgets, or when responses are inconsistent. It helps improve clarity, reduce token usage, and enhance prompt effectiveness.

This proactive token management tool helps developers stay within budget limits by analyzing task complexity and current usage. It generates intelligent chunking strategies and creates step-by-step execution plans to prevent token exhaustion. Use it before starting large tasks or when approaching budget limits during multi-phase projects.

This skill analyzes your Claude skill library to identify coverage gaps, redundant overlaps, and optimization opportunities. Use it during quarterly reviews, before refactoring, or when adding new skills to get actionable recommendations for improving your skill portfolio.

This Claude Skill provides a specialized workflow for developing, training, and deploying machine learning models. It supports various architectures like CNNs and RNNs, handles the full lifecycle from training to production, and outputs trained models, metrics, and deployment packages. Use it when you need to build a new ML model, require model training, or are preparing for a production deployment.

This skill helps developers diagnose and fix common machine learning training issues like loss divergence, overfitting, and slow convergence. It provides systematic debugging to identify root causes and delivers fixed code with optimization recommendations. Use it when facing training problems like NaN losses, poor validation performance, or when training fails to converge properly.

The interactive-planner skill uses Claude Code's AskUserQuestion tool to systematically gather project requirements through structured multi-select questions. It helps developers break complex projects into scopable decisions and convert vague ideas into concrete specifications. Use this skill when you need comprehensive requirement gathering through interactive, multi-dimensional analysis.

The intent-analyzer skill interprets ambiguous user requests by applying cognitive science principles to uncover their underlying goals. It uses probabilistic mapping, first-principles decomposition, and Socratic clarification to transform vague inputs into well-defined objectives. Use this skill when deeper understanding would improve response quality or when helping users clarify their true needs.

This Claude Skill automates internationalization workflows for web applications by handling translation, key generation, and library setup. It analyzes your project to configure i18n libraries, design key structures, and manage locale files. Use it to quickly add multi-language support and streamline the localization process.