Blockchain

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Transform vague feature ideas into clear, testable requirements using EARS format. Capture user stories, define acceptance criteria, identify edge cases, and validate completeness before moving to design.

Systematic three-phase approach to feature development using Requirements, Design, and Tasks phases. Transforms vague feature ideas into well-defined, implementable solutions that reduce ambiguity, improve quality, and enable effective AI collaboration.

Transform approved requirements into comprehensive technical designs. Define system architecture, component interactions, data models, and interfaces to create a blueprint for implementation.

Detect exposed secrets, API keys, credentials, and tokens in code. Use before commits, on file saves, or when security is mentioned. Prevents accidental secret exposure. Triggers on file changes, git commits, security checks, .env file modifications.

Enterprise session state management, token budget optimization, runtime tracking, session handoff protocols, context continuity for Claude Sonnet 4.5 and Haiku 4.5 with context awareness features

Context window management and token budget optimization

Figma design system integration with API automation, design tokens, and component libraries for scalable design infrastructure. Enhanced MCP integration, error handling, and performance optimization.

Enterprise-grade security expertise with production-ready patterns for OWASP Top 10 2021, zero-trust architecture, threat modeling (STRIDE, PASTA), secure SDLC, DevSecOps automation, cloud security, cryptography, identity & access management, and compliance frameworks (SOC 2, ISO 27001, GDPR, CCPA).

Enterprise-grade security expertise with production-ready patterns for OWASP Top 10 2021, zero-trust architecture, threat modeling (STRIDE, PASTA), secure SDLC, DevSecOps automation, cloud security, cryptography, identity & access management, and compliance frameworks (SOC 2, ISO 27001, GDPR, CCPA).

Enterprise session state management, token budget optimization, runtime tracking, session handoff protocols, context continuity for Claude Sonnet 4.5 and Haiku 4.5 with context awareness features

Design system patterns with DTCG tokens, WCAG 2.2, and Figma integration

TypeScript 5.9+ development specialist covering React 19, Next.js 16 App Router, type-safe APIs with tRPC, Zod validation, and modern TypeScript patterns. Use when developing TypeScript applications, React components, Next.js pages, or type-safe APIs.

Enterprise Encryption Security with AI-powered cryptographic architecture, Context7 integration, and intelligent encryption orchestration for data protection

Design system patterns, W3C DTCG 2025.10 token architecture, WCAG 2.2 accessibility standards, and Figma MCP workflows for consistent, accessible UI development

Enterprise Claude Code context window optimization with 2025 best practices: aggressive clearing, memory file management, MCP optimization, strategic chunking, and quality-over-quantity principles for 200K token context windows.

Use when you need to implement CloudBase Auth v2 over raw HTTP endpoints (login/signup, tokens, user operations) from backends or scripts that are not using the Web or Node SDKs.

A single skill that helps design and implement CloudBase Auth v2 using Web SDK, Node SDK, and HTTP APIs, including login methods, tokens, and best practices.

Context-efficient codebase exploration using AST analysis. Use when exploring Kosmos architecture, understanding code structure, or preparing documentation for AI programmers. Triggers: xray, map structure, skeleton, interface, architecture, explore kosmos, warm start, token budget, context compression.