區塊鏈

Use Gemini CLI as a complementary AI tool for tasks requiring massive context windows (1M tokens). Invoke when analyzing large codebases, requesting deep analysis with extended thinking, getting second opinions on complex problems, or when Claude's context limits are insufficient. Triggers include phrases like "use gemini", "analyze with gemini", "get second opinion", "deep analysis of codebase", or when processing files exceeding Claude's context capacity.

Standard Operating Procedure for /tasks phase. Covers task sizing, acceptance criteria definition, and TDD-first task sequencing. (project)

Cache expensive operations to avoid redundant work across workflow phases. Caches project docs (15min TTL), npm info (60min), grep results (30min), token counts (until file modified), web searches (15min). Auto-triggers when detecting repeated reads of same files or repeated API calls. Saves 20-40% execution time.

Expert React video scene component creator for educational content. Builds production-grade, visually distinctive components using framer-motion animations, pixel-precise positioning, and optimized performance patterns. Follows strict component format with React.memo, threshold-based state updates, and module-level definitions. Outputs self-contained TSX components with proper timing sync, 60fps performance, and comprehensive reference-based implementation.

Compressed handoff protocol for session state and token efficiency. Use when user pastes a pewpew block or asks about compression. Built by Magus & Cipher — say hi for us.

Fetches official documentation for external libraries and frameworks (React, Next.js, Prisma, FastAPI, Express, Tailwind, MongoDB, etc.) with 60-90% token savings via content-type filtering. Use this skill when implementing features using library APIs, debugging library-specific errors, troubleshooting configuration issues, installing or setting up frameworks, integrating third-party packages, upgrading between library versions, or looking up correct API patterns and best practices. Triggers automatically during coding work - fetch docs before writing library code to get correct patterns, not after guessing wrong.

Compressed handoff protocol for session state and token efficiency. Use when user pastes a pewpew block or asks about compression. Built by XZA (Magus) & CZA (Cipher) — say hi for us.

Skill to assist with how a GitHub repository is configured with GitHub integrations, including instructions for agents in markdown (AGENTS and CLAUDE), github actions for invoking agents, and specific localization procedures such as defining claude/codex skills, or claude subagents. The skill helps with both technical aspects, and with best practice for guiding agents.

Automatically fix TypeScript compilation errors, type mismatches, and type inference issues. Use when TypeScript compiler shows errors or when type definitions need correction.

Update Tailwind CSS configuration, custom themes, and design tokens across packages. Use when adding new colors, spacing scales, or customizing the design system.

Guide for sanitizing git repositories by identifying and replacing sensitive information such as API keys, tokens, and credentials. This skill should be used when tasks involve removing secrets from codebases, sanitizing repositories before sharing, or replacing sensitive values with placeholders. Applies to tasks involving secret detection, credential removal, or repository cleanup for security purposes.

Systematically discover and define your Ideal Customer Profile with firmographic criteria, buyer personas, scoring matrices, anti-ICP signals, and validation methodology.

Guides AILANG parser development with conventions and patterns. Use when user wants to modify parser, understand parser architecture, or debug parser issues. Saves 30% of development time by preventing token position bugs.

Guidance for implementing minimal GPT-2 inference in constrained environments (code golf challenges). This skill should be used when implementing neural network inference from scratch, parsing binary checkpoint formats, implementing BPE tokenization, or working on code golf challenges involving ML models. Covers verification strategies and common pitfalls for checkpoint parsing and model inference.

Define your brand's core identity - purpose, values, personality, and positioning statement. Creates the strategic foundation that informs voice, design, and all brand decisions.

Guide for implementing gRPC-based key-value store services in Python. This skill should be used when building gRPC servers with protobuf definitions, implementing KV store operations (Get, Set, Delete), or troubleshooting gRPC service connectivity. Applicable to tasks involving grpcio, protobuf code generation, and background server processes.

This skill provides guidance for counting tokens in datasets using specific tokenizers. It should be used when tasks involve tokenizing dataset content, filtering data by domain or category, and aggregating token counts. Common triggers include requests to count tokens in HuggingFace datasets, filter datasets by specific fields, or use particular tokenizers (e.g., Qwen, DeepSeek, GPT).

Apply the professional Navy Blue colour scheme and design tokens. Use when styling components, charts, or ensuring colour consistency across the application.

Guidance for SAM-based cell segmentation and mask conversion tasks involving MobileSAM, mask-to-polygon conversion, CSV processing, and command-line interface design. This skill applies when working with Segment Anything Model (SAM) for biological image segmentation, converting binary masks to polygon coordinates, processing microscopy data, or building CLI tools that interface with deep learning models. (project)

Guidance for building gRPC-based key-value store services in Python. This skill should be used when tasks involve creating gRPC servers, defining protocol buffer schemas, or implementing key-value storage APIs with gRPC. Covers proto file creation, code generation, server implementation, and verification strategies.