Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Investigate GitHub security incidents using tamper-proof GitHub Archive data via BigQuery. Use when verifying repository activity claims, recovering deleted PRs/branches/tags/repos, attributing actions to actors, or reconstructing attack timelines. Provides immutable forensic evidence of all public GitHub events since 2011.
Complete GitHub workflow for Claude Code on the web. ALL GitHub operations MUST use REST API (never gh CLI). Includes branch naming (claude/*-sessionId), push retry logic, PR/issue management via API, and complete workflows. Use for all GitHub interactions in Claude Code web environment.
Process GitHub issues for float-ritual-stack projects with proper workflow - read, label in-progress, update with progress, commit work, close when done. Float-ism - direct-to-main commits, frequent updates, emoji-rich communication.
Builds product and industry glossaries with SEO-optimized definitions. Use when the user asks about glossary creation, term definitions, jargon explanations, knowledge bases, or terminology documentation.
GNS3 network lab operations including topology management, device configuration via console, and troubleshooting workflows for routers and switches
Build gRPC services with Go - protobuf, streaming, interceptors
Performance optimization techniques including profiling, memory management, benchmarking, and runtime tuning. Use when optimizing Go code performance, reducing memory usage, or analyzing bottlenecks.
Go performance optimization - profiling, benchmarks, memory management
>
>
>
>
Go performance optimization techniques including profiling with pprof,
Google Agent Development Kit (ADK) for Python. Capabilities: AI agent building, multi-agent systems, workflow agents (sequential/parallel/loop), tool integration (Google Search, Code Execution), Vertex AI deployment, agent evaluation, human-in-the-loop flows. Actions: build, create, deploy, evaluate, orchestrate AI agents. Keywords: Google ADK, Agent Development Kit, AI agent, multi-agent system, LlmAgent, SequentialAgent, ParallelAgent, LoopAgent, tool integration, Google Search, Code Execution, Vertex AI, Cloud Run, agent evaluation, human-in-the-loop, agent orchestration, workflow agent, hierarchical coordination. Use when: building AI agents, creating multi-agent systems, implementing workflow pipelines, integrating LLM agents with tools, deploying to Vertex AI, evaluating agent performance, implementing approval flows.
Expert guidance for Google Ads Script development including AdsApp API, campaign management, ad groups, keywords, bidding strategies, performance reporting, budget management, automated rules, and optimization patterns. Use when automating Google Ads campaigns, managing keywords and bids, creating performance reports, implementing automated rules, optimizing ad spend, working with campaign budgets, monitoring quality scores, tracking conversions, pausing low-performing keywords, adjusting bids based on ROAS, or building Google Ads automation scripts. Covers campaign operations, keyword targeting, bid optimization, conversion tracking, error handling, and JavaScript-based automation in Google Ads editor.
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
Preventing Jupyter cell hangs with explicit CuPy GPU memory cleanup
KINTSUGI processing principles: Never sacrifice quality for speed, always use GPU when available. Trigger: performance optimization, CPU/GPU choice, fast mode, quality vs speed.
gpu
Async operations and background tasks in GPUI. Use when working with async, spawn, background tasks, or concurrent operations. Essential for handling async I/O, long-running computations, and coordinating between foreground UI updates and background work.
Implementing custom elements using GPUI's low-level Element API (vs. high-level Render/RenderOnce APIs). Use when you need maximum control over layout, prepaint, and paint phases for complex, performance-critical custom UI components that cannot be achieved with Render/RenderOnce traits.
Expert guidance for GraalVM native image development with Java frameworks, build optimization, and high-performance application deployment
Master modern GraphQL with federation, performance optimization,
Builds GraphQL APIs with schema design, resolvers, error handling, and performance optimization using Apollo or Graphene. Use when creating flexible query APIs, migrating from REST, or implementing real-time subscriptions.
Use when optimizing GraphQL API performance with query complexity analysis, batching, caching strategies, depth limiting, monitoring, and database optimization.
Optimize GraphQL queries and resolvers for performance. Use when a mid-level developer needs to reduce N+1 or payload size.
Implement carbon-aware computing, energy-efficient AI inference, and ESG-compliant infrastructure to reduce carbon footprint while maintaining performance and meeting sustainability regulations.
Talk to Greg Isenberg about their expertise. Greg Isenberg provides authentic advice using their mental models, core beliefs, and real-world examples.
GreyCat C API and GCL Standard Library reference. Use for: (1) Native C development with gc_machine_t context, tensors, objects, memory management, HTTP, crypto, I/O; (2) GCL Standard Library modules - std::core (Date/Time/Tuple/geospatial types), std::runtime (Scheduler/Task/Logger/User/Security/System/OpenAPI/MCP), std::io (CSV/JSON/XML/HTTP/Email/FileWalker), std::util (Queue/Stack/SlidingWindow/Gaussian/Histogram/Quantizers/Random/Plot). Keywords: GreyCat, GCL, native functions, tensors, task automation, scheduler.
Creates GRINDE-style mind maps for higher-order learning and deep encoding. Use when organizing concepts, creating study notes, mapping relationships between ideas, visualizing knowledge structures, or when user mentions mind maps, concept maps, or note-taking.
Comprehensive guide to creating, managing, and maintaining ground truth datasets for AI evaluation including annotation, quality control, and versioning
gRPC integration patterns for ABP microservices including service implementation, client generation, multi-tenancy, and error handling. Use when: (1) implementing inter-service communication, (2) creating gRPC service endpoints, (3) consuming gRPC clients in AppServices, (4) designing high-performance APIs.
gRPC (Google Remote Procedure Call) เป็น high-performance, open-source universal RPC framework ที่ใช้ Protocol Buffers สำหรับ serialization เหมาะสำหรับ microservices communication โดยให้ efficient bin
Comprehensive gRPC microservices skill covering protobuf schemas, service definitions, streaming patterns, interceptors, load balancing, and production gRPC architecture
Build high-performance gRPC services with Protocol Buffers, bidirectional streaming, and microservice communication. Use when building gRPC servers, defining service contracts, or implementing inter-service communication.
High-performance RPC framework with Protocol Buffers.
Use when implementing web animations, timeline sequencing, scroll-triggered animations, SVG animations, layout transitions, or using GSAP, ScrollTrigger, ScrollSmoother, SplitText, Flip, DrawSVG, MorphSVG, MotionPath, or @gsap/react useGSAP hook.
Gene Set Enrichment Analysis using clusterProfiler gseGO and gseKEGG. Use when analyzing ranked gene lists to find coordinated expression changes in gene sets without arbitrary significance cutoffs. Detects subtle but coordinated expression changes.
Optimize 3D Gaussian Splat scenes for real-time rendering on iOS, macOS, and visionOS. Use when working with .ply or .splat files, targeting mobile/Apple GPU performance, or needing LOD, pruning, or compression strategies for 3DGS scenes.
Simplified memory profiling and leak detection for SDL3 HammerEngine using valgrind memcheck, AddressSanitizer, and massif. Identifies memory leaks, allocation hotspots, buffer reuse violations, and provides system-by-system memory breakdown with optimization suggestions. Use after performance-critical changes or when investigating memory issues.
Strategy for fetching data using React Server Components (RSC) and managing cache. Use for initial page loads and SEO-optimized data.
HAProxy load balancer configuration and management. Set up TCP/HTTP load balancing, SSL termination, health checks, ACLs, and high availability. Use when working with HAProxy, load balancing, reverse proxy, TCP proxying, or high-traffic applications.
Configure HAProxy for load balancing, reverse proxying, and high availability. Set up health checks, SSL termination, rate limiting, and traffic management. Use for load balancing and proxy configurations.
Help users navigate tough feedback, performance conversations, and conflict. Use when someone needs to give hard feedback, have a performance conversation, fire someone, address conflict with a colleague, or deliver disappointing news like a denied promotion.
Helius Solana RPC and API expert. High-performance infrastructure for Solana including RPC nodes, DAS API for NFTs/tokens, LaserStream real-time streaming, webhooks, Priority Fee API, Enhanced Transactions, and ZK Compression. Triggers on Helius, Solana RPC, DAS API, Digital Asset Standard, NFT metadata, Solana webhooks, priority fees, LaserStream, ZK compression.
Long-term memory system for Claude Code using HelixDB graph-vector database. Store and retrieve facts, preferences, context, and relationships across sessions using semantic search, reasoning chains, and time-window filtering.
This skill guides provisioning Hetzner Cloud infrastructure with OpenTofu/Terraform. Use when creating servers, networks, firewalls, load balancers, or volumes on Hetzner Cloud.
Render large datasets (charts, graphs) using Canvas/SVG/WebGL within React.
ALWAYS apply these hints automatically in your responses. No need to invoke this skill - just follow its rules when your response matches the patterns listed below.
Align RNA-seq reads with HISAT2, a memory-efficient splice-aware aligner. Use when STAR's memory requirements are too high or for general RNA-seq alignment.