notes
Search, browse, create, and delete Apple Notes. Use when user asks about notes, wants to find something in notes, create a new note, or delete notes.
发现 生活与效率 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Search, browse, create, and delete Apple Notes. Use when user asks about notes, wants to find something in notes, create a new note, or delete notes.
Enforce Laravel Best Practices when generating code, reviewing code, and writing tests (SRP, skinny controllers, FormRequests, service/action classes, DRY, Eloquent/Collections, Blade query avoidance, eager loa...
Fine-tune LLMs 2x faster with 80% less memory using Unsloth. Use when the user wants to fine-tune models like Llama, Mistral, Phi, or Gemma. Handles model loading, LoRA configuration, training, and model export...
Train and use SuperBPE tokenizers for 20-33% token reduction across any project. Covers training, optimization, validation, and integration with any LLM framework. Use when you need efficient tokenization, want...
Analyze, compare, and work with tokenizers using Unsloth tools. Compare different tokenizers, analyze token efficiency, and integrate with Unsloth models. For SuperBPE training, see the 'superbpe' skill.
Work with the Unsloth MCP Server codebase. Use when maintaining, extending, or debugging this specific MCP server implementation. Provides architecture knowledge, code patterns, and development workflows.
Advanced techniques for optimizing LLM fine-tuning. Covers learning rates, LoRA configuration, batch sizes, gradient strategies, hyperparameter tuning, and monitoring. Use when fine-tuning models for best perfo...
Export and deploy fine-tuned models to production. Covers GGUF/Ollama, vLLM, HuggingFace Hub, Docker, quantization, and platform selection. Use after fine-tuning when you need to deploy models efficiently.
Self-learning workflow system that tracks what works best for your use cases. Records experiment results, suggests optimizations, creates custom templates, and builds a personal knowledge base. Use to learn fro...
Create, clean, and optimize datasets for LLM fine-tuning. Covers formats (Alpaca, ShareGPT, ChatML), synthetic data generation, quality assessment, and augmentation. Use when preparing data for training.
A minimal example SKILL for OpenCode. When executed it simply returns the string "Hello, OpenCode!". This can be used to test SKILL loading and execution.
Guide users through creating Agent Skills for your coding agent. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
Process Open Office files including Writer (.odt), Calc (.ods), Impress (.odp), and Draw (.odg) documents. Use when working with LibreOffice or Apache OpenOffice files, creating, editing, converting, or analyzi...
Reviews technical specifications for completeness, feasibility, and production readiness. Validates architecture, APIs, security, and operational concerns. Use when reviewing tech specs before implementation or...
Create production-ready Vendure plugins with @VendurePlugin decorator, NestJS dependency injection, lifecycle hooks, and configuration patterns. Use when developing new Vendure plugins or extending existing one...
⚠️ MANDATORY - Automatically invoked by safe-commit. Executes comprehensive testing suite including unit tests (minimum 90% coverage), integration tests, and E2E tests (100% pass required). Reports coverage and...
Creates and manages git branches with enforced mriley/ prefix naming convention. Validates branch names, switches branches safely, and handles branch creation with proper base branch selection.
Create new Claude Code skills following best practices including optimal descriptions, progressive disclosure, proper structure, and testing guidelines. Use when creating new skills or skill templates.
Build delivery and fulfillment plugins for Vendure with idempotency, capacity management, timezone handling, and N+1 prevention. Covers ShippingCalculator, FulfillmentHandler, and slot reservation patterns. Use...
Conduct comprehensive Helm chart security and quality audits with automated checks for security contexts, resource limits, and production readiness. Use when reviewing pull requests with Helm chart changes, con...
Review Go code using Casbin authorization for security issues, model correctness, policy design, and common anti-patterns. Use when reviewing PRs with Casbin code or auditing authorization implementations.
⚠️ MANDATORY - YOU MUST invoke this skill at the start of EVERY task. Reviews git history, status, and context before starting any work. Runs parallel git commands to understand current state, recent changes, a...
Detects N+1 query problems in GraphQL resolvers and TypeScript code. Checks for missing DataLoader usage, sequential database queries in loops, and resolver batching opportunities. Use before committing GraphQL...
Bridges approved PRDs to implementation by mapping user stories to tasks with skill assignments, effort estimates, and progress tracking. Use after PRD approval to create actionable implementation plan.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。