Loading...
Loading...
Found 219 Skills
Persistent, budgeted, DAG-ordered runner for parallel `claude -p` or `codex exec` workers in tmux. Use ONLY when you need persistence across sessions, per-worker budget caps, dependency ordering, or mixed models/providers per worker. For ad-hoc parallel sub-agents inside a live conversation, use Claude Code's built-in Agent tool instead.
Sets up a Ralph autonomous development loop for any project. First generates a full PRD from the user's description, then derives a task plan from it. Wraps Claude Code in an intelligent while-true loop with circuit breakers, exit detection, session persistence, and progress tracking. Use when you want Claude to autonomously work through a task list until done.
Handles MMKV storage operations and data persistence patterns with encryption. Use when implementing data persistence, caching, or user preferences in Fitness Tracker App.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Use this skill when a vanilla static SPA scaffold exists and needs to feel like a polished product — progress persistence, sidebar + scrollspy navigation, dark/light theme, content zoom, responsive (mobile sidebar overlay), keyboard nav, fade-in entrances, toast notifications, iframe modal viewers, quiz scoring with section back-links. Triggers on phrases like "加進度勾選", "響應式", "暗色模式", "縮放", "scrollspy", "sidebar 收合", "手機版", "RWD", "dark mode", "progress tracking", "quiz UX", "interactive polish". Always invoke AFTER `static-spa-conversion` (renders working), as a standalone enhancement layer.
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
Guide for creating MCP servers that enhance LLM reasoning through structured processes, persistence, and workflow guidance. Use when building MCP servers for structured thinking, journaling, memory systems, or other cognitive enhancement patterns.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Xcode project setup, SwiftData persistence, testing, debugging, profiling, and app distribution for iOS development. This skill should be used when setting up Xcode projects, working with SwiftData models and queries, writing Swift tests, debugging with breakpoints, profiling with Instruments, distributing via TestFlight, or building for visionOS and ML features.
Expert blueprint for save/load systems using JSON/binary serialization, PERSIST group pattern, versioning, and migration. Covers player progress, settings, game state persistence, and error recovery. Use when implementing save systems OR data persistence. Keywords save, load, JSON, FileAccess, user://, serialization, version migration, PERSIST group.
Expert blueprint for scene loading, transitions, async (background) loading, instance management, and caching. Covers fade transitions, loading screens, dynamic spawning, and scene persistence. Use when implementing level changes OR dynamic content loading. Keywords scene, loading, transition, async, ResourceLoader, change_scene, preload, PackedScene, fade.
Help developers build with Chainlink Data Streams, including credentials guidance, report decoding, REST and WebSocket report retrieval with official Go/Rust/TypeScript SDKs, High Availability streaming, on-chain report verification, real-time frontend displays, report schema guidance, SQLite persistence, and timestamp lookback. Use this skill whenever the user mentions Chainlink Data Streams, Streams Direct, Data Streams reports, report schemas, report decoding, data-streams-sdk, or real-time low-latency market data from Chainlink.