Skills

A science skill from Google DeepMind's collection that enables AI agents to search biomedical literature via the bioRxiv preprint server, part of a broader suite covering genomics, structural biology, and cheminformatics research.

PyTorch deep learning best practices covering device-agnostic code, reproducibility setup, model architecture patterns, training/validation loops with mixed precision, efficient data pipelines, checkpointing, gradient checkpointing, and torch.compile optimization.

A comprehensive session wrap-up skill with multi-agent analysis that runs parallel agents for documentation updates, automation scouting, learning extraction, and follow-up suggestions before ending a coding session.

A .NET diagnostic skill for performance investigations, providing AI agents with guidance on profiling, tracing, and analyzing .NET application performance issues using dotnet-diag tools.

A skill that transforms Claude Code into a fully autonomous agent system with persistent memory, scheduled cron operations, computer use, task queuing, and remote dispatch, replacing standalone agent frameworks like Hermes or AutoGPT.

The official AI agent skills collection for Aliyun Model Studio (DashScope), offering first-party skills paired with the bailian-cli tool for chat, multimodal, image/video, speech, and RAG capabilities, alongside curated third-party skills for code development, design, documentation, and testing.

A skill for building fully automated, AI-powered data collection agents that scrape public sources on a schedule, enrich results with Gemini Flash LLM, store to Notion/Sheets/Supabase, and learn from user feedback -- all running free on GitHub Actions.

A guide skill for navigating Everything Claude Code (ECC), helping users find and choose the right agents, skills, commands, hooks, rules, and install profiles by reading the live repository surface rather than relying on stale documentation.

App Store Connect CLI skill for localizing app metadata. Automates translation and management of App Store listing content across multiple languages.

Curated collection of 59+ Claude Skills for terminal, server, Kubernetes, DevOps, and cloud computing workflows, organized by category with comprehensive command references.

GitHub Copilot extensions for VS Code, Visual Studio, and Claude Code that streamline Azure development, enabling questions about Azure services and management tasks from within the IDE.

A reference HLSL shader implementation of the Slug font rendering algorithm for GPU-accelerated vector font rendering at arbitrary scales using quadratic Bezier curves, without texture atlases or pre-rasterization.

from starchild-ai-agent/official-skills

Part of a collection of auto-generated agent skills derived from GitHub's trending open-source projects by ara.so, providing installable skills for AI coding assistants via the skills.sh registry.

The final acceptance stage of the CodeStable feature workflow that verifies implementation against the design document, updates architecture and requirement docs, closes roadmap items, and produces an acceptance report as the closure record.

Stage 1 of the codestable feature workflow that drafts a comprehensive design document (covering architecture, interface contracts, implementation hints, and test design) plus an action checklist, which serve as the single source of truth for the subsequent implementation and acceptance stages.

A social reader skill from the Finance Skills collection that reads and processes Discord messages for financial analysis, part of a broader suite of market analysis, data provider, and social media reading tools.

An ECC skill providing Kotlin language idioms and best practices, part of the ECC harness-native operator system that supports 12+ language ecosystems including Kotlin/Android/KMP with dedicated reviewers and build resolvers.

Provides React Hook Form integration patterns with Zod schema validation for type-safe, performant form handling

Generates SR&ED (Scientific Research and Experimental Development) work summaries for Sentry employees, part of the Sentry agent skills collection.

ECC skill providing Django patterns, models, and views best practices for AI agent-assisted Python web development. Part of a comprehensive framework coverage including Django patterns, security, TDD, and verification loops across 12 language ecosystems.

Official Hugging Face skill for training **vision models on HF Jobs cloud GPUs** — fine-tunes object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm MobileNetV3/MobileViT/ResNet/ViT/DINOv3 + Transformers classifiers), and SAM/SAM2 segmentation; covers COCO dataset prep (xywh/xyxy auto-detect), Albumentations augmentation, mAP/mAR + accuracy metrics, DiceCE loss, Trackio monitoring, Hub persistence, and mandatory dataset validation before GPU training.

Provides production-tested Prisma ORM patterns for TypeScript backends, covering schema design, query optimization, transactions, pagination, and critical traps like updateMany returning count instead of records, $transaction timeouts, and serverless connection exhaustion.

A collection of Claude Code skills for tasks like code review, security analysis, and development best practices, each providing structured expert guidance.

An audit-first skill for inventorying and classifying all live automations (cron jobs, GitHub Actions, hooks, MCP servers, connectors) by their operational state, identifying overlaps and breakages, and recommending keep/merge/cut/fix-next actions.

A CodeStable skill that routes new feature development through a four-stage workflow — brainstorm, design, implementation, and acceptance — inserting a design document between requirements and code to prevent scope drift and leave behind a traceable record.

Part of the ECC harness-native operator system providing Redis caching and data structure patterns for AI agent-assisted backend development. Works across Claude Code, Codex, Cursor, Gemini, and other AI coding harnesses with 232 production-ready skills spanning 12 language ecosystems.

Provides advanced backend engineering expertise with comprehensive architectural guidance and system design recommendations for enterprise-level infrastructure.

A collection of AI agent skills for scientific research tasks spanning genomics, structural biology, cheminformatics, and literature search, designed to extend AI agent capabilities for specialized scientific workflows with Google Antigravity integration.

Stage 2 of the codestable feature workflow that translates an approved design document into code by following the checklist step-by-step, enforcing three core disciplines: write the minimum necessary code, only modify intended files, and never make decisions not covered by the design document.