Skills

Agent skills for OCI (Oracle Cloud Infrastructure) monitoring and observability covering metric namespaces, alarm configuration, log collection, and Terraform Landing Zone integration.

Prevents the default "GPT UI" aesthetic (soft gradients, floating panels, oversized radii, dramatic shadows, hero sections in dashboards) when generating HTML/CSS/React/Vue/Svelte — pushes for clean, human-designed internal business tool interfaces.

A skill that captures architectural decisions made during coding sessions as structured ADR documents, detecting decision moments in conversation and recording context, alternatives considered, and consequences using Michael Nygard's lightweight ADR format.

A Claude Code skill for multi-platform e-commerce competitor analysis on Amazon (Temu and Shopee planned). Performs batch product analysis with AI-driven insights covering copywriting strategy, visual assets, review sentiment, and market positioning, with output to Google Sheets and Markdown.

from yuan1z0825/nature-skills

Enforces automated code reviews as a mandatory guardrail before commits and deploys, supporting Claude, OpenAI Codex, and Google Gemini review engines with single, dual, or triple engine configurations.

Generates professional, data-driven slide decks with persuasive storytelling, structured content, and speaker notes across multiple presentation formats.

A collection of agent skills for financial analysis and trading, including stock analysis, earnings previews, SaaS valuation, options payoff charts, social sentiment readers, and startup analysis tools powered by yfinance.

Official NVIDIA-verified agent skills that teach AI agents how to use NVIDIA software optimally, including CUDA-X libraries, AI Blueprints, and platform tools. Skills are portable instruction sets maintained and synced from NVIDIA product repos.

Part of the Pika Creative Suite, which equips AI agents with a full creative studio including 58 atomic tools for image, video, music, and editing via MCP, along with 9 curated /pika:* workflow skills for tasks like generating podcasts and product videos.

Part of the Chrome DevTools MCP server, this skill helps AI coding agents debug memory leaks in Chrome by recording traces and extracting actionable performance insights via DevTools Protocol.

Agent skills for Tencent CloudBase development, covering AI model integration, authentication, database operations, and cloud function deployment extracted from the CloudBase AI ToolKit.

A Claude Code skill for 6-phase systematic literature surveys with frontier search, deep dive analysis, code review, synthesis, and report compilation.

Run Ruff checks with optional scope and rule overrides (`--select`, `--ignore`, `--extend-select/ignore`), apply safe then unsafe autofixes iteratively, review each diff, and resolve remaining findings with targeted edits or user decisions. Auto-detects Ruff runner (`uv run ruff`, `ruff`, `python -m ruff`, `pipx run ruff`) and applies `# noqa` only when justified.

Builds robust, performant web services in Rust with async handling, type-safe routing, middleware composition, and secure state management.

A skill from Anthropic's official Claude Code plugins directory, which serves as a curated marketplace for high-quality plugins including both Anthropic-developed internal plugins and vetted third-party external plugins.

Part of the Pika Creative Suite, which gives AI agents access to 58 atomic creative tools (image, video, music, editing) via MCP and 9 curated /pika:* workflow skills, all sharing a single Pika Agent identity and credit pool across Claude Code, Cursor, Codex, and more.

Guide for getting started with Firebase, covering Node.js prerequisites, Firebase CLI installation, authentication, project creation, and initialization of Firebase services like Firestore, Functions, and Hosting.

Pipeline that designs Azure infrastructure from natural language or analyses existing resources, then generates interactive HTML diagrams (605+ official Azure icons via bundled Python — no `pip install`) and ships Bicep IaC. Routes between Path A (Phase 1 advisor → Phase 2 Bicep generator → Phase 3 reviewer → Phase 4 validate/what-if/deploy) and Path B (Phase 0 scanner → modification dialog → Phase 1+) and auto-detects user language to localise all output.

Part of Binance Skills Hub, an open skills marketplace giving AI agents native access to crypto operations including token search, trade execution, wallet tracking, signal monitoring, and DeFi protocol interaction through natural language.

Part of a modular AI plugin system with 150+ skills and 45+ agents across 7+ languages including Java, TypeScript, Python, PHP, and AWS. Uses Specifications-Driven Development (SDD) workflow with constitution, specification, task generation, implementation, and QA phases.

from google/skills

A google search console skill from Marketing Skills, a collection of AI-powered marketing skills for content creation, SEO, social media, and campaign management.

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.

Comprehensive Python testing guidance using pytest, covering TDD methodology, fixtures with scopes, parametrization, mocking/patching, async testing, exception testing, and coverage requirements with 80%+ targets.

An official NVIDIA-verified agent skill from NVIDIA's skill catalog that teaches AI agents how to optimally use NVIDIA software, including CUDA-X libraries, AI Blueprints, and platform tools. Skills are maintained in their respective product repos and synced daily via an automated pipeline.

from vercel/vercel-plugin

Teaches AI agents how to connect to and operate Dropbox via the Membrane platform, enabling file storage and sharing actions through natural language without manual API key handling. Part of Membrane's library of 3,000+ app integration skills.

Dynatrace observability skill that provides AI agents with domain knowledge for querying and analyzing Kubernetes clusters, pods, nodes, workloads, labels, and resource relationships through Dynatrace.

Actionable GDPR-engineering reference inspired by CNIL developer guidance and GDPR Articles 5, 25, 32, 33, 35 — covers the core principles, privacy-by-design defaults, retention TTLs, DPIAs, RoPA updates, DSR workflows, encryption/anonymization, incident response, and cloud/CI-CD patterns. Use it when designing APIs, data models, auth, retention jobs, or reviewing PRs for privacy compliance.