Shape agent capabilities into your workflow.

Work with Chef Infra Server and Chef Automate without repeatedly looking up knife syntax. The skill covers node and cookbook operations, bootstrapping, remote execution, monitoring, and failure diagnosis, but it expects Chef Workstation, a configured knife profile, and network access to the target Chef environment.

Pull web analytics from Yandex Metrica through Claude Code, including counter details, goals, preset or custom reports, and multipart raw-log exports. The included scripts cover the management, reporting, and Logs APIs and require a Yandex OAuth token together with curl, jq, and Python.

Operate Yandex Direct from Claude Code by listing or changing campaigns, ads, and keywords, adjusting bid-related resources, and requesting performance reports. The scripts support production and sandbox environments, agency accounts, and asynchronous report polling, and they require a Yandex OAuth token with Direct API access.

Ask an AI coding agent to create or manage Yandex Cloud resources and receive commands grounded in service-specific yc CLI references. Coverage includes compute, networking, managed databases, Kubernetes, serverless, storage, load balancing, IAM, observability, and other major services across multiple agent clients.

skill-stocktake reviews an installed Claude skill library in one context and assigns Keep, Improve, Update, Retire, or Merge recommendations based on quality, overlap, freshness, and optional usage history. It supports full and changed-only audits, then asks for confirmation one item at a time before consolidation; usage counts require the bundled Claude Code hook.

Build a taste profile from recently played tracks, heavy rotation, library data, ratings, recommendations, and Replay, then create or refresh playlists for moods, activities, deep cuts, trends, and discovery. The data and cache stay local, but MusicKit access requires an Apple Developer account, an active Apple Music subscription, and both developer and user tokens.

Use this Claude Code skill to prune low-value experience and rebuild a scattered technical background into a clearer architecture, governance, or consulting narrative. It can review LinkedIn headlines, About sections, and resumes, then produce English and localized positioning for engineers targeting founders, recruiters, or B2B clients.

This Claude skill role-plays a professional bartender at an elite Louisville club between 1910 and 1915. It answers questions about period cocktails, spirits, service, and club culture using research drawn from historical bartending manuals. The persona deliberately stays within its pre-Prohibition time frame, making it useful for historically themed research or conversation.

Bloom's Quiz Builder guides teachers from an uploaded reading or chapter to a validated question set spanning all six Bloom's Taxonomy levels. It identifies testable themes, collects preferences such as grade level and question type, and asks for approval as questions are built. The finished set can be exported as JSON for editing, review, or import into a learning management system.

Nano Banana 2 Skill connects Claude Code to Google's Gemini 3.1 Flash Image model for text-to-image generation, natural-language editing, and multi-image composition. It supports resolution and aspect-ratio controls, iterative refinement, search-grounded prompts, and up to 14 reference images. Users must provide a Gemini API key and install the included Python dependencies.

OpenClaw Crypto AI is a single-file Claude Skill that generates a Binance-themed React chatbot for crypto education, trading-risk guidance, DeFi, or portfolio topics. It can produce Chinese or English interfaces and returns a renderable JSX artifact with session conversation memory. The generated app relies on the Anthropic API, and live market information requires separately enabling web search.

Java JaCoCo Coverage Backfill standardizes a repeatable workflow for Maven and Gradle projects: generate JaCoCo XML, rank classes by branch coverage, add targeted tests, and compare before-and-after snapshots. It supports single- and multi-module repositories and reports class, method, line, and branch metrics. The project must already generate JaCoCo XML, and the analysis scripts require Python 3.9 or later.

UI/UX Reviewer is a Claude Code plugin for auditing screens and components against Nielsen's ten heuristics, psychology-based UX laws, Apple Human Interface Guidelines, and WCAG 2.2. It organizes usability and accessibility findings by severity and provides actionable fixes. The bundled reference set is especially relevant to mobile and React Native work, while the review prompts can also be applied to general interface code.

This Claude skill guides a project through three developer-controlled stages: a non-executable `.bssh` blueprint, a working Bash prototype that you run and approve, and conversion into the chosen production language. Each gate requires explicit approval, reducing the chance that language-specific code is produced before the underlying logic has been tested. The final output can be a single file or a structured project.

This Claude Code skill turns a Playwright run into an MP4 suitable for bug tickets, QA evidence, or demonstrations. It confirms the output location, records the browser in headed mode, detects a system ffmpeg installation or falls back to `ffmpeg-static`, and converts Playwright's WebM output to H.264. Existing files are preserved through incremented names, and the final response includes a local link to the output folder. Node.js 18+ and Playwright are required.

Point this Claude Code skill at an OpenAPI URL, local file, or pasted YAML or JSON to generate request and response types, a Fetch- or Axios-based HTTP client, and endpoint functions grouped by tags. It can optionally create React Query or SWR hooks and includes support for authentication, retries, interceptors, and typed errors. The generated code follows the project's TypeScript and formatting settings and is checked with `tsc --noEmit`.

This Claude Code skill measures typography, colors, spacing, borders, shadows, and interactive states in a live or staging site through Chrome DevTools, then compares them with Figma, a PDF brandbook, a reference site, screenshots, or manual specifications. It cross-checks suspected deviations, filters false positives, and produces a structured Excel or Markdown report with severity and current versus expected values. A target URL, at least one design reference, and the Chrome MCP extension are required.

Meridian stores milestones, phases, plans, decisions, and checkpoints in a local SQLite state machine so Claude Code can resume deterministically after a session reset. It executes plans in scoped subagents, supports parallel waves, and applies regression checks, requirement coverage, stub detection, repair strategies, and two-stage review. Optional integrations can sync a kanban board or dispatch work to remote agents. Setup requires Python 3.11+, uv, Git, and Claude Code with skills support.