Claude Skills by agentskillexchange

Turn YAML runbooks into auditable agent actions with validation, dry-runs, destructive-step approval, and optional MCP exposure.

Run schema checks from the shell or CI so malformed JSON, JSON5, or YAML inputs fail before they reach downstream tooling.

Uses kubeconform to validate Kubernetes manifests against versioned schemas before anything touches a cluster. The agent can review rendered Helm output, raw manifests, or PR diffs and return invalid resources, missing schemas, and strict-mode failures without requiring live cluster credentials.

Catch broken schemas, bad references, anti-patterns, and inconsistent formatting before a schema repo or contract bundle ships downstream.

Check that Python docstrings stay consistent with parameters, returns, and raised exceptions as code evolves.

Automates HashiCorp Vault secret rotation using the Vault HTTP API and dynamic secrets engines. Manages database credential leases, PKI certificate renewal, and AWS STS token rotation with zero-downtime rollover.

Manages secret lifecycle through the HashiCorp Vault HTTP API v1. Rotates database credentials via Vault dynamic secrets engine and syncs to Kubernetes via External Secrets Operator CRDs.

Verifies encryption workflows with HashiCorp Vault Transit endpoints like `/encrypt`, `/decrypt`, and `/rewrap`, plus key metadata inspection. Useful for agents reviewing whether application secrets handling is actually using envelope encryption correctly instead of assuming the library setup is safe.

vdirsyncer is a command-line tool for synchronizing calendars and addressbooks between servers and the local filesystem via CalDAV and CardDAV protocols. It bridges remote calendar and contact servers with local tools like khal and khard.

Vercel Agent Browser is a browser automation CLI built specifically for AI agents. It gives agents a fast, scriptable way to open pages, inspect accessibility snapshots, click elements, fill forms, capture screenshots, and manage browser state from the command line.

Use the upstream install or setup path that matches your environment: - npm i -g vercel - npm i -g @vercel/vc-native --force - npm i -g @vercel/vc-native-darwin-x64 --force - git clone https://github.com/vercel/vercel

Verdaccio is a lightweight, zero-config private npm proxy registry that caches packages from npmjs.org and hosts private packages. It supports npm, yarn, and pnpm with authentication, access control, and plugin extensibility for managing internal JavaScript packages.

Run deterministic governance checks and policy verification before agents get real autonomy, so risky tool use and weak runtime evidence are caught early.

Uses Goss to express the expected state of a machine or container, then validates that reality still matches the contract. Reach for it after provisioning, image builds, or config changes when an agent needs a fast pass or fail answer about service health and system drift.

Use Anthropic's webapp-testing skill to spin up one or more local servers, wait for them to become reachable, and run native Playwright checks against the rendered app. It is for agent-led verification and UI debugging of local web apps, not for listing Playwright as a generic browser framework.

Catch dead links in README files, docs folders, and content drafts before a broken reference ships to users.

Query OSS Rebuild attestations and rebuild metadata so an agent can verify whether a published package artifact matches a reproducible upstream rebuild.

Create terminal session recordings as GIFs, videos, or images using VHS (charmbracelet/vhs). Write declarative .tape scripts that define typed commands, delays, and settings — then render pixel-perfect terminal demos automatically.

Extract frames and short clips from videos. Core Capabilities Process audio and video files using ffmpeg for transcription and analysis Extract text, timestamps, and speaker metadata from media cont

Translates video subtitles across 100+ languages using DeepL API and Google Cloud Translation v3. Handles SRT/VTT timing preservation, character limit enforcement, and subtitle segmentation with Aegisub CLI.

Extracts embedded subtitles from video containers using FFmpeg's subtitle stream extraction, translates SRT/VTT files through DeepL API or Google Cloud Translation v3, and re-embeds localized subtitle tracks. Supports batch processing with language detection via langdetect and proper bidirectional text handling for RTL languages.

Vikunja is an open-source, self-hosted task management application written in Go with a Vue.js frontend. It provides lists, kanban boards, Gantt charts, and CalDAV sync for organizing personal and team projects with full data ownership.

Monitors and analyzes Vite HMR (Hot Module Replacement) update chains using the vite.config.ts plugin API and ws WebSocket events. Identifies slow module boundaries, circular dependency hot paths, and generates flamegraph-compatible output for Chrome DevTools Performance panel.

VitePress is a Vite and Vue powered static site generator focused on documentation, knowledge bases, and project sites. It gives agents a reliable way to scaffold, structure, and maintain docs sites with fast local previews and Markdown-first authoring.

Vitest is a blazing-fast unit testing framework powered by Vite. It provides native ESM support, TypeScript out of the box, and a Jest-compatible API for seamless migration of existing test suites.

vLLM is a fast and memory-efficient inference and serving engine for large language models. It uses PagedAttention for efficient memory management, supports continuous batching, and provides an OpenAI-compatible API server for production-grade LLM deployment.

Volta is a JavaScript toolchain manager written in Rust that pins Node.js, npm, and yarn versions per project. It provides fast, seamless tool switching without shims or shell hooks, ensuring every team member runs the exact same tool versions.

Perform offline speech recognition across 20+ languages with Vosk. Provides compact models, zero-latency streaming transcription, and bindings for Python, Node.js, Java, C#, and Go — all without cloud API dependencies.

Debugs VS Code extensions using the Debug Adapter Protocol (DAP) with breakpoint management and variable inspection. Integrates with VS Code Extension API for webview debugging and uses Chrome DevTools Protocol for renderer process analysis.

Scaffolds VS Code extensions using the vscode-extension API with TypeScript, including commands, webview panels, language servers via LSP, and custom tree view providers.

Vue.js is a progressive JavaScript framework for building user interfaces with an incrementally adoptable architecture, reactive data binding, and a rich ecosystem including Vue Router, Pinia, and Vite.

Wagtail is an open source CMS built on Django for teams that need structured content, flexible page models, and a polished editor experience. It works for traditional websites and headless builds, with a content API, image handling, search, and multi-site support baked in.

Wails is an open source framework for building desktop applications using Go for backend logic and standard web technologies (HTML, CSS, JavaScript) for the frontend. It compiles to a single native binary with no embedded browser overhead.

Uses the W&B Python SDK and Public API to stream live training metrics, system stats, and gradients from active runs. Alerts on metric regressions by querying run history via wandb.Api().runs() and posts summaries to Slack. Supports artifact versioning and lineage tracking.

Compiles and links WebAssembly components using the WASI Preview 2 Component Model, wasm-tools CLI for component composition, and wit-bindgen for generating host/guest bindings from WIT interface definitions.

Follow a Kubernetes workload live so an agent can explain why it is pending, failing, or not becoming ready.

watchexec is a standalone file-watching tool written in Rust that automatically executes commands when it detects file modifications. It respects .gitignore rules, coalesces rapid filesystem events, and works cross-platform without requiring any language runtime.

WeasyPrint is a Python library by Kozea/CourtBouillon that converts HTML and CSS into PDF documents. It implements a CSS layout engine designed specifically for pagination, supporting web standards for printing including page breaks, headers, page counters, and responsive layouts without relying on a browser engine like WebKit or Gecko.

Use the upstream install or setup path that matches your environment: - make build - make run-client

WebdriverIO is a next-generation browser and mobile automation test framework for Node.js. It supports WebDriver, WebDriver BiDi, and Appium protocols with built-in test runner, BDD/TDD frameworks, and cloud service integration for cross-browser and mobile testing.

Automates site, CMS, and publishing workflows with Webflow’s official JavaScript SDK for the Webflow Data API. Useful for agents that need to list sites, publish changes, manage CMS data, and authenticate with workspace tokens, site tokens, or OAuth.

Use the upstream install or setup path that matches your environment: - npm install stripe - yarn add stripe - npm install stripe@public-preview --save-exact - npm install stripe@<some-version>

Webhook is a lightweight, configurable tool written in Go that creates HTTP endpoints on your server to execute shell commands. It supports JSON and YAML hook definitions with rule-based triggering, request payload parsing, and data passthrough to scripts via command-line arguments or environment variables.

Analyzes webpack bundle composition using webpack-bundle-analyzer and source-map-explorer APIs. Identifies duplicate dependencies and suggests tree-shaking optimizations with specific import rewrites.

Whishper is an open source self-hosted web app for speech-to-text, translation, and subtitle workflows built around Whisper models. This skill covers running Whishper with Docker, handling uploads and transcripts, and wiring the output into broader automation flows.

Processes audio files from an S3 bucket using Whisper large-v3, splitting recordings into 30-second chunks with ffmpeg before transcription. Outputs timestamped SRT and VTT subtitle files plus plain-text transcripts, then uploads artifacts back to S3. Supports language auto-detection and translation to English.

Runs OpenAI Whisper models locally via whisper.cpp with GGML quantized weights for CPU-efficient transcription. Supports beam search decoding, VAD-based segmentation, and SRT/VTT subtitle output formats.

Streams audio from PulseAudio or ALSA devices into whisper.cpp for real-time speech-to-text with word-level timestamps. Outputs SRT/VTT subtitles and JSON transcripts simultaneously.

whisper.cpp is a lightweight, high-performance C/C++ port of OpenAI's Whisper automatic speech recognition model. It runs on CPU and GPU across all major platforms with zero dependencies and zero runtime memory allocations.

Enhances OpenAI Whisper transcription output with speaker diarization using pyannote.audio pipeline and speechbrain embeddings. Aligns word-level timestamps from whisper-timestamped with speaker segments for multi-speaker meeting transcript generation.