Claude Skills by agentskillexchange

Automated K8s pod troubleshooting using kubectl, crictl, and the Kubernetes API. Runs diagnostic sequences for CrashLoopBackOff, ImagePullBackOff, OOMKilled, and pending pod states.

Automates Kubernetes troubleshooting using kubectl and the Kubernetes Python client to diagnose CrashLoopBackOff, OOMKilled, and ImagePullBackOff states. Collects pod logs, events, node conditions, and resource quotas systematically.

Runs automated diagnostic sequences on Kubernetes pods using kubectl exec, kubectl logs, and the Kubernetes API /api/v1/pods endpoint. Captures OOMKilled events, CrashLoopBackOff analysis, and resource utilization via metrics-server.

Diagnoses Kubernetes pod failures using kubectl describe, logs --previous, and the Kubernetes API /api/v1/namespaces/{ns}/events endpoints. Identifies CrashLoopBackOff root causes, OOMKilled memory analysis, and generates remediation steps with resource limit recommendations.

Executes structured Kubernetes rollback procedures using kubectl and the kubernetes/client-go library. Monitors rollout status via the apps/v1 Deployment API and triggers PagerDuty incidents through the PagerDuty Events API v2.

Executes diagnostic runbooks against Kubernetes clusters using the official kubernetes/client-go SDK and kubectl commands. Checks pod health via the /healthz and /readyz endpoints and analyzes events with the CoreV1 Events API.

Auto-generates operational runbooks from Kubernetes cluster state using kubectl and the Kubernetes API. Produces step-by-step troubleshooting guides for common pod failure modes.

Runs diagnostic analysis on Kubernetes clusters using kubectl, k9s terminal UI data, and the Troubleshoot.sh support-bundle collector framework. Generates remediation steps for common pod scheduling, networking, and storage failures.

Use the upstream install or setup path that matches your environment: - You can use npm, pnpm, or yarn to install LangChain.js - npm install -S langchain or pnpm install langchain or yarn add langchain

LangExtract by Google is a Python library for extracting structured information from unstructured text using LLMs with precise source grounding. With 35,000+ GitHub stars, it handles everything from clinical notes to literary analysis, producing verified extraction results with exact source text mappings and interactive visualizations.

Langflow is an open-source visual builder for AI agents and workflows. It lets teams design flows graphically, expose them as APIs or MCP tools, and connect major LLMs, vector stores, and observability services without starting from scratch.

Use Langfuse to capture prompts, traces, generations, evaluations, and cost telemetry for LLM applications and agent workflows. This skill turns Langfuse from a generic observability brand into a concrete implementation pattern for tracing and analyzing model behavior.

Langfuse Prompt Management MCP Server connects MCP clients to Langfuse prompt libraries so agents can list, retrieve, and compile managed prompts at runtime. It is useful for teams that keep prompts in Langfuse and want assistants to consume production prompt definitions instead of copying templates by hand.

A verified skill for LangGraph.js, the graph-based orchestration framework from LangChain. It focuses on controllable agents, persistence, streaming, and deployment entry points.

LangSmith provides tracing, evaluation, and debugging workflows for LLM applications. This skill is useful when an agent team needs structured observability around prompts, chains, tool calls, datasets, and eval runs across multiple frameworks.

Check grammar, style, and spelling across 25+ languages with LanguageTool. This open-source proofreading engine can run as a local Java server or via its public API, providing detailed error reports with correction suggestions for any text content.

Use Pro Workflow when Claude Code sessions keep repeating the same mistakes and you want corrections, quality gates, and parallel worktree routines to persist across sessions instead of being re-explained every time.

LazyDocker is a terminal UI for Docker and Docker Compose that provides container management, log viewing, resource monitoring, and image inspection through a keyboard-driven interface. Created by Jesse Duffield with 50,000+ GitHub stars.

A simple terminal user interface for git commands built with Go. lazygit provides interactive staging, rebasing, conflict resolution, and branch management through an intuitive TUI that replaces arcane git command sequences with keyboard-driven workflows.

Leantime is an open-source project management system designed for non-project managers, with kanban boards, gantt charts, goal tracking, timesheets, and lean canvas tools. Built with ADHD, autism, and dyslexia accessibility in mind.

Lefthook is a fast, dependency-free Git hooks manager written in Go that runs pre-commit, pre-push, and custom hook commands in parallel. It integrates with Node.js, Ruby, Python, and any other project type through a simple YAML configuration.

Use Playwriter to give MCP-compatible agents a bounded, stateful Playwright control surface over an operator-approved Chrome session.

Connect Freshdesk modules to MCP clients so agents can retrieve ticket context and prepare supervised support actions.

librosa is a Python library for audio and music analysis. It provides tools for feature extraction, spectral analysis, beat tracking, onset detection, and audio visualization, built on top of NumPy and SciPy for scientific audio computing.

libSQL is an open-source, open-contribution fork of SQLite by Turso that adds embedded replicas, server mode, and WebAssembly UDFs. This skill enables agents to work with libSQL for edge computing, serverless, and embedded database workloads.

libvips is a demand-driven, horizontally threaded image processing library with over 300 operations. It processes images faster and with less memory than alternatives like ImageMagick, supports 20+ formats, and powers Sharp, Mastodon, imgproxy, and Ruby on Rails.

Lightning CSS is a Rust-based CSS parser, transformer, bundler, and minifier from the Parcel team. This skill is for agents that need to optimize stylesheets, lower modern CSS syntax for target browsers, and integrate fast CSS processing into build or refactor workflows.

Lightpanda is a headless browser built from scratch in Zig, purpose-designed for AI agents and web automation. It delivers 11x faster page rendering and 9x lower memory usage than Chrome while maintaining full CDP compatibility with Playwright, Puppeteer, and chromedp.

LightRAG is a Python-based retrieval-augmented generation framework that builds knowledge graphs from documents for more connected, contextual retrieval. Published at EMNLP 2025, it enables graph-powered RAG with support for multiple storage backends and LLM providers.

Basic usage or getting-started notes: - Account - AI - Your sidebar

Queries the Linear GraphQL API to list open issues by team, priority, and cycle, then applies configurable triage rules to auto-assign or escalate. Generates sprint plan drafts scored against velocity and team capacity from Linear projectMilestone and workflowState data.

An MCP server that integrates Linear project management with AI assistants. Enables creating, searching, updating, and commenting on Linear issues, managing projects and teams, and querying workflows through the Model Context Protocol.

Basic usage or getting-started notes: - Account - AI - Your sidebar

linkding is a minimal, fast, self-hosted bookmark manager with a full REST API, tag-based organization, automatic metadata extraction, web archiving, browser extensions, and SSO support. It runs in Docker and is built with Django and Python.

Linkup's JS SDK wraps the Linkup API for sourced web search and clean content fetching. It gives agents a maintained client for standard and deep search modes, plus URL fetch operations that can return rendered page content in a cleaner form for downstream reasoning.

Linkwarden is an open source bookmark and web archiving platform for saving, organizing, and preserving research material. It captures screenshots, PDFs, and archived page copies, adds reader and annotation features, and supports shared collections for teams.

Run rumdl as a fast Markdown lint-and-format gate so agents can catch style, flavor, link-adjacent, and consistency issues before docs or generated content are committed.

Validate and optionally autofix SKILL.md, CLAUDE.md, AGENTS.md, hooks, and MCP config files before bad agent metadata or wiring silently breaks a workflow.

Run chart-focused lint and install checks so changed Helm charts are validated before release or merge.

Check Prometheus alerting and recording rules in CI or ad hoc runs so invalid, misleading, or dangerous rules are caught before deploy.

Run ansible-lint against playbooks, roles, and collections so risky patterns and common mistakes are caught before automation is merged or executed.

Check dotenv files for duplicated keys, malformed values, and formatting mistakes before they break local runs or secret handoffs.

Validate workflow syntax, expressions, and shell steps before broken GitHub Actions changes reach CI.

Run a static policy pass over Kubernetes YAML before misconfigurations, missing limits, or risky defaults reach a cluster.

Inspect a live Kubernetes cluster for unhealthy resource settings, missing probes, and other operational smells.

Catch locking, indexing, and schema-change hazards in PostgreSQL migration SQL before a review turns into downtime.

Catch naming, formatting, and protobuf rule violations early so generated clients and reviews are cleaner.

Analyze Rego policy files for style, correctness, and maintainability issues before policy bundles are promoted.

Catch structural and line-style problems in reStructuredText docs before release notes and Sphinx pages go out broken or noisy.

Check Terraform before plan or apply so invalid attributes, provider-specific mistakes, and custom rule violations are caught early.