Claude Skills by agentskillexchange

Run SWE-agent against a repository issue so a language model can inspect files, execute commands and tests, and produce a patch for human review.

Decompose goals into task DAGs, delegate work to agents and tools, and inspect execution traces.

Use node-ical when an agent is handed a raw .ics file or subscription URL and needs normalized event objects, recurrence-aware dates, and timezone-safe fields it can reason over. The skill stops at parsing and structuring calendar data, not acting as a full calendar product.

Read a Lark Minutes transcript, extract explicit and implied follow-ups, then let the agent execute selected tasks instead of leaving them as notes.

Run named steps directly from Markdown runbooks so operational docs stay executable instead of drifting into stale reference text.

Generate a shell-ready CLI from an MCP server, OpenAPI spec, or GraphQL endpoint so an agent can discover commands and call tools immediately without hand-written wrappers.

Define repeatable extraction pipelines that pull fields from large document collections, normalize outputs, and audit failures across the corpus.

Ingest code, docs, PDFs, images, and video from local folders into a searchable knowledge graph so agents can follow entities and relationships instead of only raw text.

Convert messy bug notes, error logs, voice dictation, and screenshots into crisp GitHub issue reports with clear repro steps, impact, and evidence.

Read a Notion spec, extract requirements and ambiguities, then create a linked implementation plan, task breakdown, and progress-tracking structure.

Use pgBadger when an agent needs to convert raw PostgreSQL logs into readable evidence about slow queries, errors, and workload hotspots after an incident.

Generate PRDs, implementation plans, validation loops, issue investigations, and autonomous fix cycles inside Claude Code before coding starts.

Feed an agent your docs, links, code, or rough process notes and it generates, validates, installs, and optionally shares a reusable SKILL.md-based workflow across supported agent tools.

Parse Windows event logs into fast timelines and detection-rich outputs so agents can triage suspicious host activity, search for known patterns, and hand investigators reviewable artifacts.

Twenty is a modern open-source CRM built to replace Salesforce, with customizable objects, workflow automation, email and calendar integration, and a GraphQL API. It offers kanban, table, and calendar views with fine-grained permission controls and self-hosting support.

Node.js, npm

Sends and receives SMS/MMS messages via Twilio REST API with webhook handler generation. Supports message scheduling, delivery status callbacks, and Twilio Verify for OTP flows.

Builds intelligent voice routing flows using the Twilio Programmable Voice API. Generates TwiML responses with , , and verbs, and manages call recordings via the Recordings REST resource.

Connects to Twilio REST API via the twilio-node SDK for programmable messaging and voice. Sends SMS with client.messages.create(), builds IVR flows using TwiML VoiceResponse, and processes delivery webhooks for message status tracking and conversation threading.

Twirp is a protobuf-based RPC framework from Twitch that generates Go servers and clients with a simple HTTP transport. It suits agent workflows that need to scaffold service definitions, generate code with protoc plugins, and wire strongly typed RPC endpoints into Go services.

Polls the X API v2 trending topics endpoint every 15 minutes and compares against a keyword watchlist stored in Redis. When a trend matches, fetches top tweets by engagement and drafts a summarizing thread via OpenAI Chat Completions. Publishes the thread via X API v2 with reply chaining, respecting OAuth 2.0 PKCE rate limits.

ty is an extremely fast Python type checker and language server written in Rust by Astral, the creators of Ruff and uv. It delivers 10-100x faster type checking than mypy or Pyright with comprehensive diagnostics, incremental analysis, and first-class editor integrations.

Resolves TypeScript symbols and generates API documentation using the TypeDoc compiler API and ts-morph for AST manipulation. Creates interlinked reference pages with declaration merging support and module augmentation tracking.

TypeDoc is the standard documentation generator for TypeScript projects. It reads TypeScript source code and JSDoc comments to produce structured HTML documentation or JSON models. With 8,000+ GitHub stars and widespread npm adoption, it powers API reference generation for thousands of TypeScript libraries.

Performs automated TypeScript refactoring using ts-morph and the TypeScript Compiler API. Handles rename operations, extract-function, and dead code elimination across large codebases.

Typesense is an open-source, typo-tolerant search engine built in C++ for building fast, relevant search experiences. It serves as a self-hostable alternative to Algolia with support for vector search, geo-search, and faceted filtering.

A blazing-fast source code spell checker written in Rust that finds and corrects typos across entire codebases. Designed to run on monorepos with minimal false positives, typos integrates into CI/CD pipelines, pre-commit hooks, and editor workflows.

Typst is a modern markup-based typesetting system designed to replace LaTeX with a faster, easier-to-learn alternative. It features built-in markup, a scripting system, math typesetting, bibliography management, and incremental compilation for near-instant builds.

Umami is a modern, privacy-focused, open-source web analytics platform and a self-hostable alternative to Google Analytics, Mixpanel, and Amplitude. It collects website traffic data without cookies and is fully GDPR compliant.

Render a Helm chart locally and assert on the generated Kubernetes objects before a broken template makes it to a cluster.

Unkey is an open-source developer platform for managing API keys, rate limiting, and usage analytics. It provides a fast, globally distributed key verification system that integrates into any API with minimal code changes.

Unlighthouse runs Google Lighthouse across an entire site instead of just a single page. This skill gives agents a repeatable way to crawl URLs, surface SEO and accessibility issues, and return prioritized audit findings for content and technical optimization work.

Unstructured is an open source document processing library that converts PDFs, HTML, Office files, emails, and other formats into structured data for downstream AI workflows. It is a practical intake layer for extraction, chunking, and preprocessing before embeddings, search, or agent use.

Unstructured is an open source document ETL toolkit for converting PDFs, HTML, emails, and office files into structured data. This skill covers how to use the real Unstructured project for partitioning documents, normalizing content, and feeding downstream agent or RAG pipelines.

Unstructured is an open-source library for ingesting and partitioning PDFs, HTML, Office documents, emails, and other unstructured inputs into structured elements and metadata. It is commonly used as a preprocessing layer for RAG, search, extraction, and downstream AI pipelines.

Use GitHub Next's update-docs workflow when code changes should trigger documentation maintenance instead of waiting for humans to remember it later. The agent analyzes what changed, generates the missing docs updates, and opens a reviewable PR rather than silently rewriting the docs in place.

An ASE skill built around Upptime, the open source uptime monitor and status page system powered by GitHub Actions, Issues, and Pages. It is a strong fit when an agent needs lightweight endpoint monitoring, incident issue tracking, and a public or internal status site without maintaining a separate monitoring server.

Upscayl is a free, open-source AI image upscaler for Linux, macOS, and Windows. It uses Real-ESRGAN models with Vulkan GPU acceleration to enhance low-resolution images, supporting batch processing, custom models, and multiple output formats.

An official MCP server from Upstash that lets AI agents manage Redis databases, QStash message queues, and Vector stores through natural language. Supports database creation, key operations, backups, and throughput analytics via the Model Context Protocol.

Uptime Kuma is an open source uptime monitor for HTTP, TCP, ping, DNS, Docker, and keyword checks. It gives agents a concrete way to create, update, and review monitors, incidents, notifications, and public status pages from a self-hosted monitoring stack.

Interfaces with the Uptime Kuma Socket.IO API to monitor service health checks. Syncs status page data to Statuspage.io via Atlassian REST API and triggers incident workflows in Rootly.

Manages bulk uptime monitoring via the Uptime Robot API v2. Creates HTTP, keyword, and port monitors with alert contacts, maintenance windows, and status page synchronization.

Integrates with the Uptime Robot API to monitor status page changes and push webhook alerts to Slack or PagerDuty. Uses the UptimeRobot getMonitors endpoint to detect downtime transitions.

Start with cheap static fetches, escalate to a browser only when needed, validate findings, and turn the result into a production-ready scraping approach.

Build a supervised RAG context layer with RAGFlow so agents can index documents, retrieve grounded context, and answer with traceable source support.

usql is a universal command-line interface for SQL databases including PostgreSQL, MySQL, SQLite, Oracle, SQL Server, and dozens more. It provides a consistent psql-like experience with syntax highlighting, tab completion, and cross-database copying.

uv is an extremely fast Python package and project manager written in Rust by Astral (creators of Ruff). It replaces pip, pip-tools, pipx, poetry, pyenv, virtualenv, and twine with a single tool that resolves and installs packages 10-100x faster.

Vale is an open-source, markup-aware prose linter that enforces editorial style guides on technical documentation. This skill enables agents to run Vale against Markdown, AsciiDoc, reStructuredText, and HTML to catch style, grammar, and terminology issues.

Use check-jsonschema when an agent needs to catch broken GitHub Actions, Renovate, Azure Pipelines, and other schema-backed config files before they hit CI. The agent picks the right schema hook, validates the changed files, and reports the exact key or structure that drifted from the contract.

Catch CloudFormation schema, region, and intrinsic-function mistakes before a stack update fails in review or deployment.