Skills for Claude Code, Codex and Cursor

roundup official github Pulls from GitHub, email, Teams and Slack, then drafts a status briefing in your own writing style. Useful when you owe the same update every week. GitHub Copilot 1,300installs roundup-setup official github Learns your communication style from answers and status examples, then configures personalized briefings. Use it before running roundup for draft updates. GitHub Copilot 1,300installs geofeed-tuner official Sid Mathur Validates and refines CSV IP geolocation feeds against RFC 8805 standards. Useful for network operators and cloud providers publishing geofeeds. GitHub Copilot 1,300installs daily-prep official github Builds an HTML prep file for the next workday from your Outlook calendar, open tasks, and workspace context. Useful before meetings and weekly planning. GitHub Copilot 1,300installs swiftui-liquid-glass official OpenAI This skill helps build and review SwiftUI Liquid Glass interfaces for iOS 26+. Use it when adopting the API or checking fallbacks, interaction, and design fit. CX Codex GP ChatGPT 121installs react19-test-patterns official github A migration reference for updating test files to work with React 19. Use it when replacing removed test utilities or revising StrictMode call-count assertions. GitHub Copilot 1,200installs freecad-scripts official github Writes FreeCAD Python scripts and macros: 3D geometry, parametric objects, PySide dialogs. Useful when you automate CAD work. GitHub Copilot 1,200installs file-conversion Seth Hobson Converts local media, documents, and data formats using tools already installed on your machine. Prevents uploading files to third-party APIs. Claude Code CX Codex Cursor 3,100installs before-you-build bin1874 This skill reviews product and feature risk before implementation. Use it to find the key assumption and the smallest useful validation step. Claude Code CX Codex Cursor 3,100installs ai-debt-detector Adit Jain This skill audits AI-generated code for missed failure paths, orphaned resources, fake dependencies, and architecture drift before a merge. Claude Code CX Codex Cursor 2,900installs react19-concurrent-patterns official github Preserves React 18 concurrent patterns during React 19 migrations and guides the adoption of use(), useOptimistic, and Actions. GitHub Copilot 1,100installs mcp-security-audit official github Audits MCP server configurations for exposed secrets, shell injection, mutable package references, and unapproved servers. Use it before changing .mcp.json. GitHub Copilot 1,100installs lsp-setup official github Installs a language server and configures LSP for Copilot CLI. Use it when you need code navigation such as go-to-definition or find-references. GitHub Copilot 1,100installs integrate-context-matic official github This skill finds third-party APIs and helps integrate their SDKs through the context-matic MCP server. Use it for external API work. GitHub Copilot 1,100installs arize-trace official arize Export Arize traces and spans by ID, then inspect them to investigate errors or LLM app behavior. Use it when you need to examine trace data already collected. GitHub Copilot 1,100installs arize-prompt-optimization official arize This skill analyzes prompts through production traces, evaluations, and annotations. Use it when you need better model responses or want to debug a system prompt. GitHub Copilot 1,100installs arize-instrumentation official arize This skill helps add Arize AX tracing to an LLM application. The agent inspects the project first, then proposes instrumentation for approval. GitHub Copilot 1,100installs arize-experiment official arize Runs Arize experiments with the ax CLI to benchmark models and export evaluation scores across dataset versions. GitHub Copilot 1,100installs arize-evaluator official arize Runs LLM-as-judge workflows in Arize for spans and experiments, with evaluator management, task control, column mapping, and continuous monitoring. GitHub Copilot 1,100installs arize-dataset official arize This skill manages Arize datasets and examples through ax. Use it for test sets, evaluation examples, and dataset exports. GitHub Copilot 1,100installs arize-annotation official arize Creates annotation schemas and review queues in Arize, then updates span labels through the Python SDK. Use it for human review workflows. GitHub Copilot 1,100installs arize-ai-provider-integration official arize Manage Arize AI integrations for language model providers: create connections, inspect their settings, and update or remove them. Use it when configuring models for Arize evaluators or other Arize features. GitHub Copilot 1,100installs agent-supply-chain official github Checks AI agent plugins, tools, and dependencies with SHA-256 manifests. Use it before promoting a plugin or auditing its files. GitHub Copilot 1,100installs visual-edit-precision Adit Jain Skill for targeted UI changes when you show elements on a screenshot or point them out in code. Edits only what you selected, without refactoring the entire component. Claude Code CX Codex Cursor 2,800installs session-guard Adit Jain session-guard monitors long sessions and rule drift. Use it for multi-step tasks or after a context compaction event. Claude Code CX Codex Cursor 2,800installs cloud-trace-querying official google This skill queries Cloud Trace spans, connects traces with Cloud Logging, and helps diagnose latency in Google Cloud services. Claude Code Gemini CLI CX Codex 835installs phoenix-tracing official [email protected] This skill guides OpenInference tracing for LLM apps with Phoenix. Use it to set up instrumentation, define custom spans, or prepare tracing for production. GitHub Copilot 1,000installs phoenix-evals official [email protected] Build and run evaluators for AI and LLM applications with Phoenix. Use it to investigate failures, evaluate RAG systems, and check model output. GitHub Copilot 1,000installs phoenix-cli official arize-ai A GitHub Copilot skill that drives the Phoenix CLI to pull traces, spans and sessions, then turns what it finds into a failure taxonomy for your LLM app. GitHub Copilot 1,000installs onboard-context-matic official github Interactive tour of the context-matic MCP server. It detects project languages, catalogs supported APIs, and demonstrates live model and endpoint lookups. GitHub Copilot 1,000installs pptx-visual-assets kimtth Places approved icons, images, SVGs, and diagrams onto editable PPTX decks with precise bounding boxes and verified rights. Claude Code CX Codex Cursor 2,600installs pptx-slide-specification kimtth A skill for writing and repairing coordinate-explicit JSON specs of slides, so an editable PPTX deck builds the same way every time. Claude Code CX Codex Cursor 2,600installs vision-sft Seth Hobson This skill configures supervised fine-tuning for vision-language models on image and text data. Use it when adapting a VLM to a new visual domain. Claude Code CX Codex Cursor 2,600installs quantized-export Seth Hobson Exports promoted checkpoints and LoRA adapters as FP8, AWQ, GGUF, or merged safetensors. Use it before deploying a model. Claude Code CX Codex Cursor 2,600installs preference-optimization Seth Hobson Selects and tunes model alignment methods: DPO, ORPO, KTO, or SimPO. Use it when training on preference pairs or binary thumbs-up feedback. Claude Code CX Codex Cursor 2,600installs lora-qlora-recipes Seth Hobson This skill configures LoRA and QLoRA supervised fine-tuning, from target modules to rank and learning rate. Use it when reviewing an adapter training setup. Claude Code CX Codex Cursor 2,600installs grpo-rlvr-training Seth Hobson Configures GRPO and RLVR training pipelines for tasks with verifiable outcomes. Useful when evaluating models with code execution, unit tests, or strict schemas. Claude Code CX Codex Cursor 2,600installs finetuning-method-selection Seth Hobson This skill decides whether fine-tuning is needed and routes the task to a method based on its data and goal. Use it before a training run. Claude Code CX Codex Cursor 2,600installs eval-harness-first Seth Hobson Builds the evaluation harness before fine-tuning with goldens, graders, judge calibration, and a base-model baseline. Useful for tracking regressions. Claude Code CX Codex Cursor 2,600installs dataset-curation Seth Hobson This skill formats and checks datasets for model fine-tuning. Use it to prepare data for SFT or preference training before a run. Claude Code CX Codex Cursor 2,600installs