Skill UI

Analyze a repository to generate recommended Claude Code settings.json permissions for read-only commands. Detects tech stack, build tools, and monorepo structure to build an evidence-based allow list. Use when setting up a new project, auditing existing settings, or determining which bash commands to allow.

This skill executes the OpenClaw local agent non-interactively to delegate bounded tasks. It sets up the working directory, checks for the openclaw command, and runs the main agent with a JSON response. It handles authentication, permissions, and ensures read-only access unless workspace changes are requested. It parses JSON payloads even on success to detect failures.

This skill enables orchestrating agents to delegate bounded coding tasks to the OpenAI Codex CLI. The orchestrator drafts the brief, runs the command, and maintains full responsibility for reviewing diffs and committing changes. It prioritizes safety by preventing automatic commits, requiring explicit user requests and manual gate verification.

Delegate bounded coding tasks to the Command Code CLI (cmd) while retaining review and landing responsibility. The orchestrator writes a brief, dispatches via a relay script, reviews the diff, and commits. Requires cmd CLI installed and authenticated, Node 22+, and git.

This skill guides you in implementing Command Query Responsibility Segregation (CQRS) patterns for scalable software architectures. It focuses on separating read and write models to optimize query performance and support event-sourced systems. Use this when you need to scale reads independently from writes or handle complex query scenarios. It is suitable for building high-performance reporting systems where detailed read/write data models are required.

This skill helps developers create Git branches following Sentry naming conventions. It automatically determines the branch type (feat, fix, chore, etc.) based on the work description or local changes. It generates a standardized branch name using the user's GitHub username and proposes it for confirmation before executing the git checkout command. Ideal for starting new work on the default branch.

Generates production-grade Cypress E2E and component tests in JavaScript or TypeScript. Supports local execution and TestMu AI cloud for cross-browser testing. Includes patterns for command chaining, network interception, and custom commands to ensure reliable automation workflows.

This guide covers troubleshooting Kubernetes pods in the crs namespace, specifically for the Buttercup fuzzing platform. It addresses common issues like CrashLoopBackOff, OOMKilled, and Redis failures. Learn to use kubectl commands for log analysis, resource monitoring, and cascade failure detection. Includes Redis debugging and queue inspection techniques.

Use DeepAPI for supported web scraping, research, and email workflows. Requires explicit credentials and user approval before executing commands or remote actions.

This skill enables the creation of production-ready Discord bots using Discord.js for JavaScript and Pycord for Python. It covers essential features including gateway intents, slash commands, interactive components, rate limiting, and sharding strategies to ensure scalability and performance in live environments.

This guide details the comprehensive workflow for distributing a single AI skill across various local agent skill directories (Codex, Claude, Pi, Hermes). It addresses canonical locations, symlink management, and specific synchronization commands to ensure that all agents detect the latest skill version while correctly navigating common development pitfalls.

This skill allows developers to query the health metrics of published EAS Updates directly from the command line. It provides data on crash rates, install counts, unique users, payload sizes, and the split between embedded and OTA users per channel. Useful for post-publish rollout monitoring and regression detection.