All Skills

Performs thorough code review on git changes. Analyzes diffs for bugs, security issues, performance problems, and design concerns. Produces actionable feedback organized by severity. Use when reviewing code, checking a PR, or when the user says /smart-review.

Registers existing React components with Tambo so AI can render them. Use when user wants to make their existing components available to AI, register components for generative UI, convert React components to Tambo components, or mentions /add-components-to-registry. For creating NEW components, see the components skill. For project setup, use add-to-existing-project or start-from-scratch skills.

Automate PR workflow with commit, push, create PR, and CI check

Automate Confluence page creation, content search, space management, labels, and hierarchy navigation via Rube MCP (Composio). Always search tools first for current schemas.

Clean Architecture principles including Dependency Inversion, Layer Separation, and Reference Rules. Use when designing new features, reviewing architecture decisions, or ensuring proper layer boundaries.

This skill should be used when running competitive intelligence scans and market research reports against tracked competitors. It invokes the competitive-intelligence agent to produce a structured knowledge-base report. Triggers on \"competitive analysis\", \"competitor scan\", \"market research\".

Code review principles covering test quality verification, architecture compliance, and general review checklist. Use when reviewing code, providing feedback, or establishing review standards.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Documents Crowdin CLI context download and upload for AI enrichment. Use when downloading or uploading strings context for Crowdin, managing context files, or running crowdin context commands.

Maintains a living mental model of the codebase. Read mental-model.md before making changes, update it when discovering new patterns or behaviors.

Help users integrate the ZETIC Melange (MLange) on-device AI SDK into Android (Kotlin/Java) and iOS (Swift) mobile apps. Use this skill whenever the user mentions Zetic, MLange, Melange, ZeticMLangeModel, ZeticMLangeLLMModel, ZeticMLangeHFModel, on-device NPU inference for mobile, or deploying ML models to Android/iOS with NPU acceleration. Also trigger when users ask about running LLMs on-device with GGUF quantization, mobile NPU model deployment, or converting PyTorch/ONNX models for mobile inference. Covers general model inference, LLM inference (streaming token generation), and HuggingFace model loading.

Transform project issues into execution-ready implementation plans with risk prediction, wave-based organization, specialist agents, and TDD workflow

Helps users find the right Azure RBAC role for an identity with least privilege access, then generate CLI commands and Bicep code to assign it. Also provides guidance on permissions required to grant roles. USE FOR: \"what role should I assign\", \"least privilege role\", \"RBAC role for\", \"role to read blobs\", \"role for managed identity\", \"custom role definition\", \"assign role to identity\", \"what role do I need to grant access\", \"permissions to assign roles\". DO NOT USE FOR: creating or configuring managed identities, or general Azure security hardening; those are out of scope for this role-selection skill.

Write professional emails to clients

Authorization and permissions management for Ruby on Rails applications using CanCanCan. Use when: (1) Implementing role-based access control (RBAC), (2) Defining user permissions and abilities, (3) Restricting resource access in controllers, (4) Filtering queries based on user permissions, (5) Hiding/showing UI elements based on authorization, (6) Testing authorization logic, (7) Managing admin vs user vs guest permissions, (8) Implementing attribute-based access control

Pre-ship quality gate for AI agents and automations. Use when the user mentions: pre-ship, checklist, ship check, ready to ship, ready to publish, launch checklist, release checklist, pre-publish, quality gate, go/no-go, agent packaging review, pre-ship check, before release, before publish, packaging audit

This skill should be used when the user wants to reject, hide, or filter out a remote job from future email digests. Triggers on phrases like "reject this job", "hide [company]", "add to reject list", "don't show [company] again", "remove [company] from results", or when reviewing remote job emails and marking jobs as not relevant.

This skill should be used when the user wants to mark a company as rejected in their Excel job tracker (List.xlsx). Triggers on phrases like "mark [company] as rejected", "reject [company] in the tracker", "[company] rejected me", "strikethrough [company]", "update [company] to rejected", "I got rejected by [company]", "remove [company] from active".

Use when writing production code that needs tests - new features, bug fixes, refactoring. Enforces RED-GREEN-REFACTOR cycle before any implementation.

Use when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.

Scan Claude Code changelog for new versions, features, and changes. Fetches official docs, parses release notes, and generates structured update report.

Enhance uxscii components from sketch to production fidelity. Use when working with .uxm files marked as "fidelity: sketch" or when user wants to add detail and polish to components.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

--- name: brainstorm description: This skill explores ideas and possibilities, recording "what if" scenarios. Use when brainstorming approaches, thinking through trade-offs, consuming sketches or diagrams into a session, or exploring before committing. Triggers include "let's brainstorm", "what if