aka. Agent Skills
Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.
WHEN refining or structuring prompts; NOT executing tasks; outputs XML-tagged instructions with roles, tasks, constraints, and examples.
WHEN writing git/conventional commits; NOT for PR text; returns concise, why-first commit lines with proper type/scope.
Comprehensive guide for implementing on-device AI models on iOS using Foundation Models and MLX Swift frameworks. Use WHEN building iOS apps with (1) Local LLM inference, (2) Vision Language Models (VLMs), (3) Text embeddings, (4) Image generation, (5) Tool/function calling, (6) Multi-turn conversations, (7) Custom model integration, or (8) Structured generation.
WHEN writing tests in Swift with the Swift Testing framework; NOT XCTest.
WHEN users express dissatisfaction with visual appearance or behavior; use Playwright MCP to capture screenshots and collaborate on UI fixes with a structured feedback loop.
WHEN creating/editing developer docs/tutorials/proposals/reviews; delivers scannable structure, clear payoffs, and strong titles.
WHEN setting working agreements/TDD rules for this codebase; clarifies boundaries and documentation expectations.
WHEN building SwiftUI views, managing state, setting up shared services, or making architectural decisions; NOT for UIKit or legacy patterns; provides pure SwiftUI data flow without ViewModels using @State, @Binding, @Observable, and @Environment.
WHEN scraping iOS/macOS App Store data (apps, reviews, ratings, search); NOT for installing or testing apps; retrieves structured JSON data using iTunes/App Store APIs with curl and jq formatting
WHEN capturing learnings/gotchas/decisions into CLAUDE.md; NOT trivial changes; guides what to record, where it lives, and format.
WHEN designing features App Intent-first so Siri/Shortcuts, widgets, and SwiftUI share logic; NOT UI-first; reuse intents across app.
WHEN tests are green and you need a refactor plan; NOT for new feature delivery; commit-first safety with prioritized improvements.
Use when fetching dbt documentation, looking up dbt features, or answering questions about dbt Cloud, dbt Core, or the dbt Semantic Layer
Use when a dbt Cloud/platform job fails and you need to diagnose the root cause, especially when error messages are unclear or when intermittent failures occur. Do not use for local dbt development errors.
Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools like Claude Desktop, Claude Code, Cursor, or VS Code.
WHEN users express issues with app behavior, visual appearance, or functionality in the iOS simulator collaborate on fixes with a structured feedback loop.
Use when creating or modifying dbt Semantic Layer components including semantic models, metrics, and dimensions leveraging MetricFlow.
WHEN drafting PR descriptions or sizing/splitting work; NOT for commit messages; provides reviewer-first templates and gh pr steps.
Use when a user asks a business question that requires querying data (e.g., "What were total sales last quarter?"). NOT for validating, testing, or building dbt models during development.
Use when adding unit tests for a dbt model or practicing test-driven development (TDD) in dbt