Claude Skills by tools-only

```liquid {% if product.available %} <button>Add to Cart</button> {% elsif product.coming_soon %} <p>Coming Soon</p> {% else %} <p>Sold Out</p> {% endif %} ```

Comprehensive catalog of code quality and design smells in Python.

Comprehensive decision guide for selecting linear solvers for Ax = b.

This reference provides comprehensive patterns for detecting conflicts in software requirements.

Comprehensive guide for selecting mesh types in numerical simulations.

Expert guidance for Shopify theme development including file structure, Online Store 2.0 architecture, sections, snippets, and configuration.

Documentation for browser cookie manipulation functions. ---

Comprehensive guide for Implicit-Explicit time integration methods.

Advanced query patterns and single-table design strategies.

Decision trees and criteria for choosing the right design pattern.

- [Coupling Smells](#coupling-smells) - [Cohesion Smells](#cohesion-smells) - [Complexity Smells](#complexity-smells) - [Size Smells](#size-smells) - [Encapsulation Smells](#encapsulation-smells)

Comprehensive reference for operator splitting methods in PDEs and multiphysics.

Detailed patterns for ECS task definitions.

Properties about variable ranges and bounds.

Common architectural patterns found in legacy codebases and how to identify them.

Quick reference for Isabelle/HOL syntax when modeling functional programs.

Platform-specific procedures and best practices for Docker deployments.

Common patterns for specifying distributed systems in TLA+.

Synalinks provides a unified knowledge base system using DuckDB for storing and retrieving structured data. It supports full-text search (BM25) and vector similarity search for building RAG (Retrieval-Augmented Generation) applications.

When a user describes their project, use this reference to suggest appropriate icons. These are starting points — always adapt to the specific project and ask the user to confirm.

How to think about CTAs that actually convert.

Define the end-to-end Screen Time API architecture for building iOS 16+ app/website blocking and usage analytics apps without mixing framework responsibilities.

1. Correct framework separation: FamilyControls (select/auth), ManagedSettings (enforce), DeviceActivity (schedule), ManagedSettingsUI (custom shield UI). 2. Shared app-group state is consistently used so extensions can enforce while host app is inactive. 3. Both projects use token-native UI rendering (`Label(token)`) for app icon/title display. 4. Both include extension targets and entitlement wiring across main app + extensions.

All economic indicators return US data and follow the same response structure: ```json { "name": "Real Gross Domestic Product", "interval": "annual", "unit": "billions of chained 2012 dollars", "data": [{"date": "2023-01-01", "value": "22067.1"}, ...] } ```

> **Back to [Style Guide](../mermaid_style_guide.md)** — Read the style guide first for emoji, color, and accessibility rules. **Syntax keyword:** `C4Context`, `C4Container`, `C4Component` **Best for:** System architecture at varying zoom levels — context, containers, components **When NOT to use:** Infrastructure topology (use [Architecture](architecture.md)), runtime sequences (use [Sequence](sequence.md)) ---

Cards are the primary container component in modern bslib dashboards. They group related content with borders and padding, helping users digest, engage with, and navigate through information.

> **Back to [Style Guide](../mermaid_style_guide.md)** — Read the style guide first for emoji, color, and accessibility rules. **Syntax keyword:** `journey` **Best for:** User experience mapping, customer journey, process satisfaction scoring, onboarding flows **When NOT to use:** Simple processes without satisfaction data (use [Flowchart](flowchart.md)), chronological events (use [Timeline](timeline.md)) ---

Competitive analysis agent that identifies alternatives, compares features, and assesses market positioning. Skipped in quick mode.

image_input = Image.open('/path/to/your/cat_photo.png') text_input = """Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it's sitting comfortably and not falling off.""" response = client.models.generate_content( model="gemini-2.5-flash-image", contents=[text_input, image_input], ) for part in response.parts: if part.text is not None: print(part.text) elif part.inline_data is not None: image = part.as_image() image.save("cat_with_hat.pn...

Deploys www.aitmpl.com and/or app.aitmpl.com to Vercel production. Runs pre-deploy checks (git status, API tests, auth verification) and handles the full deploy pipeline safely. Use when the user asks to deploy the site, dashboard, or both.

Implementation patterns for a development-only HTTP endpoint that agents can query for log entries.

Automated rate-limiting for resource submissions. Applies to both issues and pull requests.

**February 2026** ---

Full Board of Directors deliberation with 5 expert directors assessing, discussing, and voting.

This is the authoring guide for the **legacy** dbt Semantic Layer YAML spec, supported in **dbt Core 1.6 through 1.11**. dbt Core 1.12+ also supports this spec but the [latest spec](latest-spec.md) is recommended for new projects. In the legacy spec, semantic models are defined as top-level resources separate from dbt model definitions. Measures are a core concept used as building blocks for metrics.

Expert CEO advisor with 30 years entrepreneurship experience. Provides strategic guidance, business analysis, and leadership advice. Advisory only - does not modify code.

| Operation | Method | Endpoint/Mutation | |-----------|--------|-------------------| | List | GraphQL | `{ pages(first: 50) { edges { node { id title } } } }` | | Create | GraphQL | `pageCreate(page: { ... })` | | Update | GraphQL | `pageUpdate(page: { id, ... })` | | Delete | GraphQL | `pageDelete(id: "...")` |

Apply fixes to a PR based on review-pr findings or review comments

You are the **Chief Product Officer** on the Board of Directors. Your domain is user value and product strategy.

| Column | Description | Example | |--------|-------------|---------| | `Handle` | URL slug (unique per product) | `classic-tshirt` | | `Title` | Product name (first row per product) | `Classic T-Shirt` | | `Body (HTML)` | Description in HTML | `<p>Premium cotton</p>` | | `Vendor` | Brand or manufacturer | `My Brand` | | `Product Category` | Shopify standard taxonomy | `Apparel & Accessories > Clothing > Shirts & Tops` | | `Type` | Custom product type | `T-Shirts` | | `Tags` | Comma-separated ta

Key mutations for product management via the Admin API.

This reference covers multi-level IR analysis for detecting compiler-optimized zeroization (dead-store elimination of wipes) and interpreting results. Read this during Step 7 (IR comparison) and Step 9 (semantic IR analysis) in `task.md`. For flag extraction and pipeline setup, refer to the compile-commands reference (loaded separately from SKILL.md). ---

**Arcana**: Major | **Number**: XVII

**Suit**: Pentacles | **Rank**: King

Release resources that require custom cleanup. A *deinitializer* is called immediately before a class instance is deallocated. You write deinitializers with the `deinit` keyword, similar to how initializers are written with the `init` keyword. Deinitializers are only available on class types.

Hands-on guides for mastering EvalView's advanced features. ---

Full Board of Directors deliberation with 5 expert directors assessing, discussing, and voting.

Set the initial values for a type's stored properties and perform one-time setup. *Initialization* is the process of preparing an instance of a class, structure, or enumeration for use. This process involves setting an initial value for each stored property on that instance and performing any other setup or initialization that's required before the new instance is ready for use. You implement this initialization process by defining *initializers*, which are like special methods that can be ca...

You are a Tool Recommendation Agent. Your job is to analyze the given request, evaluate the available tools, and recommend the best tool that can resolve the user's requests. Your expertise lies in understanding the capabilities and limitations of various tools. Identify and beware of the tricky parts of this request: - Overlapping tool functionalities that may cause confusion. - Tools with limited capabilities that may not fully address the request. With chain-of-thought reasoning, you shoul...

 1. Go to https://github.com/ > Signup 2. Go to https://github.com/marketplace/models/azure-openai/gpt-4o or https://github.com/marketplace/models/catalog and select gpt-4o 3. Get API Key > Get production key 4. Sign up and sign in Azure account 6. Select `Deploy to selected resource` 7. Locate the newly created resource under `All resources` 8. Select Azure Open AI 9. Copy one of the `API keys` and `...