ai-toolkit
github.com/ravnhq/ai-toolkit
Skill | Added | Review |
|---|---|---|
liquid-glass-ios Apple's Liquid Glass design system for iOS 26+ and iPadOS 26+. Use when building iOS 26+ UI with glassEffect, implementing GlassEffectContainer, working with glass morphing transitions, or migrating from UIKit to SwiftUI glass APIs. | 76 76 1.54x Agent success vs baseline Quality 71% Does it follow best practices? Impact 99% 1.54xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
platform-frontend Framework-agnostic frontend architecture — state management, components, data fetching. Use when building any web frontend, choosing state patterns, or structuring UI code. | 64 64 1.10x Agent success vs baseline Quality 51% Does it follow best practices? Impact 95% 1.10xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
agent-pr-creator Analyzes git diffs and commit history to intelligently fill PR templates and create pull requests via gh CLI. Use when user wants to create a PR, needs PR description help, or says 'create a pull request', 'fill PR template', 'make a PR', 'open a pull request', or mentions PR creation. | 90 90 1.04x Agent success vs baseline Quality 88% Does it follow best practices? Impact 100% 1.04xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
lang-typescript TypeScript language patterns and type safety rules — strict mode, no any, discriminated unions. Use when writing TypeScript code, reviewing types, or enforcing type safety. | 67 67 0.96x Agent success vs baseline Quality 58% Does it follow best practices? Impact 87% 0.96xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
agent-init-deep Initialize or migrate to nested CLAUDE.md structure for progressive disclosure. Claude auto-loads CLAUDE.md from any directory it enters, so nested files get discovered automatically. Use when setting up a new project's agent config, refactoring a bloated CLAUDE.md, or adding progressive disclosure to an existing repo. Triggers on: '/agent-init-deep', 'setup progressive disclosure', 'refactor claude.md', 'split claude.md', 'claude.md is too big'. | 94 94 1.66x Agent success vs baseline Quality 92% Does it follow best practices? Impact 98% 1.66xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
agent-add-rule Add a new rule, convention, or instruction to the project's agent configuration. Analyzes the rule and helps decide placement: root CLAUDE.md (universal rules), docs/agents/ files (topic-specific guidance), or a new skill (complex workflows). Use when users say: '/agent-add-rule', 'add a rule', 'add convention', 'new coding standard', 'add instruction for claude', 'update claude.md with'. | 98 98 1.12x Agent success vs baseline Quality 100% Does it follow best practices? Impact 98% 1.12xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
platform-cli Design and implementation patterns for building command-line tools with modern UX. Use when designing a CLI, reviewing CLI UX, defining commands and flags, or implementing error handling and signal handling. | 81 81 1.15x Agent success vs baseline Quality 73% Does it follow best practices? Impact 96% 1.15xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
platform-backend Server-side architecture and security — API design, error handling, validation, logging. Use when building APIs, server logic, or reviewing backend security. | 65 65 1.06x Agent success vs baseline Quality 51% Does it follow best practices? Impact 99% 1.06xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
tech-trpc tRPC router architecture, procedure design, and Vertical Slice Architecture patterns. Use when building tRPC APIs, designing procedures, or structuring backend slices. | 71 71 1.47x Agent success vs baseline Quality 56% Does it follow best practices? Impact 100% 1.47xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
swift-concurrency Swift Concurrency patterns — async/await, actors, tasks, Sendable conformance. Use when writing async/await code, implementing actors, working with structured concurrency, or ensuring data race safety. | 85 85 1.02x Agent success vs baseline Quality 78% Does it follow best practices? Impact 97% 1.02xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
core-coding-standards Universal code quality rules — KISS, DRY, clean code, code review. Base skill every project should include. Use when writing or reviewing any code. | 69 69 1.12x Agent success vs baseline Quality 58% Does it follow best practices? Impact 81% 1.12xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
design-accessibility WCAG AA and ARIA best practices — screen readers, keyboard navigation, focus management. Use when building any user-facing interface or reviewing accessibility compliance. | 71 71 0.98x Agent success vs baseline Quality 63% Does it follow best practices? Impact 95% 0.98xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
platform-database SQL database design, query optimization, and migration safety. Use when writing queries, designing schemas, or planning database migrations. | 70 70 1.06x Agent success vs baseline Quality 56% Does it follow best practices? Impact 95% 1.06xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
tech-drizzle Drizzle ORM schema design, relational queries, and migration patterns. Use when working with Drizzle ORM, writing database queries, or managing Drizzle migrations. | 71 71 1.35x Agent success vs baseline Quality 56% Does it follow best practices? Impact 100% 1.35xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
platform-testing Framework-agnostic testing principles — test philosophy, structure, mocking boundaries. Use when writing, reviewing, or debugging tests. | 66 66 1.18x Agent success vs baseline Quality 51% Does it follow best practices? Impact 94% 1.18xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
design-frontend Visual design system patterns for web UIs — layout, responsive, Tailwind tokens. Use when implementing visual designs, working with CSS/Tailwind, or building responsive layouts. | 72 72 0.98x Agent success vs baseline Quality 58% Does it follow best practices? Impact 96% 0.98xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
tech-react React-specific component, hook, and rendering patterns. Use when writing React components, hooks, JSX, or optimizing React performance. | 71 71 1.18x Agent success vs baseline Quality 62% Does it follow best practices? Impact 97% 1.18xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
tech-vitest Vitest-specific testing utilities — vi.mock, vi.fn, fake timers, MSW. Use when writing tests with Vitest, mocking dependencies, or setting up test infrastructure. | 70 70 0.83x Agent success vs baseline Quality 67% Does it follow best practices? Impact 82% 0.83xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
promptify Transform user requests into detailed, precise prompts for AI models. Use when users say 'promptify', 'promptify this', or explicitly request prompt engineering or improvement of their request for better AI responses. | 89 89 1.58x Agent success vs baseline Quality 87% Does it follow best practices? Impact 89% 1.58xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 | |
agent-skill-creator Guide for creating effective, portable skills that extend Claude's capabilities with specialized knowledge, workflows, and tool integrations. Use when: (1) Creating a new skill from scratch, (2) Updating or improving an existing skill, (3) Structuring skill content for progressive disclosure, (4) Writing skill descriptions and triggers, (5) Packaging a skill for distribution. Triggers on: "create a skill", "build a skill", "new skill", "update this skill", "improve skill description", "skill structure", "skill triggers". | 97 97 1.16x Agent success vs baseline Quality 100% Does it follow best practices? Impact 90% 1.16xAverage score across 3 eval scenarios Reviewed: Version: 0a59ae9 |