Explore skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when creating, drafting, or rewriting Linear issues (epics, stories, hardening tickets, refactor tasks) in any workspace. Applies the linear-issue-craft conventions for titles, description structure, tone, labels, and epic-to-story decomposition. Trigger when the user says "draft an issue", "open an epic", "file a ticket", "write a Linear issue", or pastes a rough idea/bug report and asks for

根据自然语言描述生成正则表达式，附带可视化解释（铁路图）和 交互式测试页面。当用户提到"正则"、"regex"、"匹配模式"、 "文本提取"、"字符串匹配"时使用。即使用户只是描述了一种 文本模式（如"怎么找出所有邮箱地址"）也应触发。

Fire-and-forget async Codex delegation. This skill should be used when delegating debugging, implementation, refactoring, or code review to OpenAI Codex without blocking the current conversation. Trigger when: (1) implementation or refactoring touching 3+ files — do not attempt yourself, delegate, (2) debugging after 1-2 failed root-cause attempts — stop spinning and hand it off, (3) user says 'de

Miki's personal pre-self-review loop. Iteratively runs /review on the current PR and addresses obvious issues until only minor nits remain or 3 iterations have run. Surfaces judgment calls back to the user, makes atomic commits per project convention, pushes once at the end. Invoke when the user says "/miki-review-loop", "loop the review", "iterate on the review", or similar after a PR has been cr

Use this skill when the user is about to start building something and would benefit from hard questions before coding. Trigger on "ship think", "gut check", "sanity check", "should I build this", "before I start", "does this make sense", "is this worth building", "is this overkill", or "thoughts on this approach". Also trigger when the user describes a feature, migration, rewrite, or architectural

Use Bunny.net for CDN, image hosting, video hosting, edge storage, image optimization, AI image generation, edge scripting, container hosting, DNS, and security (WAF/DDoS). Trigger when user mentions bunny, cdn, image hosting, video hosting, media storage, edge storage, image optimization, video streaming, pull zone, storage zone, WebP conversion, AVIF, lazy loading, DRM, video encoding, edge func

Comprehensive iOS app development skill with Liquid Glass design, modern Swift patterns (@Observable, SwiftData), and App Store readiness. Self-updates by checking Apple Developer News for new iOS versions. Use for any iOS/SwiftUI project.

Build the world before you write the story. Advanced context engineering for deep research, foundational research, and evidence-first planning before coding. Use when the user asks for world building, deep research before building, foundational research, market mapping before coding, hands-off but non-generic results, pillar mapping, folder scaffolding, parallel research, layered synthesis, or evi

Run a code review using Cursor Agent with Gemini

Evaluates Node.js packages before installation by checking bundle size impact, comparing alternatives, verifying latest stable versions, and assessing maintenance status. Use when adding dependencies, installing packages, choosing between libraries, optimizing bundle size, or when user mentions npm install, yarn add, pnpm add, package selection, or asks about package recommendations.