hayatosc
28 verified skills9 total stars
article-review
Review and improve articles, essays, blog posts, diaries, and business or technical writing. Use when the agent needs to evaluate a text's quality, structure, persuasiveness, reader value, tone, safety, or human distinctiveness; produce a scored editorial report; prioritize revisions; or rewrite selected passages. Triggers include requests such as "review this article", "evaluate this essay", "critique this blog post", "記事を評価して", "記事をレビューして", or "改善案とリライトを出して".
testing1
empirical-prompt-tuning
agent 向けテキスト指示（skill / slash command / task プロンプト / CLAUDE.md 節 / コード生成プロンプト）を、バイアスを排した実行者に動かしてもらい、両面（実行者の自己申告 + 指示側メトリクス）で評価して反復改善する手法。改善が頭打ちになるまで回す。プロンプトや skill を新規作成・大幅改訂した直後、またはエージェントの挙動が期待通りにならない原因を指示側の曖昧さに求めたいときに使う。
data-ai1
ast-grep
Explore and transform large codebases with ast-grep using AST-aware search, rule-based scanning, and safe codemod workflows. Use when requests involve structural code search beyond regex, writing/testing ast-grep YAML rules, reducing noisy matches by syntax, or applying multi-file rewrites with controlled rollout.
development1
refactoring-code
Analyze and execute behavior-preserving refactors in small, verified steps. Use when the user asks to refactor, clean up code structure, extract functions or modules, reduce duplication, improve maintainability, or modernize code without changing external behavior.
development1
self-ship
Self-review, improve, commit, and push code that Claude has just written. Use this skill when the user asks Claude to "self-ship", "review and ship", "review then commit and push", or wants Claude to autonomously review its own output, apply improvements, and publish the changes to the remote repository. Triggered by: "self-ship", "ship it", "review and push", "review my changes and commit", or similar requests to complete the full write → review → commit → push cycle.
development1
golang-best-practices
Comprehensive Go best practices for writing production-ready, idiomatic, secure, and maintainable code. Use when: (1) writing or reviewing Go code, (2) designing project structure and layout, (3) handling errors and contexts, (4) implementing concurrency, (5) writing tests or benchmarks, (6) optimizing performance, (7) applying security practices, (8) modernizing Go codebases. Covers coding style, project organization, error handling, testing, concurrency, performance, security, and modernization.
development1
askmeplan
Dialogue-driven planning through Socratic questioning, inspired by grill-me. Surface key decisions one at a time with recommended answers, explore the codebase to self-answer when possible, and converge on a co-created implementation plan. Use when the user says "/askmeplan", "let's plan together", "ask me before planning", "help me think through", "grill me", or any request to plan interactively. Also use when the request is ambiguous or involves significant trade-offs that require human judgment before implementation can begin.
development1
typescript-recommend-tools
Recommend a modern TypeScript toolchain. Use when choosing or updating a TypeScript stack for Node or CLI projects, libraries or packages, and web apps or APIs; selecting tsgo as the primary typechecker with tsc as compatibility fallback; recommending Hono, tsx, tsdown, Vite, Vitest, oxlint, oxlint-tsgolint, oxfmt, or deciding between bun and pnpm.
tools1
typescript-best-practices
Implement, review, and refactor TypeScript code with a strong bias toward type safety. Use to fix TypeScript errors, remove `any` or unsafe `as`, review type safety, tighten TypeScript or lint settings, and ship ESM-first code that passes the repository's typecheck without weakening types.
development1
article-review
Review and improve articles, essays, blog posts, diaries, and business or technical writing. Use when the agent needs to evaluate a text's quality, structure, persuasiveness, reader value, tone, safety, or human distinctiveness; produce a scored editorial report; prioritize revisions; or rewrite selected passages. Triggers include requests such as "review this article", "evaluate this essay", "critique this blog post", "記事を評価して", "記事をレビューして", or "改善案とリライトを出して".
testing
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
development
nothing-design
This skill should be used when the user explicitly says "Nothing style", "Nothing design", "/nothing-design", or directly asks to use/apply the Nothing design system. NEVER trigger automatically for generic UI or design tasks.
testing
self-ship
Self-review, improve, commit, and push code that Claude has just written. Use this skill when the user asks Claude to "self-ship", "review and ship", "review then commit and push", or wants Claude to autonomously review its own output, apply improvements, and publish the changes to the remote repository. Triggered by: "self-ship", "ship it", "review and push", "review my changes and commit", or similar requests to complete the full write → review → commit → push cycle.
development
vue-best-practices
MUST be used for Vue.js tasks. Strongly recommends Composition API with `<script setup>` and TypeScript as the standard approach. Covers Vue 3, SSR, Volar, vue-tsc. Load for any Vue, .vue files, Vue Router, Pinia, or Vite with Vue work. ALWAYS use Composition API unless the project explicitly requires Options API.
development
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
development
ast-grep
Explore and transform large codebases with ast-grep using AST-aware search, rule-based scanning, and safe codemod workflows. Use when requests involve structural code search beyond regex, writing/testing ast-grep YAML rules, reducing noisy matches by syntax, or applying multi-file rewrites with controlled rollout.
development
skill-creator
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.
tools
empirical-prompt-tuning
agent 向けテキスト指示（skill / slash command / task プロンプト / CLAUDE.md 節 / コード生成プロンプト）を、バイアスを排した実行者に動かしてもらい、両面（実行者の自己申告 + 指示側メトリクス）で評価して反復改善する手法。改善が頭打ちになるまで回す。プロンプトや skill を新規作成・大幅改訂した直後、またはエージェントの挙動が期待通りにならない原因を指示側の曖昧さに求めたいときに使う。
data-ai
askmeplan
Dialogue-driven planning that replaces one-shot plan generation with a Socratic conversation. Instead of producing a complete plan immediately, surface key decision points one round at a time, incorporate the user's answers, and converge on a co-created implementation plan. Use when the user says "/askmeplan", "let's plan together", "ask me before planning", "help me think through", or any request to plan something interactively rather than receiving a ready-made plan. Also use when the request is ambiguous or involves significant trade-offs that require human judgment before implementation can begin.
testing
typescript-recommend-tools
Recommend a modern TypeScript toolchain. Use when choosing or updating a TypeScript stack for Node or CLI projects, libraries or packages, and web apps or APIs; selecting tsgo as the primary typechecker with tsc as compatibility fallback; recommending Hono, tsx, tsdown, Vite, Vitest, oxlint, oxlint-tsgolint, oxfmt, or deciding between bun and pnpm.
tools
golang-best-practices
Comprehensive Go best practices for writing production-ready, idiomatic, secure, and maintainable code. Use when: (1) writing or reviewing Go code, (2) designing project structure and layout, (3) handling errors and contexts, (4) implementing concurrency, (5) writing tests or benchmarks, (6) optimizing performance, (7) applying security practices, (8) modernizing Go codebases. Covers coding style, project organization, error handling, testing, concurrency, performance, security, and modernization.
development
refactoring-code
Analyze and execute behavior-preserving refactors in small, verified steps. Use when the user asks to refactor, clean up code structure, extract functions or modules, reduce duplication, improve maintainability, or modernize code without changing external behavior.
development
typescript-best-practices
Implement, review, and refactor TypeScript code with a strong bias toward type safety. Use to fix TypeScript errors, remove `any` or unsafe `as`, review type safety, tighten TypeScript or lint settings, and ship ESM-first code that passes the repository's typecheck without weakening types.
development
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
development
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
development
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
tools
modern-web-guidance
Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS tasks. Do NOT skip — web APIs evolve rapidly and training weights contain obsolete patterns. Trigger immediately for: - UI/Layout: Modals, dialogs, popovers, Glassmorphism/backdrop-filters, anchor positioning, container queries, `:has()`, `:user-valid`. - Scroll/Motion: View Transitions, Scroll-driven animations, scroll parallax/reveals. - Performance: CWV (LCP, INP), content-visibility, Fetch Priority, image optimization. - System/APIs: Local filesystem access, WebUSB, WebSockets sync, WebAssembly widgets. - Frameworks: Adapting layout/styles in React, Vue, Angular. - General Frontend: Forms, autofill, advanced inputs, custom scrollbars, modern component states, etc. DO NOT trigger for: - Backend: Database SQL, ORMs, Express API routes. - Pipelines: CI/CD deployment, Docker, Actions. - Generic: Local scripts (Python/Go tools), ESLint, Git.
tools
acpx
Use acpx as a headless ACP CLI for agent-to-agent communication, including prompt/exec/sessions workflows, session scoping, queueing, permissions, and output formats.
tools