Skill Creator

majiayu000

6838 published skills · 19,665 GitHub stars across the catalog. View on GitHub ↗

conventional-commits

majiayu000's avatarfrom majiayu000

Generate properly formatted Conventional Commits messages with Claude Code footer. Use when creating git commits, writing commit messages, or the user mentions "commit", "git commit", or wants to save changes.

quant-resource-patterns

majiayu000's avatarfrom majiayu000

Follow these patterns when implementing quant domain resources like Dataset, Signal, Alpha, Portfolio, Strategy, Universe, Backtest, or MonitoringRun in OptAIC. Use for creating DB models, DTOs, services, and tests for trading-specific entities.

race-condition-audit

majiayu000's avatarfrom majiayu000

Systematic identification of race conditions, concurrency bugs, and thread-safety issues across codebases. Use when asked to find race conditions, audit concurrent code, debug non-deterministic behavior, review thread safety, find data races, or analyze async/parallel code. Supports TypeScript, JavaScript, Python, Go, Rust, and C++.

mobx-state-tree-store-builder

majiayu000's avatarfrom majiayu000

Automates creation of MobX State Tree stores following Purrsuit Mobile App patterns for domain models, collections, and root store integration. Use when creating new MST stores, models, or extending existing store functionality with proper TypeScript typing, actions, views, and integration patterns.

conda-forge-expert

majiayu000's avatarfrom majiayu000

Comprehensive guide for conda-forge recipe development. Handles legacy (meta.yaml)and modern (recipe.yaml) formats, linting, CI troubleshooting, and feedstock maintenance.Enhanced with patterns from real conda-forge feedstocks (2025).USE THIS SKILL WHEN: creating conda recipes, packaging Python/Rust/Go/C++ software,fixing conda-forge build failures, updating feedstocks, migrating to recipe.yaml format,setting up private channels, or troubleshooting conda-forge CI.

evaluation-quality

majiayu000's avatarfrom majiayu000

Instrument evaluation metrics, quality scores, and feedback loops

pubmed-fulltext-access

majiayu000's avatarfrom majiayu000

Full text access via Europe PMC, CORE, and other open access sources. Triggers: 全文, fulltext, PDF, open access, 免費下載, PMC, 開放取用

frontend-tailwind

majiayu000's avatarfrom majiayu000

Create beautiful UIs with Tailwind CSS mastery. Expert in utility-first design, responsive layouts, and design systems. Activate for UI development, design system creation, or CSS optimization. Use it anytime you need to write Tailwind CSS.

form-builder

majiayu000's avatarfrom majiayu000

Build accessible forms with React Hook Form + Zod

multi-agent-research

majiayu000's avatarfrom majiayu000

Apply Anthropic's production multi-agent research patterns for complex research tasks. Use when research involves multiple independent dimensions, requires synthesis across many sources, or needs parallelization for speed. Includes query complexity assessment, parallel execution, progressive search refinement, thinking strategies, and findings compression.

korean-public-data-api

majiayu000's avatarfrom majiayu000

Extract API request/response schema from Korean Public Data Portal (data.go.kr) documentation pages and generate structured JSON representation

mac-automation

majiayu000's avatarfrom majiayu000

This skill should be used when the user requests Mac automation via AppleScript, including: Mail operations, Reminders/Calendar management, Safari control, Finder operations, system controls (volume, brightness, notifications, app launching), third-party apps (development tools, task management, media players), or mentions "AppleScript" or "automate Mac".

kotlin-spring-reviewer

majiayu000's avatarfrom majiayu000

WHEN: Spring Boot + Kotlin, Ktor backend review, coroutine-based server, WebFlux/R2DBC pattern checksWHAT: Spring Kotlin idioms + Coroutines integration + WebFlux patterns + Data class usage + Test strategiesWHEN NOT: Android → kotlin-android-reviewer, KMP shared code → kotlin-multiplatform-reviewer

sc-startup

majiayu000's avatarfrom majiayu000

Run repo startup: prompt load, checklist sync, optional PR triage, worktree hygiene, and CI pull. Best-effort with structured status.

pull-request-management

majiayu000's avatarfrom majiayu000

GitHub PR operations - create, list, merge, update, and manage pull requests using gh CLI

tmux-orchestrator

majiayu000's avatarfrom majiayu000

This skill should be used when orchestrating tmux sessions for multi-component development workflows. Use when creating complex multi-window, multi-pane tmux layouts via the Bash tool, especially for projects requiring simultaneous backend/frontend development, microservices, or parallel task execution. This skill provides patterns for session creation, pane management, and command orchestration using the user's custom tmux configuration.

write-release-notes

majiayu000's avatarfrom majiayu000

Generate professional Bytebase release notes by analyzing git commits, checking Terraform impact, searching Linear for customer feedback, and following established conventions. Creates Linear tracking issue and owner confirmation comments (with user approval before each write operation). Use when preparing release notes for minor or patch versions.

explore-codebase

majiayu000's avatarfrom majiayu000

Pattern for efficiently exploring codebases using parallel subagents. Use when you need to understand code structure, find patterns, or gather context.

issue

majiayu000's avatarfrom majiayu000

This skill should be used when the user asks to "create an issue", "write an issue", "add an issue", "log an issue", "report a bug", "document a problem", or wants to track tasks, bugs, or feature requests in the issues folder.

local-clickhouse

majiayu000's avatarfrom majiayu000

Install, configure, and validate local ClickHouse for gapless-crypto-clickhouse development and backtesting. Use when setting up local development environment, enabling offline mode, improving query performance for backtesting, or running E2E validation. Includes mise/Homebrew/apt installation, mode detection, connection validation, and E2E workflow scripts.

test-mcp-connector

majiayu000's avatarfrom majiayu000

ONLY trigger this skill when the user EXPLICITLY asks for MCP-based testing:**Required triggers (ALL must mention "MCP" explicitly):**- "test connector with mcp"- "test mcp connector"- "test [provider] with mcp"- "use mcp to test [provider]"- "run mcp connector test"- "mcp test for [provider]"**DO NOT trigger for:**- Generic "test the connector" requests (use stackone run / test_actions instead)- "test [provider]" without explicit MCP mention- Regular validation or testing requests- Any testing that doesn't explicitly mention MCPThis skill builds a REAL agent with Claude Agent SDK that sends natural language prompts to evaluate if action descriptions are agent-friendly. It's more intensive than regular testing and should only be used when explicitly requested.

android-screenshot-automation

majiayu000's avatarfrom majiayu000

Setup automated screenshot capture for Play Store using Fastlane Screengrab

literal-string

majiayu000's avatarfrom majiayu000

C# Literal string을 const string으로 사전 정의하여 사용하는 패턴

mechinterp-decoder

majiayu000's avatarfrom majiayu000

Analyze SAE decoder weights - output influence, feature importance, and decoder similarity