Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
research-taste-developer
Develops intuition for what makes research "good" versus "incremental." Use when asked about research taste, how to identify good research, what makes a paper impactful, how to develop research intuition, or how to pick important problems. Analyzes patterns in highly-cited work and what top researchers do differently.
majiayu000/claude-skill-registry 163
-
web-perf
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed.
majiayu000/claude-skill-registry 163
-
moonbit-agent-guide
Guide for writing, refactoring, and testing MoonBit projects. Use when working in MoonBit modules or packages, organizing MoonBit files, using moon tooling (build/check/test/doc/ide), or following MoonBit-specific layout, documentation, and testing conventions.
majiayu000/claude-skill-registry 163
-
math-calculator
This skill should be used when Claude Code needs to perform basic arithmetic calculations. It provides a Python script that safely evaluates mathematical expressions including addition, subtraction, multiplication, division, exponentiation, and square roots.
majiayu000/claude-skill-registry 163
-
observability-metrics
Operate and validate mjr.wtf observability endpoints (/health, /metrics) and logging-related behavior. Use when adding metrics, changing auth around metrics, or debugging production-like issues.
majiayu000/claude-skill-registry 163
-
golang-pro
majiayu000/claude-skill-registry 163
-
Analyze BigQuery Usage
Comprehensive analysis of BigQuery usage patterns, costs, and query performance
majiayu000/claude-skill-registry 163
-
distributed-gummy
Orchestrate gummy-agents across distributed network using 'd' command for load-balanced, multi-host AI development
majiayu000/claude-skill-registry 163
-
parallelize
Create isolated git worktree, open new iTerm2 window with Claude Code, and spawn a task agent there for parallel work. Use when the user says "parallelize" followed by a task description, or asks to work on something in parallel.
majiayu000/claude-skill-registry 163
-
build-iphone-apps
Build professional native iPhone apps in Swift with SwiftUI and UIKit. Full lifecycle - build, debug, test, optimize, ship. CLI-only, no Xcode. Targets iOS 26 with iOS 18 compatibility.
majiayu000/claude-skill-registry 163
-
forensic-refactoring-roi
Use when planning refactoring sprints, prioritizing technical debt backlog, justifying refactoring investment to executives, or creating data-driven roadmaps - calculates return on investment using effort-impact matrices and research-backed formulas
majiayu000/claude-skill-registry 163
-
bilibili-up-batch
批量下载 B 站 UP 最近 N 条视频到 imports，并用 video_pipeline 生成证据包（适合 worker panes 并行跑）。
majiayu000/claude-skill-registry 163
-
pokemon-green-ko
포켓몬 그린 버전 텍스트 RPG. 1세대 151마리 포켓몬, 165개 기술, 관동 지방 완전 재현. 한국어 전용. 사용자가 '포켓몬', '피카츄', '전투', '체육관', '야생', '도감', '새 게임', '이어하기' 등의 키워드를 사용할 때 활성화됩니다. (project)
majiayu000/claude-skill-registry 163
-
Symbolic & Archetypal Mapping
Meaning engine that translates intention into safe, effective symbolic experience
majiayu000/claude-skill-registry 163
-
codebase-index
Quickly index and understand a codebase's architecture. Use at session start to get up to speed fast. Finds entry points, API routes, classes, models, configs, and patterns.
majiayu000/claude-skill-registry 163
-
tableau
Master Tableau development including calculated fields, LOD expressions, table calculations, and dashboard design
majiayu000/claude-skill-registry 163
-
audit-semo
전체 SEMO 패키지 통합 품질 감사. Use when (1) 전체 패키지 품질 점검, (2) Agent/Skill/Command 표준 준수 검토, (3) 비효율적 구조 탐지, (4) 정기 감사 수행.
majiayu000/claude-skill-registry 163
-
prototyping-pretotyping
Use when testing ideas cheaply before building (pretotyping with fake doors, concierge MVPs, paper prototypes) to validate desirability/feasibility, choosing appropriate prototype fidelity (paper/clickable/coded), running experiments to test assumptions (demand, pricing, workflow), or when user mentions prototype, MVP, fake door test, concierge, Wizard of Oz, landing page test, smoke test, or asks "how can we validate this idea before building?".
majiayu000/claude-skill-registry 163
-
license-finder
Deterministically find license information for Python packages by checking PyPI metadata first, then falling back to Git repository LICENSE files using shallow cloning.
majiayu000/claude-skill-registry 163
-
code-review-assistant
Comprehensive PR review using multi-agent swarm with specialized reviewers for security, performance, style, tests, and documentation. Provides detailed feedback with auto-fix suggestions and merge readiness assessment.
majiayu000/claude-skill-registry 163
-
google-cloud-agent-sdk-master
Execute automatic activation for all google cloud agent development kit (adk) Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
majiayu000/claude-skill-registry 163
-
Code Quality Gates
Comprehensive code quality validation using Solargraph, Sorbet, and Rubocop for A+ Rails code. Trigger keywords: quality gates, validation, solargraph, sorbet, rubocop, type checking, linting, code quality, static analysis
majiayu000/claude-skill-registry 163
-
consistency-checker
写作过程中自动检查角色行为、世界规则和时间线一致性，在问题成为严重错误前主动提醒
majiayu000/claude-skill-registry 163
-
multi-source-investigation
Conducts systematic investigations across diverse information sources with cross-validation and credibility assessment. Use when researching complex topics, fact-checking claims, understanding different perspectives, or building comprehensive understanding. Triggers on phrases like "investigate", "verify", "fact check", "cross-reference", "multiple sources", "different perspectives on".
majiayu000/claude-skill-registry 163