Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
close-sprint
Sprint(Iteration) 종료 및 회고 정리. Use when (1) Sprint 마감,
(2) 회고 작성, (3) /SEMO:sprint close 커맨드.
majiayu000/claude-skill-registry 163
-
backup-retention-policy
Эксперт по политикам бэкапов. Используй для стратегий резервного копирования, retention rules и disaster recovery.
majiayu000/claude-skill-registry 163
-
marketplace-update
Updates the .claude-plugin/marketplace.json file when plugins are added, modified, or removed. Use when creating or updating plugin entries in the marketplace catalog.
majiayu000/claude-skill-registry 163
-
app-analytics-strategist
Expert digital data analytics consultant for designing and implementing data-driven growth strategies for mobile and digital applications. Use this skill when users need help with app analytics strategy, metrics selection, analytics framework implementation, cohort analysis, user segmentation, A/B testing, customer journey mapping, retention optimization, or choosing analytics tools. Applies to product managers, growth teams, and developers building data-driven applications across all platforms and industries seeking to optimize user engagement, retention, and revenue through analytics.
majiayu000/claude-skill-registry 163
-
morning
Start-of-day setup and readiness routine. Calculates Ready to Code Score (0-100) based on session restoration, service health, dependency updates, branch sync, PR reviews, and issue triage. Automatically captures session state to STATUS.json. Use at start of work day after opening Claude Code.
majiayu000/claude-skill-registry 163
-
type-safety-validation
Achieve end-to-end type safety with Zod runtime validation, tRPC type-safe APIs, Prisma ORM, exhaustive type checking, and TypeScript 5.7+ features. Build fully type-safe applications from database to UI for 2025+ development.
majiayu000/claude-skill-registry 163
-
go-nil-pointer
Pointer receiver nil safety - methods can be called on nil
majiayu000/claude-skill-registry 163
-
phase-development-workflow
Complete 12-step workflow for phase development from branch creation to merge. Use this when starting a new phase or when asked to follow the phase development process.
majiayu000/claude-skill-registry 163
-
td-model-selection
Automated model selection and comparison for optimal forecasting
majiayu000/claude-skill-registry 163
-
gpu-cli
Run code on cloud GPUs with GPU CLI. Use when user wants to run Python/ML code on remote GPUs, install GPU CLI, configure gpu.toml, troubleshoot pods, or manage cloud GPU resources via RunPod.
majiayu000/claude-skill-registry 163
-
Azure DevOps Work Items
Guide for creating Azure DevOps work items (Features, User Stories, Tasks). This skill should be used when working with ADO MCP tools to create work items with proper hierarchy and formatting.
majiayu000/claude-skill-registry 163
-
launch-plays
Use when orchestrating Tier 1/2/3 launches with repeatable workstreams and governance.
majiayu000/claude-skill-registry 163
-
skills-gitdipen-dip3n
majiayu000/claude-skill-registry 163
-
baml-codegen
Generates production-ready BAML applications from natural language requirements. Creates complete type definitions, functions, clients, tests, and framework integrations for data extraction, classification, RAG, and agent workflows. Queries official BoundaryML repositories via MCP for real-time patterns. Supports multimodal inputs (images, audio), 6 programming languages (Python, TypeScript, Ruby, Java, Go, C#), 10+ frameworks, 50-70% token optimization, and 95%+ compilation success.
majiayu000/claude-skill-registry 163
-
lead-research-assistant
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
majiayu000/claude-skill-registry 163
-
Bug Triage
Systematically reproduce, diagnose, and analyze bugs to determine root cause, assess severity, and plan fix strategy
majiayu000/claude-skill-registry 163
-
spec-test-driven-development
Use when user requests new features or functionality. Defines complete workflow from specification through testing to implementation.
majiayu000/claude-skill-registry 163
-
codebase-improvement-advisor
既存のコードベース全体を分析し、リファクタリング・最適化の提案を自動生成するためのスキル。 TypeScript/JavaScriptプロジェクトの品質分析、コード改善提案、重複コード検出、セキュリティスキャンなど 「このプロジェクトの改善点を教えて」や「リファクタリング候補をリストアップして」といった依頼に使用する。
majiayu000/claude-skill-registry 163
-
receive-feedback
Process external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.
majiayu000/claude-skill-registry 163
-
i18n-completeness
Comprehensive i18n consistency check with dynamic pattern detection and hardcoded string analysis. Use when working with translations, localization, i18n keys, or when the user mentions translation issues, missing keys, or language support. Auto-triggers on phrases like "check translations", "i18n consistency", "localization issues", or "translation keys".
majiayu000/claude-skill-registry 163
-
cashflow-scheduler
Optimize 30-day work schedules for cashflow management using CP-SAT and DP solvers. Use this skill when users need to plan work schedules around bills, deposits, and target balances while minimizing workdays and maximizing rest distribution.
majiayu000/claude-skill-registry 163
-
notion
Notion API for creating and managing pages, databases, and blocks.
majiayu000/claude-skill-registry 163
-
spec-authoring
Use this skill when proposing new features or changes via the Spec PR process. Manages the creation, refinement, and approval of feature specifications before any code is written. Triggers include "create spec", "propose change", "start spec PR", or beginning feature definition.
majiayu000/claude-skill-registry 163
-
pytorch-model-cli
Guidance for creating standalone CLI tools that perform neural network inference by extracting PyTorch model weights and reimplementing inference in C/C++. This skill applies when tasks involve converting PyTorch models to standalone executables, extracting model weights to portable formats (JSON), implementing neural network forward passes in C/C++, or creating CLI tools that load images and run inference without Python dependencies.
majiayu000/claude-skill-registry 163