Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
go-pro
Expert Go developer specializing in idiomatic patterns, concurrency, error handling, and clean package design. This skill should be used PROACTIVELY when working on any Go code - implementing features, designing APIs, debugging issues, or reviewing code quality. Use unless a more specific subagent role applies.
majiayu000/claude-skill-registry 163
-
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
majiayu000/claude-skill-registry 163
-
Automation Architect
Design workflow automations using Zapier, Make, n8n, and other automation tools
majiayu000/claude-skill-registry 163
-
runme-conventions
Runme.dev形式の実行可能マークダウン作成・編集用規約。
使用タイミング:
(1) マークダウンファイルに実行可能なコードブロックを追加（verify.md, README.mdなど）
(2) Runme.devセル設定の追加・編集（name, cwd, excludeFromRunAllなど）
(3) runme fmtでフォーマット適用
(4) 既存Runmeファイルの修正・改善
majiayu000/claude-skill-registry 163
-
ds-brainstorm
This skill should be used when the user asks to "start a data science project", "brainstorm analysis", "plan a data analysis", or wants to clarify analysis requirements. REQUIRED Phase 1 of /ds workflow. Uses Socratic questioning to clarify goals, data sources, and constraints.
majiayu000/claude-skill-registry 163
-
generating-nest-servers
PRIMARY expert for ALL NestJS and @lenne.tech/nest-server tasks. ALWAYS use this skill when working in projects with @lenne.tech/nest-server in package.json dependencies (supports monorepos with projects/*, packages/*, apps/* structure), or when asked about NestJS modules, services, controllers, resolvers, models, objects, tests, server creation, debugging, or any NestJS/nest-server development task. Handles lt server commands, security analysis, test creation, and all backend development. ALWAYS reads CrudService base class before working with Services.
majiayu000/claude-skill-registry 163
-
Confidence Check
Pre-implementation confidence assessment (≥90% required). Use before starting any implementation to verify readiness with duplicate check, architecture compliance, official docs verification, OSS references, and root cause identification.
majiayu000/claude-skill-registry 163
-
pr-formatter
**AUTO-TRIGGER when user says:** "create PR", "format PR", "prepare PR body", "what category for this PR", "generate PR keywords"
Formats TogetherOS pull requests with proper category (Cooperation Path), keywords, progress markers, and validation. Auto-selects category from module, generates relevant keywords, ensures correct structure for automation.
Use proactively without asking permission when task matches skill purpose.
majiayu000/claude-skill-registry 163
-
swift-core
Swift 6 fundamentals for all Apple platforms. Use when implementing concurrency, architecture, testing, i18n, or performance optimization across iOS, macOS, iPadOS, watchOS, visionOS.
majiayu000/claude-skill-registry 163
-
knowledge-discovery
Discover relevant skills and knowledge using tiered approach. SKIP for simple tasks, QUICK for single-skill, STANDARD for multi-skill, DEEP for full feature implementation. Auto-selects tier based on task complexity.
majiayu000/claude-skill-registry 163
-
SQLite Memory Access
majiayu000/claude-skill-registry 163
-
n8n-integration-patterns
Decide when to use n8n workflows versus Next.js server actions for backend logic. Use when implementing complex multi-step workflows, AI agent pipelines, or external service integrations. Provides patterns for both runtime webhook integration and development-time architectural decisions.
majiayu000/claude-skill-registry 163
-
rate-limiting-patterns
Use when implementing rate limiting, throttling, or API quotas. Covers algorithms like token bucket and sliding window, plus distributed rate limiting patterns.
majiayu000/claude-skill-registry 163
-
output-error-missing-schemas
Fix missing schema definitions in Output SDK steps. Use when seeing type errors, undefined properties at step boundaries, validation failures, or when step inputs/outputs aren't being properly typed.
majiayu000/claude-skill-registry 163
-
descobrindo-odoo-estrutura
Descobre campos e estrutura de qualquer modelo do Odoo. Lista campos de tabela, busca campo por nome, inspeciona registro, faz consulta generica. Use quando: nao conhecer um modelo Odoo, precisar descobrir nome de campo, explorar estrutura de tabela, consulta em modelo nao mapeado.
majiayu000/claude-skill-registry 163
-
baoyu-danger-x-to-markdown
Convert X (Twitter) tweet or article URL to markdown. Uses reverse-engineered X API (private). Requires user consent before use.
majiayu000/claude-skill-registry 163
-
database-operations
A skill for performing database CRUD operations following best practices. Includes guidance on session management, query building (filters, joins, aggregations), transaction handling, bulk operations, error handling, connection pooling, and query optimization. Provides reusable templates for database session dependencies, CRUD service classes, and transaction context managers.
majiayu000/claude-skill-registry 163
-
specs-creator
Creates detailed specifications from client needs including product specs, technical specs, design specs, and API specs. Use when the user requests help with requirement gathering, creating specifications, documenting client requirements, converting feature requests into structured specs, or needs to formalize project requirements for development handoff.
majiayu000/claude-skill-registry 163
-
Context Compilation with cclsp
LSP-powered context extraction using cclsp MCP tools, Solargraph, and Sorbet for type-safe code generation. Trigger keywords: cclsp, LSP, context compilation, interface extraction, vocabulary, Guardian, Sorbet, type checking, find_definition, get_diagnostics, Solargraph, type safety
majiayu000/claude-skill-registry 163
-
skill-evaluator
Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality. Analyzes SKILL.md structure, naming conventions, description quality, content organization, and identifies anti-patterns. Produces actionable improvement recommendations.
majiayu000/claude-skill-registry 163
-
moai-docs-validation
Enhanced docs validation with AI-powered features. Enhanced with Context7 MCP for up-to-date documentation.
majiayu000/claude-skill-registry 163
-
shopify-api
Complete API integration guide for Shopify including GraphQL Admin API, REST Admin API, Storefront API, Ajax API, OAuth authentication, rate limiting, and webhooks. Use when making API calls to Shopify, authenticating apps, fetching product/order/customer data programmatically, implementing cart operations, handling webhooks, or working with API version 2025-10. Requires fetch or axios for JavaScript implementations.
majiayu000/claude-skill-registry 163
-
terraform-audit
Audits Terraform code for anti-patterns, security issues, and best practice violations. Use when asked to audit, review, or check terraform code quality. Generates a comprehensive report under reports/YYYY-MM-DD/terraform-audit.md. (project)
majiayu000/claude-skill-registry 163
-
device-testing
Interact with iOS simulators and verify app behavior using xcobra
majiayu000/claude-skill-registry 163