Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
architecture-decision-records
Document significant architectural decisions. Use when making significant architectural decisions, documenting technology choices, or recording design trade-offs.
majiayu000/claude-skill-registry 163
-
sudoku
Fetch Sudoku puzzles and store them as JSON in the workspace; render images on demand; reveal solutions later.
majiayu000/claude-skill-registry 163
-
testing-skills-with-subagents
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
majiayu000/claude-skill-registry 163
-
ln-770-crosscutting-setup
Coordinates logging, error handling, CORS, health checks, and API docs
majiayu000/claude-skill-registry 163
-
Performance Profiler
Profile application performance, identify bottlenecks, and optimize for speed
majiayu000/claude-skill-registry 163
-
resize-story-resolve-io-prism
majiayu000/claude-skill-registry 163
-
replit-debug-bundle
Collect Replit debug evidence for support tickets and troubleshooting.
Use when encountering persistent issues, preparing support tickets,
or collecting diagnostic information for Replit problems.
Trigger with phrases like "replit debug", "replit support bundle",
"collect replit logs", "replit diagnostic".
majiayu000/claude-skill-registry 163
-
technical-indicators
Technical analysis with TA-Lib - Moving averages, RSI, MACD, Bollinger Bands, Stochastic, ATR, candlestick patterns, and strategy signals using OpenAlgo market data
majiayu000/claude-skill-registry 163
-
convertSubagents
Atlas skill for converting Claude Code Subagents to OpenCode Agents format. USE WHEN migrating from Claude Code to OpenCode or when you have existing subagent definitions to port.
majiayu000/claude-skill-registry 163
-
auto-generated-model-repository-pattern
Database-backed model configuration with static fallback for this project. Hook-based reactive queries (useModels, useModel), static sync helpers, AUTO_MODEL injection, type depth workarounds. Triggers on "useModels", "useModel", "model repository", "database models", "model queries", "model picker", "model config".
majiayu000/claude-skill-registry 163
-
prd-creation
majiayu000/claude-skill-registry 163
-
feature-first-lapc506-flutter-agentic-boil
majiayu000/claude-skill-registry 163
-
quantitative-management
Use when establishing measurement programs, analyzing metrics with statistical process control, setting baselines, or implementing CMMI Level 4 quantitative management - prevents vanity metrics and measurement theater
majiayu000/claude-skill-registry 163
-
llm-evaluation
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
majiayu000/claude-skill-registry 163
-
conditional-docs-setup
Set up conditional documentation loading to prevent context pollution. Use when organizing project docs, implementing progressive disclosure, or reducing CLAUDE.md token consumption with on-demand loading.
majiayu000/claude-skill-registry 163
-
data-transformation
データ変換パイプラインの設計・実装・検証を整理するスキル。
スキーママッピング、ETL設計、品質確認までの実務フローを提供する。
Anchors:
• Designing Data-Intensive Applications / 適用: データモデリング / 目的: 変換の整合性確保
• Designing Data-Intensive Applications / 適用: スキーマ設計 / 目的: マッピングの明確化
• Designing Data-Intensive Applications / 適用: パイプライン設計 / 目的: 伸縮性と監視性の確保
Trigger:
Use when designing data transformation pipelines, defining schema mappings, implementing ETL processes, or optimizing data flows.
data transformation, schema mapping, etl design, pipeline optimization, data modeling
majiayu000/claude-skill-registry 163
-
distributed-systems
Distributed systems tools including NATS messaging, libp2p networking, and Temporal workflows
majiayu000/claude-skill-registry 163
-
report-generation
Generate HTML reports, charts, and dashboards with neo-brutal design. Use for creating GitHub activity reports, Fieldy summaries, Skillz analytics, and other data visualizations.
majiayu000/claude-skill-registry 163
-
claude-restart-compact
Compact context at natural breakpoints to free tokens and continue working. Use PROACTIVELY at phase boundaries, after commits, or when token usage >150k. Better than random auto-compact. Supports custom compaction prompts.
majiayu000/claude-skill-registry 163
-
DevOps Practices
Expertise in deployment automation, container orchestration, and infrastructure as code. Activates when working with "deploy", "kubernetes", "docker", "terraform", "helm", "k8s", "container", or cloud infrastructure.
majiayu000/claude-skill-registry 163
-
branch-strategy
Modern Git branching strategies for 2026. GitHub Flow with feature flags, trunk-based development, and branch lifecycle management.
majiayu000/claude-skill-registry 163
-
rust-web
Rust Web 开发专家。处理 axum, actix, HTTP, REST, API, 数据库, 状态管理等问题。触发词：web, HTTP, REST, API, axum, actix, handler, database, web开发, 服务器, 路由
majiayu000/claude-skill-registry 163
-
principle-kiss
保持设计和实现的简单性，识别并消除不必要的复杂度。当需要架构设计评审、代码简化重构、接口设计优化时使用。覆盖代码、架构、接口、流程四大维度，提供简单性检查清单和过度复杂性的诊断修复方法。
majiayu000/claude-skill-registry 163
-
Integrating Stripe Payments
Complete guide for integrating Stripe payments (subscriptions or one-time) with Convex + Next.js. Includes user interviews, API setup, webhook configuration, testing phases, and production deployment. Use this skill when Adding payment functionality to a Convex + Next.js app
majiayu000/claude-skill-registry 163