Topic: productivity
1,476 skills in this topic.
-
extract-errors
Use when adding new error messages to React, or seeing "unknown error code" warnings.
sangrokjung/claude-forge 647
-
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
sangrokjung/claude-forge 647
-
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
sangrokjung/claude-forge 647
-
manage-skills
세션 변경사항을 분석하여 검증 스킬 누락을 탐지합니다. 기존 스킬을 동적으로 탐색하고, 새 스킬을 생성하거나 기존 스킬을 업데이트한 뒤 프로젝트 CLAUDE.md를 관리합니다.
sangrokjung/claude-forge 647
-
team-orchestrator
Agent Teams 오케스트레이션 엔진 - 팀 구성, 작업 분배, 의존성 관리, 결과 집계
sangrokjung/claude-forge 647
-
eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
sangrokjung/claude-forge 647
-
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
sangrokjung/claude-forge 647
-
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
sangrokjung/claude-forge 647
-
cc-dev-agent
Claude Code 개발 워크플로우 최적화. Context Engineering, Sub-agents, TDD, 개발 후 검증 워크플로우 제공. 트리거: CC 프로젝트 시작, CLAUDE.md/spec.md 작성, /handoff /verify /commit-push-pr, sub-agent/Explore, Agent Teams 병렬 개발 요청 시.
sangrokjung/claude-forge 647
-
dependency-upgrade
Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.
sangrokjung/claude-forge 647
-
jpa-patterns
JPA/Hibernate 模式，涵盖 Spring Boot 中的实体设计、关系、查询优化、事务、审计、索引、分页和连接池。
xu-xiang/everything-claude-code-zh 383
-
verification-loop
Claude Code 会话的全方位验证系统。
xu-xiang/everything-claude-code-zh 383
-
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
xu-xiang/everything-claude-code-zh 383
-
iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem
xu-xiang/everything-claude-code-zh 383
-
frontend-patterns
针对 React、Next.js、状态管理、性能优化及 UI 最佳实践的前端开发模式。
xu-xiang/everything-claude-code-zh 383
-
api-design
生产级 API 的 REST API 设计模式，包括资源命名、状态码、分页、过滤、错误响应、版本控制和速率限制。
xu-xiang/everything-claude-code-zh 383
-
clickhouse-io
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
xu-xiang/everything-claude-code-zh 383
-
article-writing
编写文章、指南、博客帖子、教程、新闻通讯（newsletter）以及其他长篇内容。这些内容具有从提供的示例或品牌指南中提取出的独特语气。当用户需要比段落更长的精美文案，且对语气一致性、结构和可信度有要求时，请使用此技能（Skill）。
xu-xiang/everything-claude-code-zh 383
-
backend-patterns
后端架构模式、API 设计、数据库优化以及 Node.js、Express 和 Next.js API 路由的服务端最佳实践。
xu-xiang/everything-claude-code-zh 383
-
python-testing
使用 pytest、TDD 方法论、测试夹具（Fixtures）、模拟（Mocking）、参数化（Parametrization）以及覆盖率要求的 Python 测试策略。
xu-xiang/everything-claude-code-zh 383
-
clickhouse-io
ClickHouse 数据库模式、查询优化、分析以及高性能分析工作负载的数据工程最佳实践。
xu-xiang/everything-claude-code-zh 383
-
golang-testing
Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.
xu-xiang/everything-claude-code-zh 383
-
django-patterns
Django 架构模式、使用 DRF 的 REST API 设计、ORM 最佳实践、缓存、信号（Signals）、中间件（Middleware）以及生产级 Django 应用。
xu-xiang/everything-claude-code-zh 383
-
content-hash-cache-pattern
使用 SHA-256 内容哈希缓存高昂的文件处理结果 —— 与路径无关、自动失效且服务层分离。
xu-xiang/everything-claude-code-zh 383