Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
ralph-resume
Resume from saved session state after interruption or compaction. Recovers context from checkpoints and agent-memory.
majiayu000/claude-skill-registry 163
-
rlhf
Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.
majiayu000/claude-skill-registry 163
-
qr-barcode-reader
Use when asked to scan, decode, read, or extract data from QR codes or barcodes in images.
majiayu000/claude-skill-registry 163
-
designing-architecture
Guides software architecture decisions, design patterns, and system design principles. Use when designing systems, choosing patterns, or making architectural decisions.
majiayu000/claude-skill-registry 163
-
seo-check
Analyseer SEO-aspecten zoals meta tags, headings en alt-teksten. Gebruik bij het reviewen van content voor zoekmachines of wanneer de gebruiker vraagt om SEO te checken.
majiayu000/claude-skill-registry 163
-
convex-realtime
Implement real-time features using Convex reactive queries that automatically update when data changes, enabling live collaboration, instant updates, and reactive UIs without manual polling. Use when building live dashboards, implementing collaborative editing, creating chat applications, showing real-time notifications, building activity feeds, implementing presence indicators, creating reactive search, or any feature requiring instant data synchronization across clients.
majiayu000/claude-skill-registry 163
-
prd-planner
Creates PRDs using persistent file-based planning. Use when user explicitly says "PRD", "product requirements document", or "产品需求文档". Combines PRD methodology with planning-with-files to avoid context switching.
majiayu000/claude-skill-registry 163
-
git-pull-request
Use when creating a pull request.
majiayu000/claude-skill-registry 163
-
behavioral-modes
AI operasyonel modları (beyin fırtınası, uygulama, hata ayıklama, inceleme, öğretme, dağıtım, orkestrasyon). Görev türüne göre davranışı uyarlamak için kullanın.
majiayu000/claude-skill-registry 163
-
graphql-architect
Use when designing GraphQL schemas, implementing Apollo Federation, or building real-time subscriptions. Invoke for schema design, resolvers with DataLoader, query optimization, federation directives.
majiayu000/claude-skill-registry 163
-
patterns/facade
Facade Pattern pattern for C development
majiayu000/claude-skill-registry 163
-
oracle-teach
Generate learning materials from mature patterns. Use when user says "teach me", "explain this pattern", "create a guide", "how does X work", "document this for others". Auto-trigger when sharing knowledge with team.
majiayu000/claude-skill-registry 163
-
ltv-predictor
基于RFM模型和回归算法的客户生命周期价值(LTV)预测分析工具，支持电商和零售业务的客户价值预测。使用时需要客户交易数据、订单历史或消费记录，自动进行RFM特征工程、回归建模和价值预测。
majiayu000/claude-skill-registry 163
-
hatchling
This skill provides comprehensive documentation for Hatchling, the modern Python build backend that implements PEP 517/518/621/660 standards. Use this skill when working with Hatchling configuration, build system setup, Python packaging, pyproject.toml configuration, project metadata, dependencies, entry points, build hooks, version management, wheel and sdist builds, package distribution, setuptools migration, and troubleshooting Hatchling build errors.
majiayu000/claude-skill-registry 163
-
versioning-skills
REQUIRED for all skill development. Automatically version control every skill file modification for rollback/comparison. Use after init_skill.sh, after every str_replace/create_file, and before packaging.
majiayu000/claude-skill-registry 163
-
himalaya
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-sandbox-delete
Delete a sandbox. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
rust-router
CRITICAL: Use for ALL Rust questions including errors, design, and coding. Triggers on: Rust, cargo, rustc, crate, Cargo.toml, 意图分析, 问题分析, 语义分析, analyze intent, question analysis, compile error, borrow error, lifetime error, ownership error, type error, trait error, value moved, cannot borrow, does not live long enough, mismatched types, not satisfied, E0382, E0597, E0277, E0308, E0499, E0502, E0596, async, await, Send, Sync, tokio, unsafe, FFI, concurrency, error handling, 编译错误, compile error, 所有权, ownership, 借用, borrow, 生命周期, lifetime, 类型错误, type error, 异步, async, 并发, concurrency, 错误处理, error handling, 问题, problem, question, 怎么用, how to use, 如何, how to, 为什么, why, 什么是, what is, 帮我写, help me write, 实现, implement, 解释, explain, 区别, difference, 最佳实践, best practice
majiayu000/claude-skill-registry 163
-
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
majiayu000/claude-skill-registry 163
-
nielsen-flexibility
Proporciona atajos para usuarios expertos sin afectar a novatos. Use cuando diseñe interfaces que serán usadas repetidamente o por usuarios con diferentes niveles de experiencia.
majiayu000/claude-skill-registry 163
-
javascript-expert
Expert-level JavaScript development with modern ES2024+ features, Node.js, npm ecosystem, and best practices
majiayu000/claude-skill-registry 163
-
hook-management
Central authority for Claude Code hooks management in this repository. Automates enforcement of critical repository rules through hooks. Use when adding hooks, managing hooks, configuring hooks, troubleshooting hooks, or understanding hook behavior. Delegates to docs-management skill for official hooks documentation. Provides organization-specific patterns, configuration management, and workflow guidance.
majiayu000/claude-skill-registry 163
-
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
majiayu000/claude-skill-registry 163
-
context-degradation
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
majiayu000/claude-skill-registry 163