Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
schema-patterns
Effect Schema conventions and patterns. Triggers on Schema class creation, tagged unions, enums, type guards, or test fixtures using Effect Schema.
majiayu000/claude-skill-registry 163
-
code-review-quality
Conduct context-driven code reviews focusing on quality, testability, and maintainability. Use when reviewing code, providing feedback, or establishing review practices.
majiayu000/claude-skill-registry 163
-
self-extracting-script
Create self-extracting Bash scripts that embed any payload (archives, executables, configs) using base64 encoding. Use when creating portable single-file installers, deployment packages, or distributing files without external dependencies.
majiayu000/claude-skill-registry 163
-
blazor-expert
Comprehensive Blazor development expertise covering Blazor Server, WebAssembly, and Hybrid apps. Use when building Blazor components, implementing state management, handling routing, JavaScript interop, forms and validation, authentication, or optimizing Blazor applications. Includes best practices, architecture patterns, and troubleshooting guidance.
majiayu000/claude-skill-registry 163
-
flow-shop-scheduling
When the user wants to solve Flow Shop Scheduling Problems (FSP), optimize production on assembly lines, or minimize makespan with linear routing. Also use when the user mentions "flow shop," "FSP," "permutation flow shop," "assembly line scheduling," "sequential processing," or "linear production." For job shop (flexible routing), see job-shop-scheduling.
majiayu000/claude-skill-registry 163
-
resolve-git-issue
Resolve a GitHub issue by implementing a fix and tests; use when asked to fix an issue end-to-end.
majiayu000/claude-skill-registry 163
-
sayhello
Generate friendly greetings in multiple languages and styles. Use this skill when users request greetings, welcome messages, or multilingual hello messages for various contexts (formal, casual, cultural).
majiayu000/claude-skill-registry 163
-
flutter-widget-assistant
Interactive Flutter Widget implementation assistant that guides you through widget implementation decisions by asking structured questions about state management, widget type (screen/component), and state sharing. Use this skill when you need help determining the appropriate Flutter widget architecture for your implementation.
majiayu000/claude-skill-registry 163
-
graph-based-ui-decomposition
Apply graph theory to decompose large UIs into optimal rendering subgraphs.
majiayu000/claude-skill-registry 163
-
Implement Text Response Question
Create D3 questions focused on written explanations and reflections of static content (text, images, diagrams). For video-based questions, use implement-video-question instead.
majiayu000/claude-skill-registry 163
-
resize-images
Resizes images that are too large for the blog. Use when asked to resize images, optimize images, or make images smaller. Can resize to a specific width (e.g., "resize to 300px") or default to 1000px max width. Defaults to the most recent post's assets folder.
majiayu000/claude-skill-registry 163
-
api-testing
Test FastAPI endpoints with pytest and generate API documentation. Use when creating new APIs or verifying existing endpoints work correctly.
majiayu000/claude-skill-registry 163
-
co14-platformization
Apply CO14 Platformization to extract common capabilities into reusable infrastructure serving multiple use cases.
majiayu000/claude-skill-registry 163
-
discover-collaboration
Automatically discover collaboration and teamwork skills when working with collaboration. Activates for collaboration development tasks.
majiayu000/claude-skill-registry 163
-
measure-instrumentation-spec
majiayu000/claude-skill-registry 163
-
error-recovery-patterns
Error recovery and failure handling patterns for distributed systems including rollback strategies, circuit breakers, retry logic with exponential backoff, graceful degradation, and compensating transactions. Activates when task execution fails, timeouts occur, external services fail, database transactions fail, or cascade failure risks are detected. Use when recovering from failures, preventing data corruption, implementing resilience patterns, or handling partial system failures.
majiayu000/claude-skill-registry 163
-
saas-project-orchestrator
Complete SaaS project creation orchestrator. Triggers when user wants to start a new SaaS project, build a full-stack application, or initialize a project from scratch. Guides through all SDLC phases.
majiayu000/claude-skill-registry 163
-
openai-knowledge
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.
majiayu000/claude-skill-registry 163
-
root-cause-tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
majiayu000/claude-skill-registry 163
-
auth-system-design
Authentication system design and implementation guidance with Python examples using strict typing. Use when: (1) Designing authentication flows (signup, login, logout, refresh), (2) Selecting between session vs token-based auth, (3) Designing JWT structure and claims, (4) Implementing OAuth 2.0 flows, (5) Setting up multi-service authentication patterns, (6) Creating password reset and email verification flows, (7) Implementing role-based access control (RBAC), (8) Creating security checklists for auth systems, (9) Planning frontend/backend auth integration. All examples follow Python typing standards and security best practices.
majiayu000/claude-skill-registry 163
-
code-evolution
Autonomous multi-agent code evolution system for optimization problems. Use when solving complex optimization problems (packing, geometry, scheduling, search) through evolutionary approaches with multiple independent AI agents. Multi-start hybrid heuristic+SLSQP methods significantly outperform single approaches. Triggers include genetic algorithms, evolutionary optimization, multi-agent problem solving, parameter tuning at scale, AlphaEvolve-style research, or evolving code solutions across generations.
majiayu000/claude-skill-registry 163
-
db-design-agent
Designs database schemas, data models, and database architectures
majiayu000/claude-skill-registry 163
-
dto-response
Use when creating or modifying DTO files in the `dto/` folder.
majiayu000/claude-skill-registry 163
-
claude-workflow
CWF knowledge repository providing plan structure, tasklist format, checkpoint definitions, amendment rules, and validation requirements. Load this skill when: (1) executing CWF commands like /write-plan, /implement-plan, /amend-plan, (2) answering questions about CWF workflow or plan/tasklist format, (3) validating plan or tasklist documents, (4) understanding phase structure or task conventions. This is KNOWLEDGE context, not an action - do NOT confuse with the /write-plan, /implement-plan, /amend-plan, or /brainstorm commands which are user-invoked.
majiayu000/claude-skill-registry 163