Skill Creator
majiayu000
6838 published skills · 19,665 GitHub stars across the catalog. View on GitHub ↗
agent-patterns
Modular orchestration of agent patterns from Anthropic's engineering guide. Intelligently selects and implements prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer, and autonomous agents. Includes pattern combinations and language-specific implementations.
odin-install
Install and configure the Odin programming language. Use when:- Setting up Odin on a new machine- Updating Odin to latest version- Configuring Odin language server (ols)
unsloth-core
Core fundamentals of Unsloth for fast LLM fine-tuning, covering FastLanguageModel setup, optimized gradient checkpointing, and native inference acceleration (triggers: unsloth, FastLanguageModel, from_pretrained, get_peft_model, for_inference, gradient checkpointing).
apple-design
Create Apple-inspired modern, minimalist UI designs with glassmorphism, smooth animations, generous whitespace, and elegant typography. Use when designing portfolio websites, landing pages, hero sections, product showcases, or implementing Apple-style components, dark mode, or responsive layouts.
web-test-cleanup
Clean up test sessions - kill browsers, stop dev servers, free ports, and optionally remove test data. Use this BEFORE starting new tests or AFTER completing tests.
backend-orchestrator
Coordinates backend development tasks (APIs, services, databases). Use when implementing REST APIs, business logic, data models, or service integrations. Applies backend-standard.md for quality gates.
document-parser
Parse large documents into structured sections with abstracts and metadata
sprint-planner
Use this skill when planning a new sprint by selecting approved specs from the project board and creating atomic GitHub issues for the development team. Triggers include "plan sprint", "create sprint", "start new sprint", or beginning a development cycle.
container-scanner
Scans containers and Dockerfiles for security issues. Wraps Hadolint for Dockerfile linting and Trivy for container image scanning. Use when user asks to "scan Dockerfile", "lint Dockerfile", "container security", "image scan", "Dockerセキュリティ", "コンテナスキャン".
devops-dx
GitHub/Railway housekeeping for CI env/secret management and DX maintenance.Use when setting or auditing GitHub Actions variables/secrets, syncing Railway env → GitHub, or fixing CI failures due to missing env.
bq-query-optimization
Use when writing BigQuery queries, optimizing query performance, analyzing execution plans, or avoiding common SQL gotchas. Covers parameterized queries, UDFs, scripting, window functions (QUALIFY, ROW_NUMBER, RANK, LEAD/LAG), JSON functions, ARRAY/STRUCT operations, BigQuery-specific features (EXCEPT, REPLACE, SAFE_*), CTE re-execution issues, NOT IN with NULLs, DML performance, Standard vs Legacy SQL, and performance best practices.
bigquery-patent-search
Fast, cloud-based patent searching across 76 million+ worldwide patents using Google BigQuery - keyword search, CPC classification, patent details retrieval
catz-challenge-evaluator
Evaluates Catz Android coding challenge submissions against SWORD Health requirements. Use when reviewing or assessing this coding challenge. Produces a structured markdown report with seniority level assessment (Junior/Mid/Senior/Staff) and confidence rating, covering requirements compliance, architecture, code quality, testing, and documentation.
admin-windows
Windows system administration with PowerShell 7.x. Profile-aware - reads your preferencesfor package managers (scoop vs winget), paths, and installed tools.Use when: Windows-specific admin tasks, PowerShell automation, PATH configuration,package installation, bash-to-PowerShell translation.
backend-dev-guidelines
Comprehensive backend development guide for Node.js/NestJS/TypeScript microservices. Use when creating controllers, services, database access, middleware, DTOs, or working with NestJS APIs, dependency injection, or async patterns. Covers layered architecture (controllers → services → dbservice), error handling, performance monitoring, testing strategies.
fhir-software
Comprehensive FHIR (Fast Healthcare Interoperability Resources) software development assistant. Use when working with FHIR APIs, implementations, or healthcare data exchange. Supports FHIR R4, R4B, R5, Implementation Guides (IGs), validation, terminology, and SMART on FHIR. Ideal for building FHIR servers, clients, validators, or healthcare applications that need to process FHIR resources.
role-based-access
Implement role-based access control (RBAC) with user roles (admin, lead, member) and permission middleware. Use when adding authorization or restricting endpoints by role.
detecting-incorrect-memset
Detects incorrect use of memset() including wrong argument order, incorrect size calculations, and misunderstood behavior. Use when analyzing memory initialization, buffer clearing, or investigating memset() usage errors.
weavr-api
Use when making Weavr API calls for corporates, consumers, cards, accounts, transfers, or KYC/KYB
implement-and-verify
Implement tasks from plans with test-first approach, user-story-centric execution, and AC verification. Use proactively when executing implementation plans. Enforces quality gates, MVP-first delivery, and Article VII story-by-story implementation.
parsing
Use the lean4-parser library for parsing structured input. Invoke when implementing parsers for AoC puzzles or other text processing tasks in Lean.
assessment-builder
Creates assessments with varied question types (MCQ, code-completion, debugging, projects) aligned to learning objectives. Use when educators design quizzes/exams, need questions at appropriate Bloom's cognitive levels, want balanced cognitive distribution (60%+ non-recall), or require rubrics for open-ended questions.
multi-agent-orchestration
Enable Claude to orchestrate complex tasks by spawning and managing specialized sub-agents for parallel or sequential decomposition. Use when tasks have clear independent subtasks, require specialized approaches for different components, benefit from parallel processing, need fault isolation, or involve complex state management across multiple steps. Best for data pipelines, code analysis workflows, content creation pipelines, and multi-stage processing tasks.
clean-code
Clean code principles for readable, maintainable software