浏览所有 Claude 技能

HyDE Semantic Retrieval

29

Enhances RAG retrieval accuracy by generating hypothetical answer documents to bridge vocabulary gaps in semantic search.

Ollama Local Inference

29

Enables high-performance local LLM execution for cost-effective, private, and offline AI-powered development.

LangGraph Human-in-the-Loop

29

Implements robust human-in-the-loop patterns for LangGraph workflows to enable manual review gates and approval-based agent supervision.

Prompt Caching & Cost Optimizer

29

Optimizes LLM performance and reduces API costs by implementing provider-native prompt caching for Claude and OpenAI models.

Dignified Python 3.12 Standards

29

Enforces high-quality Python 3.12 coding standards, including modern type syntax, robust error handling, and clear API design principles.

Backend Architecture Enforcer

29

Enforces FastAPI Clean Architecture by validating layer separation and dependency injection patterns in real-time.

Nette NEON Formatter

29

Standardizes NEON configuration files with Nette-specific syntax rules and best practices for PHP development.

Comprehensive Feature Verification

29

Verifies software implementations through parallelized agent analysis, automated testing, and detailed evidence compilation.

Nette Utils Helper

29

Streamlines PHP development with a comprehensive suite of utility classes for data manipulation, validation, and file system operations.

Python Background Jobs & Queues

29

Implements robust asynchronous task processing and job queues using Celery, ARQ, and Redis for Python backends.

Code Review Playbook

29

Standardizes code reviews with structured processes, conventional comments, and quality-focused checklists.

Nette Frontend Development

29

Optimizes Nette framework frontend workflows by integrating modern build tools like Vite, SCSS, and TypeScript with the Nette Assets system.

SkillForge Configuration Wizard

29

Configures and customizes your SkillForge environment through an interactive wizard for skills, agents, and hooks.

React i18n & Date Patterns

29

Implements comprehensive internationalization and locale-aware formatting for React applications using industry-standard patterns.

PHP Documentation Standards

29

Enforces concise, high-quality PHPDoc standards to improve code readability without redundant signature duplication.

Nette Commit Message Standards

29

Generates standardized, Nette-compliant git commit messages using specific tense, casing, and formatting rules.

Nette Schema Data Validation

29

Validates and normalizes complex data structures, configuration files, and API inputs using the Nette Schema library.

PHP Coding Standards (Nette)

29

Enforces professional PHP coding standards and naming conventions based on the Nette framework for consistent, high-quality codebases.

LangGraph Parallel Execution

29

Implements high-performance parallel execution patterns for LangGraph workflows using fan-out, fan-in, and map-reduce strategies.

Deep Codebase Explorer

29

Accelerates repository onboarding and architectural understanding through parallel multi-agent codebase analysis.

Input Validation & Sanitization

29

Implements secure input validation and sanitization patterns using Zod and Pydantic to prevent injection attacks and ensure data integrity.

MSW API Mocking

29

Intercepts and mocks network requests using Mock Service Worker 2.x to create deterministic frontend tests for REST, GraphQL, and WebSockets.

Structured Brainstorming

29

Transforms rough ideas into fully-formed technical designs through guided Socratic questioning and architectural alternative exploration.

LLM Function Calling & Tool Use

29

Implements production-ready tool-use patterns and structured output schemas for LLMs using the latest industry standards.

Error Pattern Analyzer

29

Analyzes and troubleshoots recurring error patterns in Claude Code sessions to streamline debugging and prevent repeated failures.

Webapp Testing & Playwright Automation

29

Automates end-to-end web testing using Playwright's autonomous agents for planning, generating, and self-healing tests.

LLM Safety Patterns

29

Implements production-grade security patterns for LLM integrations to defend against prompt injection and prevent hallucinations.

AI Defense-in-Depth

29

Implements a robust 8-layer security architecture to harden AI pipelines and protect LLM integrations from end-to-end.

Agent Documentation Management

29

Enforces documentation standards, structure, and best practices for agent-focused repositories.

Full-Stack Feature Implementer

29

Orchestrates end-to-end feature development using parallel subagent execution for simultaneous frontend, backend, and testing workflows.