全部能力

Playwright testing best practices for Next.js applications (formerly test-playwright). This skill should be used when writing, reviewing, or debugging E2E…

Ansible 高级配置管理、自动化和基础设施即代码

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from…

用于 test-long-runner 的 Agent 技能 - 使用 $agent-test-long-runner 调用

Handle cross-platform compatibility including file paths, environment detection, platform-specific dependencies, and testing across Windows, macOS, and Linux. Use when dealing with platform-specific code or OS compatibility.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII…

性能基准测试代理技能 - 使用 $agent-performance-benchmarker 调用

记录 API 变更、破坏性变更、迁移指南和版本历史。用于 API 版本控制、破坏性变更记录或创建 API 迁移指南时。

Scaffolds new or restructures existing projects to Clean Architecture. Use when setting up project structure.

Reviews task implementation for quality, code standards, and test coverage. Use when task is in To Review. Sets task Done or To Rework.

Guidelines for building modern APIs with Koa.js and TypeScript, featuring the onion middleware model and async/await patterns

Generates Dockerfile and docker-compose configuration for multi-container development. Use when containerizing a project.

Kotlin development guidelines with best practices for clean code, naming conventions, function design, and data handling

Builds all detected projects and verifies successful compilation. Use when checking that a bootstrapped project compiles.

Sets up security scanning for secrets and dependency vulnerabilities. Use when adding security infrastructure to a project.

Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. Prevents 10 documented errors including vector store upload bugs, temperature parameter conflicts, memory leaks. Deprecated (sunset August 2026); use openai-responses for new projects. Use when: maintaining legacy chatbots, implementing RAG with vector stores, or troubleshooting thread errors, vector store delays, uploadAndPoll issues.

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI…

Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes. Use…

Polymarket screeners — discover trending events, top markets by volume, and search for specific markets. Use when browsing what's happening on prediction…

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical…