agents-ui
Build React frontends for LiveKit voice AI agents. Use this skill when creating web interfaces for voice assistants using LiveKit's shadcn-based Agents UI components. Covers AgentSessionProvider, audio visualiz...
发现 研究与调研 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Build React frontends for LiveKit voice AI agents. Use this skill when creating web interfaces for voice assistants using LiveKit's shadcn-based Agents UI components. Covers AgentSessionProvider, audio visualiz...
【强制】所有浏览器操作必须使用本技能,禁止在主对话中直接使用 mcp__chrome-devtools 工具。触发关键词:打开/访问/浏览网页、点击/填写/提交表单、截图/快照、性能分析、自动化测试、数据采集/爬取、网络模拟。本技能通过 c...
【Bug 诊断专用】当遇到程序错误、异常行为、性能问题、功能故障时必须使用本技能。触发关键词:报错、Bug、问题、异常、故障、不工作、诊断、排查、修复。本技能提供系统性根因分析,输出详细诊断报告和可执行修复方案,包含...
Analyze codebase structure using Serena's symbolic tools. Use for understanding project architecture, generating structure overviews, mapping dependencies between components, and onboarding to new codebases.
Automated code review with security scanning, quality metrics, and best practices analysis. Use when reviewing code for: (1) Security vulnerabilities and common attack vectors, (2) Code quality issues and maint...
Professional web application testing and automation using Playwright with support for multiple browsers, mobile emulation, screenshot capture, network interception, and comprehensive test assertions. Use for: (...
Quick code exploration using Serena MCP. Use for small-scale tasks like checking single file structure, finding a specific symbol, or quick reference lookup. No subagent - runs in main context for efficiency.
Systematic debugging and error resolution using the TRACE framework (Trace, Read, Analyze, Check, Execute). Use when debugging errors, analyzing stack traces, investigating failures, root cause analysis, or tro...
This skill should be used when the user requests a code review of changed files. Use this to review git-diffed files for security vulnerabilities (OWASP Top 10), performance issues (O(N) complexity, ORM optimiz...
【大型代码库分析专用】当需要分析整个项目架构、识别代码模式、追踪功能实现、梳理模块关系时必须使用本技能。触发关键词:分析整个项目/代码库、架构梳理、模块划分、代码模式识别、功能追踪、全局扫描。本技能通过 Gemini C...
Performs comprehensive audits to detect placeholder code, mock data, TODO markers, and incomplete implementations in codebases. Use this skill when you need to find all instances of "theater" in code such as ha...
Lightning-fast quality check using parallel command execution. Runs theater detection, linting, security scan, and basic tests in parallel for instant feedback on code quality.
Comprehensive dependency mapping, analysis, and visualization tool for software projects
Comprehensive performance profiling, bottleneck detection, and optimization system
Detects non-functional "theater" code that appears complete but doesn't actually work. Use this skill to identify code that looks correct in static analysis but fails during execution, preventing fake implement...
Check resource usage (CPU, memory) on cluster nodes. Used to identify nodes under pressure. Keywords: node resources, cpu, memory, capacity, pressure, metrics, cluster health.
Deep investigation of a failing pod. Gathers logs, events, and resource status to identify root cause. Keywords: investigate, debug, pod failure, troubleshoot, root cause, logs, events.
Explain how components are expanded under the hood, including HasComponent and ComponentState; use when a request involves debugging or understanding generated component code in Cairo.
Guides Claude through integrating Gleam with JavaScript code using FFI, external functions, and NPM packages. Use when building for JavaScript target, using browser APIs, or wrapping JS libraries.
Explain Cairo references, snapshots (`@`), `ref` parameters, and desnap (`*`); use when a request involves borrowing, avoiding moves, or mutating data through references in Cairo.
Explain Cairo unrecoverable errors, `panic`, `panic!`, `panic_with_felt252`, `nopanic`, and `panic_with`; use when a request involves panics or panic annotations in Cairo.
Configure Claude Code sandbox network isolation with trusted domains, custom access policies, and environment variables
Automated comprehensive code documentation generation with API docs, README files, inline comments, and architecture diagrams
Audits code against CI/CD style rules, quality guidelines, and best practices, then rewrites code to meet standards without breaking functionality. Use this skill after functionality validation to ensure code i...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。