claude-plugin
**Use MCP repo-map tools when:** - Searching for symbols by name pattern (faster than Grep) - Getting all symbols in a file (faster than Read + parsing)
Essential command-line tools and system utilities.
**Use MCP repo-map tools when:** - Searching for symbols by name pattern (faster than Grep) - Getting all symbols in a file (faster than Read + parsing)
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
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
Enforce Core Web Vitals optimization. Use when building user-facing features, reviewing performance, or when Lighthouse scores drop. Covers LCP, FID/INP, CLS, and optimization techniques.
Use when first encountering an unknown binary, ELF file, executable, or firmware blob. Fast fingerprinting via rabin2 - architecture detection (ARM, x86, MIPS), ABI identification, dependency mapping, string extraction. Keywords - "what is this binary", "identify architecture", "check file type", "rabin2", "file analysis", "quick scan"
Master Go concurrency with goroutines, channels, sync primitives, and context. Use when building concurrent Go applications, implementing worker pools, or debugging race conditions.
Systematic methodology for debugging bugs, test failures, and unexpected behavior. Use when encountering any technical issue before proposing fixes. Covers root cause investigation, pattern analysis, hypothesis testing, and fix implementation. Use ESPECIALLY when under time pressure, "just one quick fix" seems obvious, or you've already tried multiple fixes. NOT for exploratory code reading.
Analyze binary files (exe, dll, sys, bin, ocx, scr, cpl, drv) to assess if they are malicious, perform decompilation, extract strings/imports/exports, detect malware, and provide threat assessment. Use this skill when user asks to analyze, examine, check, or assess any binary file, asks if a file is malicious/suspicious/safe, or provides a file path to a binary. Trigger for phrases like "Is [file] malicious?", "Analyze [file]", "What does [binary] do?", or any request involving binary file analysis.
Debug WebSocket connection issues between CLI and FigJam plugin. Use when diagrams aren't syncing or connection fails.
Full-stack performance analysis, optimization patterns, and monitoring strategies
【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 CLI 快速扫描完整代码库,提供 AI 驱动的架构洞察和代码分析,大幅节省手动探索时间。仅返回原始分析结果,不做二次解读。
WebSocket server and client patterns with heartbeat and reconnection. Use when implementing real-time features, debugging connection issues, or reviewing WebSocket code. Triggers on: WebSocket, wss, heartbeat, reconnect, real-time.
【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 chrome-devtools-expert agent 执行浏览器操作,避免大量页面快照、截图、网络请求数据污染主对话上下文。
Operates and debugs the local stack (API/worker/frontend); focuses on observability, logs, and safe automation.
Maintain NAP (Name, Address, Phone) consistency across all platforms. Use when managing citations, updating business info, or generating schema markup.
URL validation and contextual analysis specialist. Use when validating links, analyzing URL context, extracting links from content, or ensuring link appropriateness. Combines technical validation with content analysis.
Fast web fuzzer for DAST testing with directory enumeration, parameter fuzzing, and virtual host discovery. Written in Go for high-performance HTTP fuzzing with extensive filtering capabilities. Supports multiple fuzzing modes (clusterbomb, pitchfork, sniper) and recursive scanning. Use when: (1) Discovering hidden directories, files, and endpoints on web applications, (2) Fuzzing GET and POST parameters to identify injection vulnerabilities, (3) Enumerating virtual hosts and subdomains, (4) Testing authentication endpoints with credential fuzzing, (5) Finding backup files and sensitive data exposures, (6) Performing comprehensive web application reconnaissance.
Pointers for Copilot/agents to apply Perigon conventions
Universal patterns for tree-sitter code parsing. Covers AST visitors, query patterns, and language plugin development. Framework-agnostic.
Installs Claude Code hooks for automatic skill usage measurement. Use when setting up skill tracking infrastructure in a new project. NOT when hooks are already installed (run verify.py to check).
Python type hints and type safety patterns. Triggers on: type hints, typing, TypeVar, Generic, Protocol, mypy, pyright, type annotation, overload, TypedDict.
Use when you need to find code by concept (not just text). Uses Serena MCP for semantic code search across the codebase with minimal token usage. Ideal for understanding architecture, finding authentication flows, or multi-file refactoring.
Work on the core package (types, validation, normalization, diff). Use when modifying DSL processing logic or data flow.