Guide for diagnosing lsp errors. This skill should be used when users wants to debug a lsp/diagnostic errors, warnings, or exceptions and get clear explanations and potential solutions. <prompt-triggers> <trigger>"Why am i getting this [diagnostic error]?"</trigger> <trigger>"how do i fix this [lsp error]"</trigger> </prompt-triggers>
Debug and eliminate fallback/generic-stub replies quickly. Use when you see empty assistant replies, “Thanks for your message…” stubs, or “no specific information available” messages. Produces a minimal reproduction (test or deterministic trace) and pinpoints the fallback source + trigger.
Detects N+1 query problems in GraphQL resolvers and TypeScript code. Checks for missing DataLoader usage, sequential database queries in loops, and resolver batching opportunities. Use before committing GraphQL resolvers or during performance reviews.
Context compression for long coding sessions. Creates checkpoints (state snapshots) and maintains them as you work.
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
Debug event flows systematically from EventSource to Workflow. Use diagnostic commands and logging levels to isolate failures in production event systems.
Static HTML/CSS/ARIA analysis without requiring a browser. Use this skill when analyzing code for semantic HTML issues, ARIA validity, landmark structure, heading hierarchy, form labeling, or any accessibility problems detectable from source code. Queries aria-mcp for ARIA rules and wcag-mcp for success criteria mapping. Part of the a11y-orchestrator workflow.
Analyze malware samples for forensic investigation. Use when investigating malware infections, determining malware capabilities, extracting IOCs, or understanding attack techniques. Supports static and dynamic analysis of executables, scripts, and documents.
This skill should be used when analyzing errors, stack traces, and logs to identify root causes and implement fixes.
Profile and optimize application performance. Use when diagnosing slow response times, detecting memory leaks, analyzing CPU hotspots, optimizing bundle size, or measuring Core Web Vitals.
Systematically trace bugs backward through call stack to find original trigger
Debug TUI (Text User Interface) applications through visual observation and semantic inspection. Use when: (1) debugging rendering issues in terminal UIs, (2) troubleshooting widget behavior or key bindings, (3) diagnosing data flow issues where updates aren't appearing in widgets, (4) investigating layout problems, (5) any TUI application debugging where you need to observe runtime state. Supports Textual (Python) with deep semantic inspection, and any TUI via mcp-tui-server visual observation.
**SMART CONTEXT v1.0** - '컨텍스트', '관련 코드', '참조', '토큰 절약', '효율적 분석' 요청 시 자동 발동. codebase-graph 기반으로 필요한 컨텍스트만 선택적 추출. 토큰 72% 절감, 정확도 92% 달성. 모든 코드 분석 작업의 기반 레이어.
File descriptor abuse, race conditions, and TOCTOU vulnerabilities
Performance analysis, bundle size tracking, and optimization suggestions
Telemetry, metrics, tracing, and observability for Elixir/BEAM applications
Analyze and validate links and buttons on web pages. Use when users ask to check links, verify button hrefs, find empty links, detect javascript:void links, find broken navigation, or audit clickable elements. Detects empty href, javascript:void(0), hash-only links, missing href attributes, and non-accessible buttons.
chrome-devtools-mcp を使ってWebサイトの問題を体系的にデバッグします。ネットワークエラー、コンソールエラー、パフォーマンス問題、UI/UXの問題を調査する際に使用します。
This skill should be used when the user asks to "find the root cause", "trace the bug", "why is this happening", "where does this come from", or when errors occur deep in the call stack. Systematically traces backward to identify the source.
Automated tooling and detection patterns for JavaScript/TypeScript security vulnerabilities. Provides scan commands, vulnerability patterns, and severity mapping—not output formatting or workflow.
