Loading...
Loading...
Found 1,434 Skills
Investigate stuck runs and execution failures by tracing Symphony and Codex logs with issue/session identifiers; use when runs stall, retry repeatedly, or fail unexpectedly.
Inspect and debug KGF (Knowledge Graph Framework) specs — tokenize, parse, and extract edges from source files. Use when the user wants to debug language parsing, inspect how indexion processes a file, or verify KGF spec behavior.
698/645 electricity meter protocol serial port frame sending and parsing Skill, supporting frame assembly, sending, receiving, parsing and assertion verification, used for fast regression verification after bug fixing
This skill should be used when the user asks to "use marimo", "create a marimo notebook", "debug a marimo notebook", "inspect cells", "understand reactive execution", "fix marimo errors", "convert from jupyter to marimo", or works with marimo reactive Python notebooks.
ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace URL (e.g. /llm-observability/traces/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs.
CLI harness for RenderDoc graphics debugger capture analysis
Use this when you need to inspect iOS simulator or physical-device logs through CatPane's MCP server, including starting scoped captures, checking status, pinning relevant lines, and querying buffered logs.
E2E 시나리오 생성, 실행, 자동수정을 통합 처리하는 스킬. "시나리오 만들어줘", "시나리오 실행", "e2e 실행", "E2E 돌려", "시나리오 돌려", "시나리오 변환", "녹화 변환", "e2e 변환", "codegen 변환", "e2e 생성", "시나리오 생성", "시나리오 검증" 키워드로 트리거.
Report a bug in the compound-engineering plugin
This guide provides step-by-step instructions for recording Lynx performance traces. Use this guide when the user asks how to record a trace.
Remap the function_id:pc_index to the original source code position by provided debug info json file.
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