Diagnose Explorbot test failures from Langfuse exports or log files.
npx skills add https://github.com/testomatio/explorbot --skill explorbot-debug
Please help me install this Agent Skill. Skill: explorbot-debug Source: https://github.com/testomatio/explorbot/tree/main/.claude/skills/explorbot-debug Command: npx skills add https://github.com/testomatio/explorbot --skill explorbot-debug
## What problem does it solve? This Skill helps developers and QA engineers diagnose why Explorbot test sessions fail by analyzing execution traces from Langfuse exports or log files to surface root causes and propose Knowledge fixes.
## Core Features & Use Cases
### Quick Start Start by providing one of the following inputs: a Langfuse JSON export file path, or confirm that I should analyze the latest session from output/explorbot.log. The skill will extract tool calls, prompts, and URL visits, diagnose failure patterns, and output a ready-to-save Knowledge file that encodes best practices for future runs. Save the recommended knowledge file to knowledge/<page_name>.md and apply it to subsequent Explorbot runs to improve reliability.
High-intent search queries and answers about installing and using this skill.
You diagnose failing Explorbot sessions by analyzing Langfuse JSON exports to identify failing tool calls, parse prompts, and surface root causes like missing context or wrong tool choices. This pinpoints exact failure points to guide debugging efforts.
Fix recurring failures from wrong prompts by analyzing execution traces to identify the pattern, then generating a targeted Knowledge file. This file encodes best practices to guide AI behavior and prevent recurrence in subsequent runs.
Yes, you can analyze recent sessions without a Langfuse export by parsing the latest logs from output/explorbot.log. This reconstructs the most recent session to extract tool calls, URL visits, and errors for root cause diagnosis.
Create a knowledge file by providing a Langfuse export or log file for analysis. The tool diagnoses failure patterns and outputs a ready-to-save Knowledge file, which you save to knowledge/<page_name>.md and apply to future runs.
Explorbot fails tests due to missing context when execution traces lack necessary data for tool calls. You identify this by analyzing Langfuse exports or logs to surface this specific pattern, then generating a Knowledge file to correct it.
Danik911Extracts Langfuse Cloud API traces, observations, and metrics for debugging, telemetry analysis, and audit trails.
jimmymalhanLog failures with fixes and preventative measures for future reference.
sammcjGuide AWS Strands Agents SDK and AgentCore deployments across Lambda, ECS/Fargate, and AgentCore Runtime.
89jobrienParse logs and analyze stack traces to diagnose errors across languages.
