Toolverse
All skills
Testing

debug-e2e

by AztecProtocol

Interactive debugging for failed e2e tests. Orchestrates the debugging session but delegates log reading to subagents to keep the main conversation clean. Use for ping-pong debugging sessions where you want to form and test hypotheses together with the user.

Installation

Pick a client and clone the repository into its skills directory.

Installation

Quick info

Author
AztecProtocol
Category
Testing
Views
5
GitHub repo

About this skill

Interactive debugging for failed e2e tests. Orchestrates the debugging session but delegates log reading to subagents to keep the main conversation clean. Use for ping-pong debugging sessions where you want to form and test hypotheses together with the user.

How to use

  1. Uruchom umiejętność poleceniem /debug-e2e wraz z identyfikatorem: hash logu CI (np. 343c52b17688d2cd), numer PR (np. #19783), URL CI, lub nazwę testu (np. epochs_l1_reorgs). Jeśli nie podasz argumentu, system zapyta Cię, co chcesz debugować.

  2. Narzędzie automatycznie wyśle żądanie do pomagiera identify-ci-failures, który pobierze logi i zidentyfikuje miejsca awarii w teście.

  3. Na podstawie zwróconego podsumowania sformułuj hipotezę dotyczącą przyczyny błędu — może to być błąd logiki, zła konfiguracja, czy problem z czasowaniem.

  4. Jeśli potrzebujesz głębszej analizy konkretnego logu, poproś pomagiera analyze-logs o szczegółowe badanie wybranych fragmentów.

  5. Pracuj iteracyjnie z systemem: testuj hipotezy, porównuj wyniki udanych i nieudanych przebiegów, aż zidentyfikujesz przyczynę.

  6. Nie używaj tego narzędzia do oczywistych błędów asercji (widocznych w output testu), błędów kompilacji czy prostych problemów konfiguracyjnych — w tych przypadkach debuguj kod bezpośrednio.

Related skills

dependency-upgrade

by wshobson

Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.

Testing
17138

langchain

by zechenzhangAGI

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering

Testing
21123

pair-trade-screener

by tradermonty

Statistical arbitrage tool for identifying and analyzing pair trading opportunities. Detects cointegrated stock pairs within sectors, analyzes spread behavior, calculates z-scores, and provides entry/exit recommendations for market-neutral strategies. Use when user requests pair

Testing
994

ppt-creator

by daymade

Create professional slide decks from topics or documents. Generates structured content with data-driven charts, speaker notes, and complete PPTX files. Applies persuasive storytelling principles (Pyramid Principle, assertion-evidence). Supports multiple formats (Marp,

Testing
2739

webapp-testing

by anthropics

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Testing
130255

lean4-theorem-proving

by cameronfreer

Use when developing Lean 4 proofs, facing type class synthesis errors, managing sorries/axioms, or searching mathlib - provides build-first workflow, instance management patterns (haveI/letI), and domain-specific tactics

Testing
9108