Qe — Testing & QA agent for Claude Code
Performs functional and acceptance testing against the task spec — Julia Pkg.test (CPU always, CUDA/GPU when required), JuliaFormatter check of touched files, documentation of public API changes, benc.
How to install Qe
Installs to ~/.claude/agents/zinoex-intervalmdp.jl-qe.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Zinoex/IntervalMDP.jl/HEAD/.claude/agents/qe.md -o ~/.claude/agents/zinoex-intervalmdp.jl-qe.md Restart Claude Code, or start a new session, for it to be picked up.
What Qe does
name: qe description: Performs functional and acceptance testing against the task spec — Julia Pkg.test (CPU always, CUDA/GPU when required), JuliaFormatter check of touched files, documentation of public API changes, benchmark evidence for performance specs. Use during the QE stage of the harness workflow, after Dev and Formal Verification. tools: Read, Write, Edit, Bash, Glob, Grep
You are the QE Agent. Independently test the implementation produced by Dev in the **target root** named
Alternatives in Testing & QA
- Council Bezos — The strategy and decisions seat on the Roast Room council 281 ★
- Evaluator Cosmwasm Agent — CosmWasm smart-contract vulnerability evaluator — spawned per smart_contract surface with chain_family=cosmwas 97 ★
- Stagehand Expert — Use this agent when you need executable Stagehand test files for TDD workflow 52 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Product Docs
Creates and updates process docs, templates, decision artifacts, and agent specs. TRIGGER when: (1) task adds
Salesforce Test Engineer
Identifies required test cases before implementation and writes/updates Apex test classes (positive, negative,
Manual QA
Use when a change needs to be exercised in a real running app — not unit tests, but a human-style check of the
Doc Validator
Use when a brainstorming spec names or implies any library, SDK, framework, language version, or external API
Langertha Worker
Default Langertha worker — implement, refactor, debug, and test code in this distribution. Pre-loaded with the
API Exploratory Tester
Performs spec-aware, contract-aware session-based exploratory testing of a live API — REST or GraphQL — given
Related Skills
GPU Server Setup
Agent skill that prepares a Linux server with NVIDIA GPUs for LLM workloads - driver and CUDA, Docker with NVI
GPU Check
Check GPU availability + driver version — ROCm untuk AMD RX 6700S, CUDA untuk NVIDIA GTX 1650.
Bonsai AI Deploy
Deploy Bonsai-2-27B (ternary 27B, 5.95GB) on a single 8GB consumer GPU via an AI agent. 用 AI 部署 Bonsai-2-27B:一