E2E testing conventions for Protocol Designer and Labware Library using Playwright + pytest in e2e-testing/. Use when writing, running, or modifying end-to-end tests, page objects, or Playwright tests.
Vite demo and Playwright + Applitools tests for packed @opentrons JS packages in js-package-testing/. Covers components, shared-data, step-generation, and protocol-visualization. Use for integration testing, package linking, or visual testing.
Run and debug Agmente iOS end-to-end tests against a real local Codex CLI app-server instance. Use when validating Codex websocket/protocol compatibility, connect/initialize/thread flows, or reproducing Codex-only UI test failures with an actual local Codex server.
Run Agmente iOS end-to-end tests against a local Codex app-server endpoint, validate Codex thread/turn protocol flow, and perform mandatory cleanup.
Guide for running code style linters and formatters. Use this when asked to check code style, run linters, or fix formatting issues.
Guide for writing unit tests. Use this when creating tests to verify Python logic.
Clean Code principles (DRY, KISS, YAGNI), naming conventions, function design, and refactoring. Use when user says "clean this code", "refactor", "improve readability", or when reviewing code quality.
Review Java concurrency code for thread safety, race conditions, deadlocks, and modern patterns (Virtual Threads, CompletableFuture, @Async). Use when user asks "check thread safety", "concurrency review", "async code review", or when reviewing multi-threaded code.
Java security checklist covering OWASP Top 10, input validation, injection prevention, and secure coding. Works with Spring, Quarkus, Jakarta EE, and plain Java. Use when reviewing code security, before releases, or when user asks about vulnerabilities.
Create effective skills for OpenCode agents. Load FIRST before writing any SKILL.md. Provides required format, naming conventions, progressive disclosure patterns, and validation. Use when building, reviewing, or debugging skills.
模拟李工（后端工程师）在架构评审、发布流程、跨团队对齐场景下的工作方式与沟通边界。用于团队内部对齐与培训。
Write high-quality JUnit 5 tests with AssertJ assertions. Use when user says "add tests", "write tests", "improve test coverage", or when reviewing/creating test classes for Java code.
Sounding-first testing patterns for The Boring JavaScript Stack — one test() API, a Sails-centered trial context, worlds under tests/, JSON and Inertia request testing, mail capture, and browser-capable trials only when the browser truly matters. Use this skill when writing, configuring, or debugging tests in a Sails.js + Inertia.js application.
Apply repository-standard formatting to minimize diff noise and meet linter expectations.
Use Go AST-aware analysis to enumerate symbols, extract signatures, and propose mechanically safe refactors (read-only by default).
Diagnose configuration-related failures, enumerate required env vars, and guide safe local test setup (no secrets).
Propose minimal seams and local substitutes so tests run without real RDBMS/Redis/Mongo infrastructure.
Diagnose failures and propose minimal, test-backed fixes with verification and rollback instructions.
Run and triage Go tests with correct environment handling; produce compact, actionable failure summaries.
Get best practices for TUnit unit testing, including data-driven tests
Zero Script QA — test without scripts using structured JSON logging and Docker monitoring. Triggers: zero-script-qa, log testing, docker logs, QA, 제로 스크립트 QA.
Core rules for bkit — PDCA methodology, level detection, agent triggering, quality standards. Triggers: bkit rules, core rules, methodology, 핵심 규칙, PDCA 규칙.
Define coding rules, conventions, and standards for AI collaboration. Triggers: convention, coding style, lint, rules, 코딩 규칙, 컨벤션.
