Testing Skills

> data problem, explore and audit datasets, run defensible statistical analysis, build and validate predictive models, and turn results into decision-ready reports. Use this skill whenever the user asks to analyze, explore, or profile a dataset or CSV/Parquet/Excel file; asks what drives a metric or why a number changed ("why did churn go up?"); wants to test whether a difference is real (A/B tests, experiments, "is this significant?", "how many samples do I need?"); wants a predictive model (churn, forecast, scoring, segmentation, classification, regression); asks to review an existing analysis, notebook, or model for flaws; or needs analysis results written up for decision-makers — in any language ("phân tích dữ liệu", "xây model dự đoán", "kiểm định A/B"), even when they never say "data science" or "statistics".

Look at real hardware, screens, panels, and wiring on a desk or workbench through a camera, so Claude can SEE physical output that no unit test, log, or API can. Use whenever the user says "are you seeing this?", "olha isso", "look at this", "watch this", "can you see...", "check the camera", "look at the screen" / "look at the display", "is this wired right?", or "what's this part?"; asks to visually verify a rendered display, LCD, LED, or panel; wants a wiring, polarity, or voltage-rail check before power-on; or needs to confirm a font, layout, clipping, or on-screen value renders correctly instead of trusting green tests. Grabs the current camera frame(s) and reads them; supports a watch mode for an action in progress. Needs a snapshot-capable camera reachable over HTTP (Android IP Webcam app, Raspberry Pi camera-streamer, or any snapshot URL) set via CCE_CAM_URL.

> Disciplined debugging methodology. Triggers on bug reports, test failures, "debug this", "diagnose this", unexpected behavior, build failures, integration issues, or performance regressions. Find root cause before a permanent corrective fix; contain urgent harm safely first.

> Execute an approved Spec-backed Plan from plan.json. Uses task tracking when useful, enforces TDD, and reports between batches. Trigger when the user says "implement", "go", "start", or "do it" after approving a persisted plan. Do NOT use without an approved Spec-backed Plan.

Use when a coding agent must design, scaffold, implement, or verify an iOS or macOS SwiftUI interface with Apple-platform state, accessibility, availability, testing, and Xcode evidence.

> Application Security Engineer role bundle for security design, testing, and code review of applications. Orchestrates new application reviews, PR security reviews, API security assessments, and AI feature security reviews. Auto-invoked when the user needs help with application threat modeling, secure code review, API security testing, or evaluating the security of LLM-powered application features.

Full-lifecycle guide for implementing a feature end-to-end in a London-school DDD Swift/iOS codebase (or any layered Domain/Infrastructure/App project that uses protocol + concrete impl aggregates, narrow infrastructure ports, and Chicago-school state-based TDD). Use this skill whenever the user asks to **build**, **implement**, **add**, **ship**, or **develop** a feature — including vague asks like "let's add X", "build me Y", "implement Z", or "wire up the W flow". Strongly prefer this skill over jumping straight to code whenever a new domain concept is in play. Each lifecycle phase has its own focused sub-guide so the agent loads only the instructions for the current task, not a 600-line monolith.

Comprehensive E2E + Security Tests for Vercel Preview Deployments. Combines Playwright automation with Claude-in-Chrome MCP for interactive debugging. Activate on PR creation, before merge, or manual /preview-test.

Formal Quality Assurance Checklist before every Merge/Deploy. 6-phase validation with Build Verification, Test Suite, No-Touch Zones, Region Check, Security Review, and QA Report generation. Activate on "merge", "deploy", "release", "production", or /qa command.

Erzwingt striktes Test-Driven Development mit Red-Green-Refactor Zyklus. Blockiert Code-Generierung ohne vorherige Tests. Dokumentiert 13 ungueltige Rationalisierungen. Aktivieren bei neuen Features, Bug Fixes, Refactoring.

Develop, test, build, and deploy Godot 4.x games. Includes GdUnit4 for GDScript unit tests and PlayGodot for game automation and E2E testing. Supports web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.

Test web applications comprehensively for quality. Performs functional, integration, and user experience testing of web applications.

Build autonomous game-playing agents using AI and reinforcement learning. Covers game environments, agent decision-making, strategy development, and performance optimization. Use when creating game-playing bots, testing game AI, strategic decision-making systems, or game theory applications.

Request peer review with proper context and preparation. Structures review requests with clear description of changes and testing status.

Validate quality before completing tasks. Performs verification checks, testing, and quality assurance before marking work complete.

Expert product discovery guidance for user research and problem validation. Use when conducting user interviews, validating problems, applying jobs-to-be-done framework, sizing opportunities, customer segmentation, competitive analysis, prototype testing, usability testing, designing surveys, or synthesizing research insights. Covers discovery sprints, continuous discovery, and research operations.

> Load this skill whenever you are filing, reviewing, or generating accessibility bug reports — whether from automated tool output, manual testing, user reports, or testing with disabled people. The purpose of this skill is to make accessibility findings easier to report accurately, connect them to real people and tasks, and let developers reproduce, understand, and fix them without unnecessary back-and-forth. Absolutely always describe the barrier and its task impact before citing a WCAG criterion. Under no circumstances guess a disability diagnosis, treat automated tool output as a conformance conclusion, or expose secrets/personal data in a report.

> Load this skill whenever you are planning, executing, or reviewing manual accessibility testing. Manual testing with real assistive technologies is essential — automated tools catch only ~30–40 % of WCAG issues. Absolutely always include keyboard-only testing and at least one screen reader test before marking a feature accessible. Under no circumstances skip forced colors mode testing for UI components.

Explains Cypress tests (E2E and component tests), and answers questions about Cypress use and behavior. Use when the user asks to explain how a test works, explain how Cypress works, review or critique a test without writing code. Apply even when the user does not say 'Cypress' (e.g. 'explain this test'). Prefer the cypress-author skill when the user wants to create, fix, or update tests.

Creates, updates, and fixes Cypress tests (E2E/end-to-end and component tests). Use when the user asks to create tests, add tests, write tests, update tests, test this file/component, new spec, or fix a failing or flaky test. Apply even when the user does not say 'Cypress' (e.g. 'create tests for this file'). Prefer cypress-explain when the user only wants to explain or review tests without changing code.

All-in-one fullstack dev engine. /aura: 46 modes (build/fix/clean/deploy/review/spec/lore/ax/experiment/payment/debug/qa/orchestrate/escalate+), 6-layer security with 32 hooks, tiered models (ZERO/ECO/PRO/MAX), 8 languages, 16 specialized agents, SPEC/EARS/TRUST5/XLOOP/RALF/Autopus absorbed. ~55% token savings.

Survey a codebase as a senior advisor and turn the highest-value findings into implementation plans for other agents to execute — strictly read-only on source code, never implements anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, architecture, migrations, DX), suggest features or roadmap direction, or generate handoff plans for another agent to implement.

Use when making user-facing UI changes and you want automated screenshot walkthroughs, or at release time to compare visual changes between releases and prioritize what needs human review. Requires Playwright.

Use when selecting, implementing, or stress-testing the causal identification strategy for an empirical economics manuscript — difference-in-differences (including staggered designs), instrumental variables (including weak-IV-robust inference), regression discontinuity, synthetic control, or shift-share / Bartik. Apply before writing the introduction or results.

Use when constructing or revising regression tables, descriptive statistics tables, or figures after results are estimated and before submission for an AER, AER:Insights, or AEJ manuscript. Implements AER booktabs house style, regression-table layout, and figure-note conventions.

| Adversarial breaker that reviews code by trying to make it fail, not by confirming it works. Hunts the unhappy paths — the malformed input, the empty string, the reversed range, the race condition — that the happy-path reviewer never types. Sounds like a gleeful adversary who thinks in inputs nobody intended and assumes everything is broken until a concrete attempt to break it comes up empty. Not a QA checklist — a hostile witness for the failure that hasn't happened yet. A lens for any checkpoint — brainstorm, design, plan, implement, debug, or review — not just a test gate. for "I tried to break it and couldn't," or nobody has named the input that makes this fall over — any time the worry is "how does this fail, and where are the edges?"

> Use when verifying that completed work actually works. Auto-surface during /verify mode, post-implementation review, or before claiming a task is done. Teaches the discipline of testing outcomes vs implementation, the unit/integration/smoke gradient, and what "done" actually means.

Creates code-based evaluators for LangSmith-traced agents. Use when building custom evaluation logic, testing tool usage patterns, or scoring agent outputs programmatically. Triggers on requests to evaluate agents, create evaluators, or run experiments against LangSmith datasets.

Turn a validated Next.js reproduction and canary verification into the smallest appropriate regression test in vercel/next.js. Use when a confirmed issue needs a focused test that proves the reported behavior and fits the existing Next.js test suite.

Implement and validate the smallest correct fix for a confirmed issue in vercel/next.js after reproduction, canary verification, and regression-test work. Use when a focused failing Next.js regression test exists and the product code must be corrected without weakening that test.

Locate the introduction or fix boundary for a validated Next.js regression using releases or commits and an executable reproduction. Use after reported-version-versus-canary verification when a vercel/next.js maintainer needs the last unchanged and first changed version or commit.