Testing Skills

Use for bun:test syntax, assertions, describe/it, test.skip/only/each, and basic patterns.

Use for test lifecycle hooks: beforeAll, afterAll, beforeEach, afterEach, fixtures, preload.

NautilusTrader developer guide for contributing, building from source, testing, and extending the platform. Use this skill for NautilusTrader development setup, Rust/Python integration, testing practices, and contribution guidelines.

| Interactive code simulation engine that spawns ghost personas to review your code before it ships. Each ghost walks through your code line-by-line from a idempotency), The Enterprise Edge (business logic gaps, multi-currency, B2B tax exemptions, locale), Chaos Monkey (timeouts, partial failures, network partitions, OOM). Produces a chaos timeline, structured bug report with severity ratings, and three resolution tiers (quick fix, robust architecture, generated test suite). Use this skill whenever the user mentions code review, PR review, "find bugs", "what could go wrong", "will this break", "is this safe", "stress test", "edge cases", design review, pre-merge check, dry run, chaos test, or wants a second opinion on any code — even if they don't explicitly ask for "ghost personas" or "simulation". Also trigger when someone pastes a code snippet with any question about its correctness or safety.

Turn long videos & livestream VODs into viral vertical shorts, 100% locally — on-device transcription, LLM highlight detection, 9:16 reframe with karaoke captions, and a per-clip render-QA report. Use when the user asks to clip / cut / 切片 / 剪 a long video, podcast or stream replay into short clips, find highlights / 爆点 in a video, or transcribe a media file. Footage never leaves the machine.

基于张海燕四步审查法+何力/常金光三观分析法，对合同进行深度审查。支持企业核验、多语言自动检测、Mermaid业务流程图、二段式审核意见、合同概览、客户可读合同编号、业务摘要、22类合同专项审查、续约提醒和 Word 修订模式审核红线稿。飞书正式交付物必须包含问题卡片列表和业务流程图；用户选择修订模式时，以原合同为只读来源，先生成 redline-plan.json，再运行 scripts/redline/apply_redline_plan.py 生成带真实修订痕迹和批注的 Word 审核修订稿，并完成红线 QA。其他记录保存为本地 Markdown。

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance (LCP/CLS/INP), or verify visual output with real runtime data. Complements Playwright — use this for live debugging and performance work, Playwright for stable E2E test suites.

Opens the running app in a browser and verifies recent UI changes actually work. Use whenever the user wants a quick smoke test or sanity check of recent work, or says "go", "open in browser", "check in browser", "test your work", "make sure it works", "smoke test", "verify", "did it actually work", "make sure the form/page works", "check the form submits", "works on mobile" — even when they don't explicitly ask for browser testing. Also activates implicitly when the user appends "...and make sure it works" to a UI request. Skips design critique; for that, use go-ui.

Use when creating, writing, fixing, or reviewing tests in a Flutter project. Covers unit tests, widget tests, integration tests, Riverpod provider testing, and Mockito mocking. Provides Given-When-Then patterns, layer isolation strategies, and test setup for GetIt, SharedPreferences, and FakeDatabase.

> Author useful, low-noise log alerts on services in a PostHog project. Use when the user asks to set up alerts for their logs, suggest alerts they should add, or evaluate whether a service is worth monitoring. Covers service triage, baseline characterisation, threshold drafting, back-testing via simulate, and shipping with a notification destination.

> Focused Signals scout for PostHog projects using error tracking. Watches `$exception` bursts, stuck loops, multi-fingerprint clusters, status regressions, and stack-trace activity-name patterns. Emits findings only when they clear the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet — no dependencies on other skills.

> Focused Signals scout for PostHog projects collecting Content Security Policy (CSP) violation reports. Watches `$csp_violation` events for fresh blocked-URL clusters, per-directive bursts, page-scoped regressions after deploys, and suspicious third-party domains that may indicate a compromised script. Emits aggregated findings only when a cluster clears the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet — no dependencies on other skills.

Audits and repairs Markdown link health across a skills repo via a four-tier pipeline (config hardening, intra-repo file-ref fixes, external URL substitutions, residual exclusions) and enforces a Tier 3 substitution guardrail that prevents regressions of previously-passing links; designed for lychee-based GitHub Actions link checkers but generalizes to markdown-link-check and similar tools. Use when the request mentions link audit, dead links, link health, lychee, broken links, link checker, markdown link audit, link-health audit, 404 audit, check-links failing, CI link-check, or 連結健檢, 死鏈, 失效連結, 斷鏈檢查. Part of the AlterLab Academic Skills suite.

Submits and tracks protein-testing experiments on the Adaptyv Bio Foundry cloud lab (wet-lab validation), and optimizes protein sequences before submission with computational tools (NetSolP, SoluProt, SolubleMPNN, ESM). Use when designing proteins that need wet-lab validation - binding/affinity screening, expression testing, thermostability, or fluorescence assays - or when submitting experiments to the Foundry API, browsing the target catalog, tracking experiment status, retrieving results, or pre-screening sequences for solubility/expression. Triggers on "Adaptyv", "Foundry API", "cloud lab", "biolayer interferometry / BLI", "wet-lab validation". Part of the AlterLab Academic Skills suite.

Runs time series machine learning with the aeon library — classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search via scikit-learn compatible APIs. Use when working with temporal data, sequential patterns, or time-indexed observations (univariate or multivariate) that need specialized algorithms beyond standard ML approaches. Part of the AlterLab Academic Skills suite.

Enforces statistical-test selection as a discipline, holding the Iron Law NO TEST CHOSEN AFTER SEEING THE P-VALUE: routes the choice through a fixed decision tree (outcome type -> groups -> paired? -> normality) terminating in named tests (t-test, Mann-Whitney U, ANOVA, Kruskal-Wallis, Wilcoxon, Friedman, chi-square, Pearson/Spearman, regression), gates interpretation behind a mandatory Shapiro-Wilk/Levene/linearity assumption check, blocks test-shopping with an Excuse-vs-Reality table and Red-Flags-STOP list, and applies a 3+-tests escalation gate forcing Bonferroni/FDR correction or an exploratory label. Use when choosing or switching a statistical test, asking which test to run, dropping a test after a non-significant result, or running many tests hunting for significance. For executing the chosen test prefer alterlab-statistical-analysis or alterlab-statsmodels; for the broader frozen-plan discipline see alterlab-preregistration-discipline. Part of the AlterLab Academic Skills suite.

Fits and reports mixed-effects / multilevel / hierarchical models for clustered, nested, longitudinal, and repeated-measures data — random intercepts and slopes, variance components and the ICC, cross-level interactions, and GLMMs (logistic/Poisson) — using statsmodels MixedLM and bambi (Bayesian on PyMC) in Python, or the field-standard R lme4 / glmmTMB / brms via Rscript. It enforces the reporting items reviews find under-reported: full fixed + random specification, centering, variance components + ICC, estimation method, assumption checks, model comparisons, and effect sizes. Use when data are grouped/nested (students in schools, repeated measures, panel/longitudinal) and the question concerns within- vs between-cluster variation. For general single-level regression prefer alterlab-statsmodels; for panel fixed effects used for causal identification prefer alterlab-causal-inference. Part of the AlterLab Academic Skills suite.

Handles missing data with principled methods — forces an explicit MCAR / MAR / MNAR mechanism statement, then applies multiple imputation by chained equations (MICE) with Rubin's-rules pooling of estimates and standard errors, or full-information maximum likelihood (FIML) where a likelihood/SEM model applies. Uses statsmodels MICE / MICEData in Python or the field-standard R mice via Rscript, and warns that single (mean/regression) imputation and scikit-learn's IterativeImputer return one completed dataset without Rubin's-rules pooling, so they understate standard errors if used as multiple imputation. Use when a dataset has missing values, when choosing an imputation strategy, or when reporting how missingness was handled. For general modeling on complete data prefer alterlab-statistical-analysis; for latent-variable models with FIML prefer alterlab-sem-psychometrics. Part of the AlterLab Academic Skills suite.

Fits and evaluates measurement models — confirmatory factor analysis, full structural equation models, exploratory factor analysis, item response theory, and multi-group measurement invariance — using the verified Python stack: semopy (model syntax =~ / ~ / ~~, Model.fit, inspect(std_est=True), calc_stats for CFI/TLI/RMSEA), factor_analyzer (EFA, KMO, Bartlett, ConfirmatoryFactorAnalyzer), and pingouin/girth, computing McDonald's omega from standardized loadings and judging fit against Hu & Bentler cutoffs. Use when the request mentions confirmatory factor analysis, structural equation modeling, a latent variable or construct model, factor loadings, IRT, or measurement invariance across groups. For deciding whether a scale is trustworthy at all prefer alterlab-ssci-measurement-gate; for plain regression prefer alterlab-statistical-analysis. Part of the AlterLab Academic Skills suite.

Routes a social-science study to its research design — true experiment, quasi-experiment (difference-in-differences, instrumental variables, regression discontinuity, interrupted time series, fixed effects), observational/correlational, qualitative, or mixed — by walking the random-selection and random-assignment decisions, then PINS the identifying assumption the causal claim will rest on (parallel trends, exclusion restriction, continuity at the cutoff, selection-on-observables, or qualitative saturation logic) before any analysis begins. Use when choosing a study design, asking what design to use, framing a causal question from observational data, or deciding experiment vs quasi-experiment vs observational. For executing the analysis prefer alterlab-statistical-analysis; for qualitative design depth prefer alterlab-qualitative-methods; for choosing the statistical test downstream prefer alterlab-test-selection-guard. Part of the AlterLab Academic Skills suite.

Verify publication figures with a render-then-check QA pass — data-fidelity against every underlying row, axis/label floor-and-ceiling legibility, bounding-box collision detection for overlapping text/markers, and 300-dpi print-readiness. Use when proofing or auditing a finished figure for correctness and print quality, catching mislabeled or overlapping elements, or confirming a plot faithfully represents its data before submission. For CREATING the plot prefer alterlab-matplotlib (or alterlab-seaborn / alterlab-plotly); for multi-panel publication layout prefer alterlab-scientific-viz; for schematic diagrams prefer alterlab-scientific-schematics. Part of the AlterLab Academic Skills suite.

Use test-driven development for behavior-changing feature or fix work, and whenever the user mentions TDD, test-first, red-green-refactor, tracer bullets, integration tests, or public-interface behavior tests. Skip for docs-only, path-only rename, formatting-only, or purely mechanical chores unless explicitly requested.

Create outbound phone calls, web calls, and batch calls using the Vapi API. Use when making automated calls, testing voice assistants, scheduling call campaigns, or initiating conversations programmatically.

> AI-powered visual QA testing that walks through an app in the browser, records every action with annotated captions (what was done, what should happen), captures screenshots/GIFs, and sends the evidence to Gemini for automated review. Catches UX misalignments, broken flows, missing states, and edge cases that traditional tests miss. Can use Agent Teams for parallel "check the ui", "record a test", "walk through the app", "e2e test", "end to end test", "catch edge cases", "gemini review", "screen test", "ux test", "visual regression".

>- Complete methodology for computing publication-quality cumulative abnormal returns with proper event-study test statistics, matching the robustness of Kaspereit's eventstudy2 for Stata. Covers dateline construction, event-date mapping, estimation and event windows, thin-trading adjustment, OLS with Theil prediction error correction, abnormal return computation, CAR/CAAR/AAR accumulation, boundary contamination guards, and common tests such as Patell, BMP, Kolari-Pynnonen, generalized sign, Wilcoxon, and GRANK-T. Use when the user mentions abnormal returns, event windows, market-model regressions, CARs, CAAR, AAR, eventstudy2, thin trading, trade-to-trade returns, or event-study test statistics.

>- Set up, format, fix, and clean up LaTeX regression and estimation tables in empirical economics or finance papers. Use when (a) creating a .tex, results.tex, main.tex, or preamble to display regression or estimation output from Python (pyfixest), Stata, or R — including any mention of estout, esttab, estauto, estwide, or table fragments; (b) formatting or repairing estout-style regression tables that overflow the right margin, have cramped or boxed notes, misaligned columns, or poor significance stars, or when asked to match a reference paper, make the note fill the table width, or choose among \estwide, \estauto, and landscape layouts; (c) diagnosing "Misplaced \omit" errors from \input-ed table fragments inside tabular environments. Covers \@@input, \estwide, \estauto, \estautoLT, \specialcell, \sym, minipage notes below tabulars, and the convert-and-verify workflow. Do NOT trigger for general LaTeX documents like beamer presentations, problem sets, letters, or CVs.

| pyfixest demeaner_backend="cupy64" (including its CPU fallback when cupy is absent) is NOT numerically identical to the default numba backend and does adding demeaner_backend="cupy64" to existing pf.feols/fepois calls changes the printed coefficient table, (2) a regression report suddenly gains rows with absurd estimates (e.g. coef 435.8, SE 7106) for controls absorbed by the fixed effects, (3) diffing outputs before/after a backend change, or (4) anything parses a pyfixest text report by line position.

| Diagnose and fix slow pyfixest regression GRIDS (many feols/fepois calls run sequentially) that stay slow despite demeaner_backend="cupy64" and an idle panel takes ~1 min/model, (2) process inspection shows ~1-1.5 cores busy and nvidia-smi shows ~0% GPU utilization with a resident cupy context, (3) planning any worker prompt that will run a model grid (robustness variants x fixed costs (formulaic model-matrix build, interaction construction, singleton detection, cluster vcov) dominate wall time; GPU demeaning is a pyfixest multiple-estimation syntax; mandate this IN THE WORKER PROMPT.

> Expert guidance for systematic backtesting of trading strategies on Indian markets (NSE/BSE). Use when developing strategies, testing robustness, avoiding overfitting, or validating trading ideas.

Automate the full Jira bug-fix pipeline end-to-end. Use when the user says 'fix ticket', 'fix PROJ-123', 'fix this bug', 'resolve PROJ-XXX', 'fix and ship this ticket', or passes a Jira ticket ID for autonomous bug resolution. Reads the Jira ticket, implements the fix, reviews it, commits, moves the ticket to QA, assigns to QA engineer, and comments with a summary. Also use when the user wants to automate the fix-review-commit-handoff cycle for any Jira bug ticket.

Scan all unresolved Sentry errors, group by root cause, fix in batch with TDD, and resolve in Sentry after deploy. Use when the user says 'fix sentry errors', 'scan sentry', 'resolve sentry issues', 'fix all errors', 'sentry cleanup', or wants to proactively fix production errors from Sentry monitoring.

Map testable surfaces, audit existing tests for quality, and write test specifications that prevent AI shortcuts. Use when asked to "audit tests", "specify tests", "test architect", "map test coverage", or invoke /test-architect. Two modes — audit (evaluate existing tests against Beck's principles) and specify (write test specs for new code). Powered by Carmack × Beck quality-testing.md reference doc. Stack: Next.js App Router / TypeScript / Vitest / Cypress / tRPC / Prisma / Neon.

AI Native 产品方法论——价值发现循环的实操 Skill。 用户提供已上线或正在验证的 AI 产品，Skill 自动执行价值发现流程： 价值信号识别 → 伪价值排除 → 价值密度评估 → 市场测试设计 → 定价策略联动 → 方向修正建议 → 输出价值发现方案。 基于《AI Native 产品方法论》第22章。 '

AI Native 产品方法论——产品形态探索的实操 Skill。 用户提供能力实验结论，Skill 自动执行产品形态探索： 能力边界分析 → 交互原型设计 → 工作流嵌入测试 → 产品形态判断 → 输出产品形态建议。 基于《AI Native 产品方法论》第07章（试验展开-产品形态探索）。 '

Omni-expert principal software architect. Triggers on requests for app development, coding, refactoring, or architectural design. Enforces clean code, clean architecture, deep reasoning, mandatory testing, and strict anti-ambiguity protocols.

Omni-expert principal software architect. Triggers on requests for app development, coding, refactoring, or architectural design. Enforces clean code, clean architecture, deep reasoning, mandatory testing, and strict anti-ambiguity protocols.

Plan, run, and synthesize usability tests: test plan, tasks, script, findings, recommendations.

Enforce OOP and DDD engineering constraints for C# and TypeScript game development. Use when implementing, refactoring, reviewing, or verifying gameplay systems, domain-controlled engine-view wrappers, domain models, aggregates, application services, repositories, public APIs, or Context-based shared dependencies. Preserve encapsulation, avoid test-only production hooks, unit-test only engine-agnostic leaf logic, and verify integrated behavior by running the real engine.

性能基准测试

Quality validation gates for Agile V agents. Adds interface validation, test quality checks, data type awareness, and time allocation guidance to prevent common failure patterns identified in comprehensive testing.