Use when writing a test case template, reviewing a batch of test cases for quality, or migrating cases between tools. Lists the ISO/IEC/IEEE 29119-3 and ISTQB test case fields, maps them to TestRail, Xray, Zephyr Scale, Allure TestOps and Qase, and gives a PASS, WEAK or FAIL review rubric.

Use when a suite has outgrown its value and someone is about to delete tests. Sorts candidates into duplicate, tautology, trivial, dead-signal and orphan, and deletes only when all four gate conditions hold, with a written reason, coverage evidence and a named reviewer.

Validates the statistical significance of an A/B / feature-flag experiment result - computes per-metric effect size + p-value (chi-square for proportions, Welch's t-test for continuous metrics), applies a multiple-comparison correction (Bonferroni / Benjamini-Hochberg) when N>1 metric, surfaces practical-vs-statistical-significance distinction, and emits a ship/don't-ship verdict per metric. Use when an experiment has finished and someone is about to ship the winning variant off a dashboard readout, when a result rests on a small sample, or when more than one metric was compared - the rigorous version of "the variant looks better in the dashboard."

Use when a PRD, design doc or product brief must be turned into testable non-functional requirements. Extracts performance, accessibility, security, i18n, reliability and observability needs as threshold-bound assertions, each mapped to its measurement source (Lighthouse, axe, OWASP ASVS, WCAG).

Use when a team has no Definition of Done, wants to revise it, or is about to mark a story or PR done without checking it. Drafts a starter DoD and a per-PR checklist, and audits work line by line against an existing DoD with repository evidence, never on self-attestation.

Use whenever HTTP, WebSocket or gRPC load tests should be written in JavaScript with k6, or a k6 threshold passes but the system still feels slow: VU scripts with checks, stages for ramps, thresholds on p95 latency and errors as the CI gate, and how to read tail latency and coordinated omission.

Use whenever a GraphQL query fires one database query per item (N+1), a slow-query alert traces to GraphQL, or a PR adds a list resolver: find the fan-out, write a test that counts queries, and fix it with DataLoader batching, parent projection or selection-set prefetch.

Use when a game must hit a frame-time or memory budget before a milestone or platform cert, or a change needs a performance regression check. Profiles with Unity Profiler and Performance Testing or Unreal Insights, sets 16.6 ms and 33.3 ms budgets, adds CI perf tests and reports per SKU.

Use when tests must prove a request produces the expected spans across services in a running Jaeger, Zipkin or Grafana Tempo backend. Runs the backend in CI, queries traces by service and operation, and asserts on spans, parent-child links and durations.

Use whenever Qt C++ code needs unit or GUI tests in-process: Qt Test entry macros, private-slot test functions, QVERIFY, QCOMPARE and data-driven QFETCH, simulated mouse, key and touch events, QSignalSpy, QBENCHMARK and JUnit XML output for CI, including Qt Quick and QML logic.

Use when a Windows desktop app needs UI tests from C# or .NET with in-process UI Automation calls: FlaUI UIA2 and UIA3 packages, launching or attaching to the app, ConditionFactory locators, Retry waits and xUnit, NUnit or MSTest. For the WebDriver protocol use winappdriver.

Use when Jupyter notebooks must run in CI as tests, their outputs must stay stable, or a PR adding notebooks needs review. Wires papermill parameterized runs, nbval output checks, testbook unit tests, nbstripout and artifacts into GitHub Actions, plus a review checklist with a BLOCK or PASS verdict.

Use whenever user stories, acceptance criteria, manual test steps or a spec section need to become Gherkin .feature files. Maps criteria to scenarios, finds Scenario Outlines and Background, reuses existing steps and flags hidden preconditions. Writes Gherkin only, not step code.

Use whenever an app uses self-hosted Keycloak and needs integration tests: a throwaway Keycloak per test class via Testcontainers, realm JSON imports, OIDC discovery, token and introspection endpoints, the admin REST API, password, auth-code, client-credentials and token-exchange flows, and UMA.

Use when a stateful REST API (resources created, read, changed and deleted in sequence) needs fuzzing that finds multi-step bugs stateless fuzzers miss. Runs Microsoft RESTler from an OpenAPI spec (compile, test, fuzz-lean, fuzz) and reports 5xx errors, resource leaks and hierarchy violations.

Use when a feature needs manual screen-reader testing before sign-off: step-by-step scripts for NVDA, JAWS, VoiceOver or TalkBack with keystrokes and expected announcements, WCAG 2.2 checklists per page type, widget keystroke matrices and a guided session with a signed report.

Produce a rigorous, verified, fully-cited research report on ANY topic by running a disciplined five-stage pipeline: CLARIFY the question, PLAN (an editable research plan), FAN-OUT parallel search subagents, VERIFY every key claim (cross-source + adversarial + cross-model), then SYNTHESIZE a cited report. Use this WHENEVER the user wants real research rather than a quick answer — "research X", "do a deep dive on Y", "write me a report / brief / literature review on Z", "compare A vs B and back it with sources", "what's the state of the art in …", "investigate …", "find evidence for/against …", "give me a market/landscape/competitor analysis", or any question where being wrong is costly and the answer needs citations. Trigger even when the user does not say the word "research" but clearly needs multi-source, fact-checked, cited output. This is the general-topic web-research orchestrator — not the codebase-to-wiki `deep-research` skill. For a fast single-fact lookup, answer directly instead.

Use when a learner wants to start, work through, or be guided or tutored through the Reviewing your changes with tessl change review lesson — reviewing their own diff with reviewer skills. Walks them one step at a time through making a change, running tessl change review with a code-review skill, reading the summary subheading, inline hunk comments, and unplaced findings, and emitting the result as JSON for a GitHub caller, running a check after each step before moving on. Triggers on asks like guide me through reviewing my changes with tessl change review, start the change review lesson, or how do I review my diff with a reviewer skill.

Standardize the current GitHub repository's durable project context for coding agents by default. Use when asked to create or update AGENTS.md routing, scaffold or normalize docs/ project documentation, separate consumer README content from contributor/developer docs, or apply a reusable repo documentation convention with root README.md, CONTRIBUTING.md, RELEASE.md, and docs/README.md.

Triage many open GitHub PRs at once — for each PR, check its CI verdict and mergeability, then merge (with admin bypass + squash fallback) or close, in bulk. Use when the user wants to clean up a queue of stale PRs ("close all the old Snyk PRs", "merge anything green and close anything red", "process all the dependabot PRs across my repos") spanning more than a handful of PRs. Trigger on phrases like "go through all my open PRs", "merge or close them all", "clean up the PR backlog", "any PR that's failing CI / unmergeable / stale", or when the user wants the same per-PR decision rule applied to a list of PRs. Sibling skill to `gh-bulk-repo-edit`, but the surface is PR state changes (merge / close / leave), not file contents.