Assembles a multi-step end-to-end user-journey test from a list of high-level user intents - translates each intent ("user signs up", "user adds product to cart", "user completes checkout with promo code") into the corresponding test-runner step (Playwright / Cypress / Selenium / Karate), wires shared state across steps via test fixtures, and emits the resulting test as a single Scenario in the project's E2E framework. Use when scaffolding an E2E test that exercises a complete user flow rather than a single page.

Reads Real User Monitoring data (Datadog RUM, Sentry Performance, GA4 Core Web Vitals / CrUX) to identify high-traffic user journeys that have no synthetic monitor coverage: ranks journeys by session volume times business value, diffs the ranked list against existing synthetic monitors, and emits a prioritized gap list ready to feed into synthetic-monitor-author. Use when an observability stack has RUM instrumented but the team suspects synthetic coverage is sparse, biased toward low-traffic paths, or was never systematically derived from real usage data.

Reads a user story, PRD section, or feature spec and emits well-formed acceptance criteria as Given/When/Then steps in Gherkin (Feature/Scenario file format) or as a numbered plain-text list. Identifies missing-precondition gaps and proposes Background blocks for shared context. Use after a story is testability-confirmed and before implementation begins.

Wraps Vercel Edge Runtime testing patterns: the @edge-runtime/jest-environment + edge-runtime CLI for executing Web-Standard APIs (Request / Response / fetch) in jest tests, the `vercel dev` local emulator for full route testing, and the Edge vs Node Function divergence (no fs, no Buffer; Request / Response only). Covers the 30s Edge function timeout per vercel.com/docs. Use when testing Vercel Edge Functions or middleware.

Pattern catalog for "I can't write the test first" moments - recognizes common testability blockers (singletons / static dependencies, network in constructors, time / random as hidden inputs, deeply nested construction, untestable boundaries) and proposes the refactor that unblocks TDD (extract interface, dependency injection, seam, ports-and-adapters). Use as TDD coaching when an engineer is stuck on a class of code. For a catalog of what-to-test heuristics with no story use heuristic-test-design-reference, to label a change's shape before planning test effort use code-change-shape-classifier, and for conventions on writing the test well once the code is testable use test-code-conventions.

Build-an-X workflow producing a project-level risk register - risks to project execution (schedule slippage, environment instability, people / staffing, vendor / dependency, scope creep) rather than the product itself. Walks the author through ISO 31000-aligned identification, impact × likelihood scoring, mitigation strategy (avoid / mitigate / transfer / accept), and ownership; the project manager reviews it weekly. Use for release-execution risk. For product-quality risks use product-risk-register-builder, for the per-release product risk table use risk-matrix, and to sign off accepting one specific risk use risk-acceptance-decision-author.

Build-an-X workflow that produces a product-level risk register catalogue - per-feature / per-component product risks (functionality, performance, security, usability, compatibility, reliability) that persist across releases, distinct from per-release risk matrices. Walks the author through risk identification by ISO 25010 quality characteristic, scoring per impact × likelihood, and linking each register entry to mitigations + owners + review cadence. Output is a Markdown register the team reviews quarterly and that seeds release-level risk matrices. Use for long-lived product-quality risks; complements risk-matrix for per-release risks.

Wraps Braintree (PayPal-owned) sandbox testing patterns: sandbox merchant credentials, Drop-in / Hosted Fields client-side patterns, the Transaction lifecycle (submitted_for_settlement → settled), Braintree's distinctive test-card behaviours (specific PANs trigger specific errors), and the webhook verification (Braintree Webhook Parser). Use when testing Braintree-integrated code.

Build-an-X workflow for testing real-time in-app notifications delivered over WebSocket (RFC 6455) or Server-Sent Events (WHATWG SSE spec), Firebase Realtime Database / Firestore listeners, and notification center read/unread state - covers fan-out to multiple sessions, offline-then-reconnect delivery, and ordering guarantees. Distinct from email, SMS, push, and webhook channels. Use when authoring tests for any notification that appears inside a connected web or mobile app UI without leaving the application.

Configures Stryker.NET for mutation testing of .NET Core / .NET Framework projects - installs `dotnet-stryker` global tool, scopes mutation to specific csproj, supports xUnit / NUnit / MSTest, authors `stryker-config.json` with thresholds, runs in CI. Use when a .NET test suite needs mutation-quality verification - closes the .NET ecosystem gap left by Stryker.NET being newer than the JS variant.

Converts a regression suite (or test plan) into an executable manual checklist for cases when automation isn't viable - a release-day smoke checklist, a post-incident verification list, or a periodic compliance check. Outputs a per-TC checkbox list with the minimal preconditions, the action, and a one-line "what to look for" - short enough to fit on one page per major flow. Use when the team needs a focused human-runnable list (not full step-tables), e.g., for production smoke after deploy or for the on-call rotation's quick verification.

Pure-reference catalog of James Bach's SFDPOT heuristic - 'San Francisco Depot' - a 'you are here' framework that catalogues what a tester can vary in a system to find bugs. Six dimensions: Structure, Function, Data, Platform, Operations, Time. Use as a what-to-vary checklist during an exploratory session, complementing HICCUPPS-F (which catalogues what to compare against).

Pure-reference catalog of Michael Bolton's HICCUPPS-F oracle heuristic - the reference points a tester consults to decide 'is this a bug?': History, Image, Comparable products, Claims, Users' desires, Product (internal consistency), Purpose, Standards/statutes, plus Familiar problems. Use mid-session to test an observation against each oracle. For what to VARY use sfdpot-exploratory-heuristic, for what to MODEL use fcc-cuts-vids-heuristic, for quality criteria use crusspic-stmpl-heuristic.

Pure-reference catalog of James Bach's CRUSSPIC STMPL heuristic - thirteen quality criteria (quality attributes / non-functional requirements) a tester can evaluate a system against. CRUSSPIC: Capability, Reliability, Usability, Security, Scalability, Performance, Installability, Compatibility. STMPL: Supportability, Testability, Maintainability, Portability, Localizability. Use when checking a product's quality attributes or non-functional requirements, or picking which quality characteristics a test session evaluates - a checklist for judging product quality holistically; complementary to the ISO/IEC 25010 software product-quality model.

Drafts a `lighthouserc.js` (or `budget.json`) at design time - picks Web Vitals thresholds (LCP / INP / CLS) per route based on traffic class (cached / dynamic / API-heavy / form-heavy) and the team's NFRs, plus resource-size budgets (JS / CSS / images / total bytes). Emits the config file ready for the lighthouse-perf runner. Use when starting Lighthouse coverage on a project that has no budgets yet, or when the existing budgets need a redesign.

Reads `EXPLAIN` / `EXPLAIN ANALYZE` output from PostgreSQL, MySQL, or SQLite - identifies the dominant cost (sequential scan, nested loop, sort spill, missing index, type-cast preventing index use), proposes the specific index or query rewrite to fix it, and emits the candidate `CREATE INDEX` statement. Use when load testing or production telemetry shows the database as the bottleneck and the team needs targeted query-level remediation.

Authors and runs OpenAI Evals - Python framework + registry for evaluating LLMs and LLM-backed systems with `oaieval {model} {eval-name}` CLI; supports template-based evals (Match / Includes / FuzzyMatch / ModelBasedClassify) defined in `evals/registry/evals/*.yaml` against JSONL data files in `evals/registry/data/`, plus custom Python eval classes implementing the Eval interface. Use when the user works with the openai/evals repo, needs the OpenAI-curated eval registry, or contributes new evals via PR to the registry.

Wraps Mercurius (Fastify GraphQL plugin) testing patterns: `app.inject()` for HTTP-layer simulation without spinning up a network listener, plugin-registration setup (await app.register(mercurius, { schema, resolvers, graphiql: false })), production-config gates (graphiql: false; jit threshold; query depth limits via fastify-rate-limit + complexity), and the per-test app lifecycle (app.close() in afterEach). Use when writing tests for a Fastify + Mercurius GraphQL server.

Pure-reference catalog of GraphQL introspection as an attack surface and the production-deployment controls for it. Covers what introspection exposes (every type, field, directive, deprecation, description via __schema / __type), Apollo Server's default behaviour (introspection: false when NODE_ENV=production), the `hideSchemaDetailsFromClientErrors: true` companion setting (strips 'did you mean' suggestions), Yoga / Mercurius / Hasura equivalents, query-depth + query-cost limits, persisted-query allowlisting as the strongest mitigation, and the testable behaviours each control creates. Use when designing the production-safety posture of a GraphQL server or auditing an existing deployment.

Author and run Go's native fuzzing (Go 1.18+) - coverage-guided fuzzing built into the standard testing package via FuzzXxx functions. Covers f.Add seed-corpus declaration, f.Fuzz callback signature with typed parameters, testdata/fuzz/{FuzzXxx}/ directory layout for seeds + regression cases, the -fuzz flag for `go test`, and CI integration via short smoke runs. Use for fuzz testing Go libraries - Go's native approach integrates seamlessly with standard `go test` rather than requiring a separate toolchain like AFL++.