测试
单元测试、集成测试与测试自动化
reviewer-app-testing
hushh-labs
Use when operating reviewer-account browser rehearsals that require BYOK unlock, memory-only decrypted information, and same-session client navigation.
quality-contracts
hushh-labs
Use when changing cross-surface verification policy, contract-test placement, test selection, or quality gates across frontend and backend.
mobile-parity-audit
hushh-labs
Use when auditing mobile/native parity, release readiness, the native route inventory report, or platform-specific coverage gates across the Hussh app.
fix-issue
remix-run
Fix a reported issue in Remix from a GitHub issue. Use when the user provides a GitHub issue URL and asks to fix a bug, investigate an issue, reproduce a problem, or complete part of a tracking issue. Handles the full workflow: fetching the issue, finding the reproduction, writing a failing test, implementing the fix, and recording merged progress on tracking-issue checklists.
write-tests
remix-run
Write, refactor, or review tests in the Remix repository. Use when adding or changing .test.ts/.test.tsx files, package test scripts, test fixtures, mocks, coverage tests, e2e tests, or package metadata for test-only dependencies.
build-prevail
microsoft
Build and test the PREVAIL verifier (external/ebpf-verifier) standalone. Use this skill when asked to build, test, or iterate on the PREVAIL verifier, run YAML verification tests, or work with the verifier's cmake build system.
kotlin-coroutines
vitorpamplona
Advanced Kotlin coroutines patterns for AmethystMultiplatform. Use when working with: (1) Structured concurrency (supervisorScope, coroutineScope), (2) Advanced Flow operators (flatMapLatest, combine, merge, shareIn, stateIn), (3) Channels and callbackFlow, (4) Dispatcher management and context switching, (5) Exception handling (CoroutineExceptionHandler, SupervisorJob), (6) Testing async code (runTest, Turbine), (7) Nostr relay connection pools and subscriptions, (8) Backpressure handling in event streams. Delegates to kotlin-expert for basic StateFlow/SharedFlow patterns. Complements nostr-expert for relay communication.
svelte-code-writer
sveltejs
CLI tools for Svelte 5 documentation lookup and code analysis. MUST be used whenever creating, editing or analyzing any Svelte component (.svelte) or Svelte module (.svelte.ts/.svelte.js). If possible, this skill should be executed within the svelte-file-editor agent for optimal results.
reviewing-compiler-prs
dotnet
"Performs multi-agent, multi-model code review of F# compiler PRs across 19 dimensions including type checking, IL emission, binary compatibility, and IDE performance. Dispatches parallel assessment agents per dimension, consolidates with cross-model agreement scoring, and filters false positives. Invoke when reviewing compiler changes, requesting expert feedback, or performing pre-merge quality checks."
vsintegration-ide-debugging
dotnet
Fix F# debugging issues (breakpoints, .pdb, sequence points). Build, run VS integration tests, inspect IL/PDB.
run-helix-tests
dotnet
"Submit and monitor .NET MAUI unit tests on Helix infrastructure. Supports running XAML, Resizetizer, Core, Essentials, and other unit test projects on distributed Helix queues."
write-xaml-tests
dotnet
Creates XAML unit tests for GitHub issues in the Controls.Xaml.UnitTests project. Tests XAML parsing, compilation (XamlC), and source generation. Use when testing XAML-specific behavior, not UI interactions.
dart-test
dartsim
"DART Test: unit tests, integration tests, CI validation, and debugging"
animation-test-migration
ag-grid
'Migrate a series type from ratio-snapshot animation tests and manual -test docs pages to frame-trajectory coverage. Use when converting a series (area, pie, scatter, histogram, range-bar, candlestick, radar, …) to the trajectory harness.'
plotpickle-human-acceptance
BryanHarrisScripts
Exercise PlotPickle through its rendered UI like a first-time human user, preserve story context across the workflow, and report reproducible PASS, WARN, or FAIL findings with evidence.
cairo-testing
keep-starknet-strange
Cairo smart-contract testing with snforge. Trigger on "write tests", "add unit tests", "fuzz test", "integration test", "test this contract", "regression test". Guides test strategy, cheatcode usage, and coverage.
atlas-event-driven-weights
kaecer68
"Use when modifying factor weights, adding factor types, or connecting narrative events to portfolio factor calculations. Triggers: factor weight logic changes, new factor type, FactorBridge, FactorWeightEngine modifications."
atlas-llm-provider-capability
kaecer68
"SOP for adding a new LLM provider client or capability handler in atlas-go. Covers BaseClient embedding, ProviderImpl interface, capability constant registration, routing table updates, handler wiring, and required tests. Trigger: user asks to add a new LLM provider, capability, or routing chain entry."
atlas-fubon-supervisor-invariants
kaecer68
"Mandatory invariants (F1-F9) for modifying the fubon-proxy ProcessManager supervisor, Start pre-flight, Stop cancellation, backoff, and zombie auto-kill logic in atlas-go. Prevents orphan processes, goroutine leaks, Stop deadlocks, and EADDRINUSE backoff loops."
run-moses-y-github-io
moses-y
Build, run, screenshot, smoke-test and regression-check the moses-y.github.io static site and its data pipeline. Use when asked to run/serve/preview the site, screenshot a page, verify the projects feed, Code Graph, Code Brain or blog articles, regenerate blog pages/RSS/SQLite, iterate on site improvements, or check that a change did not break existing capability.
atlas-macro-narrative
kaecer68
"Use when analyzing macro narrative events, deriving foreign capital flow probabilities, or working with the six macro dimensions. Triggers: macro analysis, narrative event detection, Taiwan stress index, causal chain analysis."
sd-socratic-review
platypeeps
Use when the user wants a bounded, adaptive Socratic review that asks one question at a time, tests demonstrated understanding, repairs misconceptions, and reports evidence without grading.
sd-status-update
platypeeps
Use when the user wants an objective-oriented project status update from supplied or connected work sources, with outcomes, current state, blockers, risks, decisions, asks, and next actions.
sd-tdd
platypeeps
Write the test before the code and watch it fail, so that a passing test is evidence rather than agreement.