test-value-evidence
Assess tests for an identified code or test change, feature, PR or commit. USE FOR: review changed behavior or regression tests, prove pre-fix/missing behavior…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
Testing & quality
13,074 results
testability-obstacle
MUST USE for C#/.NET deterministic tests that require the smallest production seam for DateTime/Task.Delay/File/Environment/Guid/Random, static API…
testfx-test-value-evidence
Apply the vendored test-value-evidence skill with TestFx toolchain, assertion, parallel-safety, packed-consumer, and review conventions. Use when implementing…
review-external-pr
Triage an external contributor's PR and prepare it for merge. Detects push permission, base branch, draft state, size, and history quality, then picks one of…
debug-failing-test
Debug a failing test using an iterative logging approach, then clean up and document the learning.
run-integration-tests
Run integration tests to verify that extension components work together correctly. Use this after modifying component interactions or event handling.
run-pre-commit-checks
Run the mandatory pre-commit checks before committing code. Includes lint, type checking, and unit tests. MUST be run before every commit.
ui-scenario-validation
Use when reproducing a UI bug or verifying a fix by driving a real VS Code window end to end and capturing evidence. Launches VS Code through the automation…
expert-reviewing
Route code changes to relevant review dimensions based on affected files and folders. Use when reviewing PRs, analyzing code quality, or performing targeted…
trx-analysis
Parse and analyze Visual Studio TRX test result files. Use when asked about slow tests, test durations, test frequency, flaky tests, failure analysis, or test…
vstest-build-test
Build, test, and validate changes in the vstest repository. Use when building vstest projects, running unit tests, smoke tests, or acceptance tests, or when…
xdp-testing
XDP-for-Windows test execution and debugging workflow. Use when running tests (functional, spinxsk, pktfuzz, ringperf, rxfilter, xskmaprx, xskfwdkm), debugging…
plan-tests
Use when choosing the first failing spec for a Rails change. One minimal example opens the gate. Trigger words: first failing test, what test first, TDD, spec…
test-service
Use when writing RSpec for a service object under spec/services/. Test the public .call contract. Trigger words: service spec, test service object,…
triage-bug
Use when investigating a bug, error, or regression in a Ruby or Rails codebase. Creates a failing reproduction test, isolates the broken code path, and…
steve
Use the steve CLI to automate macOS apps via Accessibility APIs. Use when you need to drive Mac UI (apps, windows, menus, elements), run UI smoke tests, or…
test-automator
Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with…
gh-fix-ci
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft…
e2e-ci-trace-debug
A workflow for tracking down and fixing E2E tests that failed in CI, from the PR or GitHub Actions run link all the way to the end. When a PR merge is blocked by an E2E failure, or there is a failure with a trace/Playwright report artifact uploaded to Actions, or "e2e broke in CI /…
e2e-flow-planner
Explore the codebase, issues, and planning documents to identify Critical User Flows (core user workflows where failure blocks revenue, loses data, or breaks trust), and create a markdown E2E test plan for human review before writing code. Deciding "what to write first" for E2E/regression tests…
e2e-harness-setup
Bootstrap four kinds of "test harness" (AGENTS.md codebase guide, E2E operating rules SSOT, shared fixture/helpers, MCP server wiring) as if onboarding a new hire, so that an AI agent can write and operate E2E tests on its own. By default, the agent has test strategy, domain knowledge, project structure…
e2e-test-generator
A Generator that takes a reviewed E2E test plan (scenarios and steps), implements it as Playwright test code, runs it step by step in a real browser to verify behavior, and then validates all the way to lint, type-check, and green tests. "Turn the test plan into code", "This scenario…
e2e-test-hardener
Refine generated/authored Playwright E2E tests into independent, robust tests free of flakiness. Apply the three principles (test independence, mocking external dependencies, flakiness prevention) from the Naver Pay/Naver Financial-style "E2E test harness for AI agents" presentation. In requests/situations such as the following…
e2e-test-healer
Diagnose failed Playwright E2E tests based on traces to find the root cause, and run an automated healing loop (Healer) that fixes and re-runs until they pass. Use whenever an E2E / Playwright / browser test is failing, flaky, red, or…