Test design, vulnerability assessment, and quality assurance (13K skills)
Review unresolved game bugs by separating impact from urgency, then recommend repair priorities and sprint assignments, meaning work planned for a development cycle. Reports also highlight recurring problems, older issues, and bugs in previously completed work.
Turn game bug descriptions or suspected code problems into structured reports with reproduction steps, severity, and priority. Follow reported bugs through fix verification and closure, recording test results or manual checks before marking an issue closed.
Review skill and agent definitions for structural issues and whether their instructions meet expected behavior. Four modes cover structure, test specifications, category criteria, and coverage reports that reveal missing specifications or checks.
Create a game development test plan for a sprint, feature, or individual task. Classify the work and specify automated tests, manual checks, basic functionality checks, and playtest needs from documented requirements.
Create a game release checklist tailored to target devices and distribution requirements. Review builds, bugs, store information, and launch preparations, then report readiness while clearly separating known blockers from checks that could not be assessed.
Create a game playtest report template or turn session notes into organized feedback. Separate gameplay problems from bugs, compare observations with design intent, and identify priorities for design changes, balance adjustments, and polish.
Turn user stories and acceptance criteria into detailed test scenarios. Define objectives, starting conditions, user roles, actions, and observable results, including invalid inputs and boundary cases, so a quality assurance team can carry out the checks.
Compare documented permissions and data boundaries with actual code to find meaningful gaps. Produce findings that connect each documented rule to implementation evidence, identify who could exploit it and who is affected, and propose a concrete fix.
Test the pages affected by a branch or pull request in a browser. The skill checks rendered pages and key interactions, then reports passes, failures, skipped checks with reasons, and steps to reproduce problems.
Build and exercise an iOS app in a simulator using XcodeBuildMCP. Collect screenshots, logs, and human verification results, then report which checks passed, failed, or were skipped, alongside the overall outcome and remaining failures.
Test user journeys affected by a branch’s changes in a real browser. Check correctness and the experience for intended users, fix small defects with regression tests, and commit fixes alongside a report documenting results and unresolved decisions.
Verify a local OpenSEO MCP server, which exposes tools to AI agents, through real DataForSEO calls and a headless Claude trial. Check protocol correctness alongside tool discovery, input rules, response size, errors, and asynchronous task recovery.
Evaluate changes to OpenSEO skills by running fresh Codex sessions against a local backend. Compare saved reports using weighted criteria, then inspect tool logs to understand failures and check whether revised instructions improve output.
Evaluate Vitest tests by the observable behavior and realistic regressions they protect. Guide new test authoring and review existing suites for duplication, dependence on implementation details, and code used only by tests, with evidence for retention or removal.
List and capture every interface state added or changed by a pull request, a proposed code change. Include error states, toggles, buttons, forms, and edited pages so reviewers can inspect their appearance.
Automate real browser tasks to test websites, complete forms, and collect page information. The skill guides agents through identifying clickable elements, interacting with pages, comparing page states, and saving screenshots or PDFs.
Create and run tests for interactive command-line tools and terminal interfaces using @microsoft/tui-test. Simulate keyboard input, check visible text, and compare screen snapshots in a separate terminal environment for each test.
Verify OpenWork changes by running the real product and following user or client actions. Choose suitable tests, capture screenshots and reports, and demonstrate that the check fails on dev but passes on the changed branch.
Review an outside contributor’s pull request before running its code. Identify concealed behavior, obfuscated code, risky dependencies, and build hooks, with file locations and specific checks for maintainers to follow up.
Measure chat layout jumps while a response runs by tracking the Working line through CDP, a browser debugging connection. Count upward movements and compare the same prompt before and after changes to status lines, step rows, or folding behavior.
Run Openwork end-to-end tests, which verify complete user journeys, locally or on Daytona. Check the exact commit and runtime, investigate failures or skipped tests, and report results with commands, counts, and an explicit overall verdict.
Reproduce chat errors, retries, parallel tool calls, and app creation in a running desktop application. Check how messages and cards appear, including interrupted replies, grouped steps, and error details.
Investigate failed tests, type checks, builds, and CI jobs by recording exact evidence and repeating checks in a clean comparison environment. Use the results to distinguish existing failures, newly introduced problems, environment issues, and unresolved cases.
Control a running OpenWork app from the shell to inspect UI changes and reproduce chat states. Start fresh sessions, select models, send prompts, wait for completion, capture screenshots, and run JavaScript, with no visible window by default.