Test design, vulnerability assessment, and quality assurance (13K skills)
Checks published OpenWork desktop downloads for mac-arm64, verifying developer signatures, Apple notarization, and update metadata. It checks versions, download references, and file hashes, then records evidence to support a release rollout decision.
Review code changes for newly introduced security issues with a plausible attack path. Produce findings for the Warden security summary, including affected lines, severity, a minimal fix, and observable conditions for confirming the issue is resolved.
Guides review of pull requests from external forks, covering code ownership, contribution terms, security-sensitive changes, and tests tied to the reviewed commit. It produces a review record and supports moving changes to a maintainer branch when needed.
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.
Set up a Windows sandbox in Daytona to test OpenWork with a simulated corporate certificate authority. Check successful and broken HTTPS connections, the desktop app’s use of Windows trust, and certificate handling in runtimes it launches.
Reproduce model connection failures and interrupted responses in the desktop app using a local fault server and test providers. Check error messages and retry behavior for refused connections, DNS failures, HTTP errors, stalled requests, and cut streams.
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.
Write tests that demonstrate a pull request’s user-visible changes through before-and-after steps, screenshots, and recorded observations. Extend an existing core journey or create a one-off proof that helps reviewers understand the outcome and access boundaries.
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.
Test a released archon binary through Homebrew or curl installation on macOS or a Linux VPS. Check version information, bundled workflows, Claude execution, and sensitive environment key removal, then clean up and report the results.
Automate browser actions such as filling forms, clicking buttons, and switching tabs. Inspect page snapshots, network requests, and console messages to check website behavior, record interactions, and support work on Playwright tests.
Interpret n8n validation results and work through fixes for missing settings, broken references, and expression errors. Distinguishes blocking errors from advisory warnings, explains validation profiles, and guides review of automatic fixes and execution failures.
Check mesh files for 3D printing by measuring geometry and comparing it with process-specific design limits. Get findings on wall thickness, overhangs, and supports, plus build orientation options and concrete redesign guidance.
Run NemoClaw live end-to-end tests, which check complete workflows, or inspect existing release evidence. Routes requests to local or trusted GitHub workflows and reports the tested commit, results, workflow link, and relevant job links.
Investigate failing or flaky NemoClaw end-to-end tests, which check complete workflows. Trace each assertion through its inputs and implementation, including cleanup and dependent jobs, and produce an evidence ledger to guide authorized repairs and reruns.
Continuously monitor automatic end-to-end tests on NemoClaw main, group failures by root cause, and coordinate fixes and peer reviews through GitHub. Track ownership and merge readiness while checking whether later runs confirm each repair.
Review a NemoClaw pull request for security risks by examining changed code, configuration, and dependencies. Assess nine categories and report findings with severity, file locations, and recommended fixes, alongside an overall assessment of whether it is safe to merge.
Validate the staging NemoClaw Brev Launchable by checking its web deployment flow, environment access, deployed image, and preinstalled user journey. Report inference results and missing dependencies separately as advisory evidence outside automated end-to-end testing.
Recheck older NemoClaw bug reports against the reported and newest releases, then prepare evidence-backed recommendations for maintainers. It documents reproduction results and proposed updates for approval without automatically closing issues.
Test CodexBar against real provider services, check application settings, and verify menu contents. Use command-line checks and visual evidence to distinguish authentication problems, API mismatches, and display issues before a release.
Build Handsontable demo pages for visual regression tests, which compare screenshots for appearance changes. It guides feature routes, URL-driven display states, sample data, and decisions about testing the same feature across framework wrappers.
Write and update Handsontable unit tests with Jest and type tests with TypeScript. Explains file placement, focused test runs, boundary cases, and checks for public types, while helping choose between isolated logic tests and browser tests.
Open local or public web pages in BrowserStack Live for checks on real mobile devices or desktop browsers. The skill prepares temporary access to a local server, launches the requested session, and shares its dashboard link.
Add or update Handsontable performance tests for rendering and user interactions. The skill guides trace recording, measurement boundaries, baseline comparisons, and reports that help reviewers identify performance changes in pull requests.