Test design, vulnerability assessment, and quality assurance (13K skills)
Generate consistent identifiers for evidence-backed findings, then mark duplicates within the supplied batch and findings seen in historical records. This helps organize repeated issues without making assumptions about fixes.
Compare differences and statuses in explicitly supplied page lists from the same environment. A local Python script processes JSON without opening a browser or accessing the network, keeping gaps in the supplied information visible in its output.
Start a product testing workflow by clarifying the test environment, key user journeys, and permitted actions. Use screenshots, recordings, or a confirmed test environment to produce an initial page map and issue reports with reproduction steps.
Audit code within an agreed scope, trace how data moves, and verify suspected defects. Produce an issue ledger with reproduction evidence, clues for identifying duplicates, and focused repair suggestions.
Check supplied JSON for evidence coverage across the current version's acceptance criteria and required theme modes. The local check reports gaps in the data without rendering pages or establishing that a visual inspection occurred.
Begin a focused code audit by clarifying the repository, scope, priority concerns, and permission to prepare fixes. The skill reviews a chosen module or recent changes and reports up to three reproducible issues with supporting evidence.
Inspect product pages and approved workflows in an isolated test environment. Maintain page maps, compare changes, and document new issues, regressions, and recoveries with reproduction steps and current evidence. Until isolation is verified, analysis uses supplied materials only.
Check whether the checks and supporting evidence listed in a delivery ledger belong to the current version. It works from supplied records without calling Git, CI services, or the network.
Operate, diagnose, and test the live All API Hub extension interface on desktop or supported Android browsers. Use logged-in sessions to reproduce bugs, verify account workflows, and check development updates through browser debugging connections.
Collect open Dependabot alerts, group them by dependency files, and propose fixes suited to each package manager. After approval, update dependency versions or override settings and verify that patched versions are installed without introducing new audit issues.
Identify the checks required for changed files, run tests, and review applicable project rules. Get a table of passed, failed, and skipped checks with evidence, helping you verify changes before handoff or pushing code.
Review code changes with five parallel agents before committing. Each checks a separate area: code quality, simplicity, consistency, robustness, or task scope. Results identify issues, and every check must pass before the changes are considered ready.
Validate substantial Rust changes by running the repository’s prescribed checks in order. Handle check failures, review formatting changes, and report which commands ran and whether validation passed before handing the work back.
Audit a research replication package with ten checks covering R syntax, file references, output freshness, dependencies, data sources, and documentation. Receive a pass/fail report with specific issues and suggested fixes for preparing the package for submission.
Checks code changes before a pull request by reviewing builds, types, coding rules, tests, potential secrets, and changed files. Produces a report showing results, test coverage, and issues that need fixing.
Test local web applications with Playwright, a browser automation tool. Write Python scripts to check interface behavior, inspect rendered pages, capture screenshots, and collect browser logs, with a helper that manages one or more application servers.
Audit an entire repository with four parallel agents checking documentation, hook scripts, skills, and rules. Identify broken references, incorrect counts, code issues, and conflicting information, then apply fixes and repeat verification for up to five rounds.
Review academic slide decks or audit empirical analysis pipelines. It checks slide arguments, layout, and compilation, or reproduces numerical results in R, Stata, and Python to diagnose discrepancies and produce a formal report with prioritized recommendations.
Guide Claude Code to check files, documentation, data, and execution results before presenting answers. The skill sets verification steps for coding, analysis, and writing, including checking citations and numbers, diagnosing errors, and clearly stating what cannot be verified.
Inspect automated test results in TestDino, filter runs by branch or environment, and investigate failed or flaky tests—tests with inconsistent outcomes. Use historical runs to explore likely causes and recommendations for a failing test.
Manage manual test runs in TestDino, from finding or creating a run for a release to inspecting its cases and summary statistics. Assign individual cases and update results or elapsed time using recognizable run and case IDs.
Check the TestDino connection and personal access token, then discover accessible organizations, projects, and available modules. Use the results to identify the correct projectId before starting project-specific work.
Audit Playwright automated test code using context from TestDino. The skill guides a review that produces a local Markdown report, submits findings with a score, and lets you retrieve previously submitted audits.
Organize manual testing in TestDino by browsing, creating, and updating test cases and suites, which group related cases. Maintain steps and preconditions, filter existing cases, and update selected fields while preserving other details.