Test design, vulnerability assessment, and quality assurance (13K skills)
Classify existing tests with standard tags for success cases, errors, boundaries, and other behaviors. Get a per-test mapping and distribution summary, or apply tags using supported framework syntax and verify compilation and test discovery.
Migrate .NET tests from xUnit.net v2 to v3 while preserving the existing test runner. Update packages, project settings, and affected test code, then verify test discovery, execution, and skip behavior.
Make C# code testable when it directly uses static services such as time, files, or processes. It introduces existing abstractions or minimal wrappers, supplies dependency registration, and demonstrates tests with controlled substitutes for real resources.
Review existing tests using 19 research-backed test smell categories, meaning patterns that can weaken test quality. Get findings ranked by demonstrated risk, with precise code evidence and fixes suited to the test framework in use.
Analyze .NET test suites for repeated setup, assertions, and copied test methods. Get a report with file locations, before-and-after refactoring examples, priorities, and readability trade-offs, without changing the source files.
Review mock configurations in .NET tests by tracing the production code each test exercises. Identify unused, unreachable, duplicated, or replaceable setups, explain concrete fixes, and distinguish them from appropriate mocks for databases, HTTP clients, and other external services.
Verify OpenMausBot server and conversation changes in an isolated instance using a fake engine, a stand-in for the real engine. Follow the canonical verification guide and shared control tool to check supported server workflows before reporting success.
Operate a physical Android phone connected to OpenMausBot through authorized USB debugging. Open apps, read screens, tap controls, enter text, and swipe, checking the resulting screen after each action to support app testing and phone tasks.
Create a project-specific SKILL.md that teaches an agent how to launch, operate, and verify an app. It tests a representative workflow first, then records reliable steps, evidence of success, cleanup instructions, and maintenance guidance.
Run Weave Router locally with Codex to reproduce routing bugs and check response conversion, model selection, and routing markers. Temporary configuration keeps everyday Codex settings intact, with real providers or repeatable mock responses.
Reproduce and verify Weave Router behavior locally with Docker Compose and Claude CLI. Test model routing, response conversion, and streaming against real APIs or a mock service, then inspect logs without changing global Claude Code settings.
Maintain reference test data and expected results for model-routing audits, which analyze how AI models are selected. Investigate mismatches, update outputs after intentional behavior changes, and add captured workflow runs as new test cases.
Validate changes to Squad coordinator and agent templates through real sessions using a locally built CLI. Check generated files, agent behavior, and saved state, then record evidence, scenario verdicts, and progress for pull request reviews.
Review technical claims and deliverables by checking evidence and testing alternative explanations. Confirm that references and API endpoints exist, then report verified, unverified, or contradicted claims alongside evidence and an overall review verdict.
Manage work and personal GitHub identities in agent workflows by checking the active account and selecting credentials for each operation. It covers personal repository pushes, pull requests from forks, and separate configuration directories for account isolation.
Guide agents in handling credentials safely by avoiding live environment files, using placeholders in shared records, checking staged changes before commits, and escalating secrets already exposed in Git history.
Keep tests aligned with API changes and actual project files. This skill guides agents to update related tests in the same commit, refresh expected counts and lists, and check stale assertions when automated checks fail.
Design metrics that measure whether a workflow achieved its intended outcome using recorded session evidence. Choose built-in checks or custom JavaScript, retain suitable Bash evaluators, and define tests that distinguish success, failure, and missing evidence.
Review GitHub security advisories, verify fixed versions, and update compatibility rules with narrowly scoped changes. Document upgrade steps and check that version blocking, warnings, and related configuration behave as intended.
Review GitHub agentic workflows, automated workflows guided by AI agents, for security and correctness. Compile changes, inspect permissions and safeguards, and use available run logs to identify supported improvements to cost and execution time.
Review and implement gh-aw workflows and Go code with security checks for untrusted input, shell commands, dependency versions, and permissions. The skill also covers event-specific conditions and tools that inspect workflows for errors and security risks without running them.
Review git and gh operations in gh-aw workflows to check credential availability for each repository. Identify missing token handoffs, risky expansions of limited checkouts, and error handling needed where credentials are intentionally unavailable.
Automate browser tasks such as clicking, filling forms, and navigating tabs. Inspect page structure, console messages, and network requests, and capture screenshots or recordings to support web testing, debugging, and UI feedback.
Review regular expressions used to detect errors in agent engines. Check for empty matches, test patterns against real logs, and add safeguards against repeated matches that can cause JavaScript loops to hang.