Test design, vulnerability assessment, and quality assurance (13K skills)
Create a Google Model Armor template for checking AI prompts and responses. Specify a Google Cloud project, location, and template ID, then use a preset or provide custom settings in JSON.
Validates skill files and registration consistency, then checks project tests and system health. Compares failures with recent changes to distinguish regressions, outdated tests, intermittent failures, and infrastructure issues, producing a report that tracks results over time.
Create evaluation drafts for existing skills using actual conversations and user corrections. Produce criteria and repeatable test cases, distinguish evidence from specification assumptions, and prepare an anonymized draft for human review.
Check YAML frontmatter, the metadata at the top of knowledge pages, for formatting and identity errors. Explain why gbrain holds files during sync, preview proposed changes, and repair supported problems after approval.
Have a different AI model review code, analysis, or documents against the original skill's stated requirements. Receive evidence-based findings and a comparison of agreement and disagreement, then decide which recommendations to accept.
Review bulk deletions before they happen by showing affected data, recovery options, and alternatives. The skill asks for explicit user consent and records confirmed deletions, covering files and gbrain data through agent procedures.
Prepare a personal knowledge base for team sharing by removing compensation, performance assessments, personal details, and other sensitive content. The skill checks pages and searchable records, verifies the cleaned material, and addresses sensitive Git history with explicit confirmation.
Use external APIs and GitHub's gh command through Iron Proxy while keeping real credentials out of the client. The skill guides account setup through the operator console and helps investigate blocked requests using observed errors.
Verify changes to the Cua Driver daemon and its CLI/MCP desktop tools against a real Electron fixture on Linux. The workflow checks accessibility and health, performs UI actions, confirms their side effects, and retains logs, screenshots, video, and process-cleanup evidence.
Operate apps and websites by inspecting screenshots, clicking controls, typing, and dragging. Use it to fill forms, check layouts, and test complete user flows, with recorded actions available for replay and review.
Choose and run checks for Python SDK changes using nox, Makefile targets, Ruff, mypy, and pytest markers. It supports adding tests, diagnosing CI issues, and checking basic behavior, type inference, and builds.
Choose and run checks for TypeScript SDK changes, including type checks, linting, builds, Vitest suites, and tests of complete runtime flows. Also guides writing or adapting CLI tests for Effect v4.
Create, update, and debug Docker-based end-to-end tests for the Composio CLI. Covers running the executable, keeping test data separate, checking command output, and maintaining package manifests within the CLI test suite.
Run final checks on reviewed SDK changes, covering code formatting, linting for code issues, type checking, and tests. Confirm completion only after every required check succeeds, with wrappers for macOS, Linux, and Windows.
Plan and, after explicit approval, run controlled checks of software behavior. Compare baseline and failure cases, repeat sensitive measurements, and report observed results with execution context, comparison conditions, and the status of temporary evidence files.
Review logs and source files from a completed manual example run. Check that results are current and complete, verify intended behavior beyond successful exit codes, and distinguish product defects from environment or credential problems.
Measure Python SDK test coverage, the code exercised by tests, and identify meaningful gaps in user-visible behavior. Report proposed scenarios or add authorized tests, then verify the changes and report remaining gaps alongside coverage results.
Audit Python SDK logs, exceptions, and telemetry for sensitive data exposure. Trace values to their sources, fix confirmed leaks, and test that redaction hides sensitive information while preserving the caller's expected behavior.
Write unit tests for FastGPT code, covering normal behavior, edge cases, and errors. It guides test placement, limits mocks that replace real dependencies, and checks TypeScript errors and coverage, the share of code exercised by tests.
Review FastGPT pull requests in stages, starting with the intended change and key execution paths. Check security, performance, tests, and compatibility, then organize findings by severity into a review report and line-level comments.
Create and review Mastra tests that reproduce user-visible failures through public APIs, real network requests, and actual storage. Verify that tests fail before a fix and cover the different execution paths affected by the bug.
Create a Mastra project at a specified version and check its Studio in Chrome. Test page loading, agent chat, tool execution, and workflows, then report passed and failed checks, encountered errors, and screenshots.
Test mastracode’s terminal interface in Konsole, covering model setup, conversation switching, task state isolation, and display issues. The guide combines interactive checks with scripted rendering tests and troubleshooting steps for common build and configuration problems.
Reproduce Mastra Code bugs with a real model and compare timestamped logs across network, streaming, execution, and terminal interface layers. Use the evidence to locate timing problems, incorrect token rates, flicker, or stuck status displays.