测试与安全技能

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.

中文简介正在准备中。当前显示英语简介。

• Creating a template with the jailbreak preset
• Defining template settings in JSON
• Preparing a template for prompt and response checks

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 Compares failures with recent changes to distinguish regressions, outdated tests, intermittent failures, and infrastructure issues, producing a report that tracks results over time.

中文简介正在准备中。当前显示英语简介。

• Validating definitions and registration for new skills
• Running daily tests and system health checks
• Classifying failures after code changes

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.

中文简介正在准备中。当前显示英语简介。

• Turn user corrections into repeatable test cases
• Compare promised behavior with actual usage
• Draft an evaluation from conversation history

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.

中文简介正在准备中。当前显示英语简介。

• Audit metadata across knowledge pages
• Investigate files held during sync
• Preview and repair formatting errors

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.

中文简介正在准备中。当前显示英语简介。

• Getting a second opinion on substantial code changes
• Reviewing authentication and other security-sensitive changes
• Checking work before a bulk operation

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.

中文简介正在准备中。当前显示英语简介。

• Reviewing files before a bulk cleanup
• Checking recovery options before deleting knowledge pages
• Confirming impact before dropping database tables

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.

中文简介正在准备中。当前显示英语简介。

• Creating a shared team knowledge base from personal notes
• Auditing an existing shared knowledge base
• Checking sensitive content before onboarding team members

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.

中文简介正在准备中。当前显示英语简介。

• Connect an external API account through the operator console
• Use gh with credentials managed by Iron Proxy
• Investigate requests returning 401 or 403 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.

中文简介正在准备中。当前显示英语简介。

• Checking a Linux desktop action after a Cua Driver change
• Confirming that a click changed the fixture app’s state
• Reviewing MCP responses alongside screenshots and video

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.

中文简介正在准备中。当前显示英语简介。

• Fill forms and use file upload dialogs
• Test buttons and complete user flows
• Check layouts and capture screenshots

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.

中文简介正在准备中。当前显示英语简介。

• Adding tests for Python SDK changes
• Diagnosing Python CI issues
• Checking SDK and provider changes

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.

中文简介正在准备中。当前显示英语简介。

• Validate changes to TypeScript packages
• Choose focused checks for a change
• Investigate failing TypeScript CI checks

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.

中文简介正在准备中。当前显示英语简介。

• Add end-to-end tests for CLI commands
• Debug unexpected CLI test output
• Keep test data isolated between tests

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.

中文简介正在准备中。当前显示英语简介。

• Verify runtime code changes after review
• Run final checks after test or build configuration changes
• Rerun required checks after fixing a failure

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.

中文简介正在准备中。当前显示英语简介。

• Investigating a suspected runtime regression
• Checking retries, interruptions, and concurrent operations
• Comparing latency or cost under matched conditions

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.

中文简介正在准备中。当前显示英语简介。

• Review results after a manual example run
• Verify behavior in examples that exited successfully
• Separate product failures from environment 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.

中文简介正在准备中。当前显示英语简介。

• Auditing Python SDK test coverage
• Investigating a decline in coverage metrics
• Finding untested error and cancellation paths

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.

中文简介正在准备中。当前显示英语简介。

• Audit logs and exceptions for sensitive data exposure
• Fix leaks involving model or tool data
• Test redaction and caller 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.

中文简介正在准备中。当前显示英语简介。

• Adding unit tests for individual functions
• Testing edge cases and error handling
• Testing functions that make API requests

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.

中文简介正在准备中。当前显示英语简介。

• Checking a pull request before merging
• Reasoning through normal, edge, and error cases
• Assessing API and database compatibility risks

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.

中文简介正在准备中。当前显示英语简介。

• Reproduce a reported bug before fixing it
• Review tests that rely heavily on mocked dependencies
• Check regression coverage across engines and adapters

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.

中文简介正在准备中。当前显示英语简介。

• Checking a newly created Mastra project
• Testing initialization with a specified version or package manager
• Checking Studio chat, tools, and workflows

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.

中文简介正在准备中。当前显示英语简介。

• Checking task state when switching conversations
• Setting up OpenRouter for interactive tests
• Testing borders and wrapping at different terminal widths

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.

中文简介正在准备中。当前显示英语简介。

• Investigating incorrect token rate displays
• Reproducing intermittent bugs with a real model
• Tracing flicker or stuck status displays