테스트·보안 스킬

Audit acceptance tests, which check whether features meet user needs, and verification records across project phases. Compare outstanding items with the codebase, flag outdated documentation, and produce a prioritized plan for human testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding outstanding acceptance tests across phases
• Collecting blocked items and checks needing human input
• Checking whether verification records match the code

Routes quality checks to the appropriate skill, covering code review and fixes, debugging, security checks, acceptance testing, AI response evaluation, and interface reviews. It also directs requests for validating phase outputs or reviewing plans across AI systems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review code and fix reported issues
• Investigate feature failures and errors
• Check security and acceptance testing

Audit a completed AI development phase to check whether its planned evaluations were implemented. Produce EVAL-REVIEW.md with a score, verdict, identified gaps, and a plan to address missing coverage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review evaluation coverage after an AI phase is complete
• Check implemented evaluations against AI-SPEC.md
• Document evaluation gaps and remediation steps

Run an audit, separate findings that can be fixed automatically from those needing manual work, and apply eligible fixes with tests and separate commits. Use severity filters, a finding limit, or a classification-only dry run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fixing audit findings with test verification
• Prioritizing findings by severity
• Limiting how many findings are fixed

Add tests to a completed development phase using its records and implementation. Review the proposed coverage, then generate unit tests for individual components and browser tests for full workflows, verify them, and commit the test files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding automated tests after a development phase is complete
• Turning acceptance criteria into test coverage
• Reviewing which code needs unit or browser tests

Validate Claude Ads data contracts, scoring inputs, run outputs, installation procedures, and release readiness. Return machine-readable pass or fail results with evidence, the most urgent blocker, and recovery steps, while checking source freshness and safe removal boundaries.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking Claude Ads run outputs and scoring inputs
• Auditing evidence and checks before a release
• Verifying installation instructions and archive checksums

Model distributed systems and concurrent algorithms in TLA+ or PlusCal, then check possible states with TLC. Use the results to investigate deadlocks, broken rules, and differences between specifications and implementation code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Model a distributed protocol before implementation
• Create a specification from existing concurrent code
• Investigate deadlocks and race conditions

Write Apache Cassandra distributed tests that simulate multiple nodes within one JVM, the Java runtime. The guide covers cluster setup, queries, node restarts, message dropping for failure scenarios, and troubleshooting problems caused by isolated class loading.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing read and write tests across multiple nodes
• Testing timeouts by dropping messages between nodes
• Verifying node replacement and restarts

Turn bug reports into small, runnable tests or scripts with clear failure checks. Verify that they expose the reported problem, then reduce inputs and setup while preserving the same failure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a bug report into a runnable test
• Reduce a complex test to its essential trigger
• Record failure rates for intermittent bugs

Write and review Apache SeaTunnel unit tests and E2E tests that check complete jobs using Testcontainers. It provides concrete rules for container setup, waiting, resource cleanup, and assertions to address intermittent failures and resource leaks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing a new connector E2E test
• Reviewing a test diff before a pull request
• Fixing intermittent failures or resource leaks in tests

Review Renovate pull requests that update GitHub Actions. Verify pinned commits against upstream version tags, inspect release notes for breaking changes, and check existing workflow settings before giving a clear recommendation on whether to merge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing GitHub Actions updates proposed by Renovate
• Verifying pinned commits against upstream version tags
• Checking breaking changes and workflow compatibility

Audit npm dependencies before updating them with Bun. Check maintainers, release age, signatures, published file changes, and release notes, then update packages that pass review and record deferred updates for later follow-up.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing dependency updates before installation
• Checking maintainer changes and suspicious package contents
• Updating packages that pass integrity checks

Record real ClawHub browser behavior and turn it into evidence for a GitHub PR. Add captions and focused zooms, distinguish before and after results, inspect the finished media, and attach it directly to the PR.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Showing a feature working in a real browser
• Comparing behavior before and after a fix
• Documenting desktop and mobile UI changes

Audit and fix four access-control problems in Convex apps: impersonation, missing ownership checks, sensitive data exposure, and writes into another user's container. Check the authentication foundation first, then verify changes with TypeScript.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether callers can impersonate another user
• Restrict document access to its owner
• Review queries that expose sensitive data

Investigate Convex production errors, prepare fixes on a branch, and verify them before opening a pull request for human review. After an approved deployment, check whether the same error recurs. Never automatically merge changes or deploy to production.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating recurring production errors
• Preparing verified fixes for code or schema defects
• Checking data changes against a production snapshot

Tests a specific Convex feature with sample data and simulated users, without deployment. It checks expected results, rejects unauthorized callers, and verifies that queries return only data belonging to the current user.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Verifying a newly implemented Convex feature
• Checking that other users cannot modify owned data
• Testing rejection of unauthenticated requests

Create tests for Convex functions with convex-test and vitest, using a backend that runs in memory. Check arguments, return values, authentication, indexes, errors, and scheduled functions without relying on real time or network access.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test Convex function arguments and return values
• Check behavior with different authentication identities
• Cover errors as well as successful requests

Combine Convex authorization, code quality, performance, and failure audits into one readiness report. It removes duplicate findings, scores confirmed issues with a stated formula, and orders the fixes while clearly identifying checks that could not run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a Convex app before launch
• Combining audit findings into one report
• Prioritizing authorization and performance fixes

Review code in a convex/ directory for security, access control, input and output validation, performance, and schema design. Receive findings grouped by severity, with explanations of each issue and suggested fixes before release.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing Convex functions before release
• Checking authentication and resource access controls
• Finding inefficient queries and missing validation

Design or extend DataFusion benchmarks using SQL where practical. Select representative workload variations, keep unrelated processing lightweight, and integrate runs with bench.sh so measurements reflect useful execution paths and remain practical to run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add SQL benchmarks for DataFusion operators
• Select representative input sizes and filter conditions
• Reduce unrelated processing overhead in measurements

Audit one datafusion-spark function against Apache Spark 4.2.0. Compare source code, accepted types, and edge cases, verify expected results with PySpark, then fix differences and record remaining gaps as issues and disabled tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing a function for Spark compatibility
• Checking NULL, overflow, and ANSI mode behavior
• Finding missing SQL test coverage

Compare Bifrost HTTP API code with OpenAPI, its API specification, to find missing routes and mismatched methods, authentication, parameters, and responses. Get an audit report with code references and recommended fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find API routes missing from OpenAPI documentation
• Check documented authentication against middleware behavior
• Compare request parameters and response formats

Turn a Bifrost PR or GitHub issue into API regression tests that catch recurring bugs. Review existing coverage, add cases to the Postman collection, and validate collection processing and provider filtering.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add regression coverage for a merged PR
• Turn an issue's reproduction steps into API tests
• Test streaming and non-streaming responses

Review codebases, APIs, and tools for vulnerabilities using source evidence and bounded local checks. Produces supported findings with impact, priority, and focused fixes, and can create structured reports for explicitly requested full audits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review security concerns in specific code
• Investigate a suspected vulnerability
• Audit a codebase and produce reports