테스트·보안 스킬

Audit code, frontend behavior, and agent traces for ignored errors, fallbacks that hide failures, and unsupported success reports. Findings identify locations, severity, user impact, and evidence, with repair handoffs based on reproduced failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating ignored exceptions
• Reviewing fallbacks that may hide failures
• Checking whether success reports have evidence

Design and summarize fair comparisons of coding agents on reproducible tasks. Assess quality, correctness, cost, time, tool use, and verification separately, then recommend an agent for a specific scenario using observed run evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare Codex and Claude Code on the same bug fix
• Define tasks, scoring criteria, and budgets before evaluation
• Compare output quality, cost, and time

Investigate an AI agent that stalls, repeats tool calls, or loses its goal. Compare possible causes against recorded evidence and prepare a small, reversible recovery step, with unresolved questions clearly identified.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating repeated calls to the same tool
• Reviewing an agent that has drifted from its goal
• Preparing a recovery step after repeated failures

Configure a shared guard that blocks destructive shell commands before local AI agents execute them. Adjust blocking rules, connect agent integrations, and test why commands are blocked or allowed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adjust rules for blocking destructive commands
• Connect the guard to another agent or machine
• Investigate blocked or unexpectedly allowed commands

Check assumptions before changes to APIs, pricing, quotas, or defaults. This skill combines research, measurements from real services, documented results, and product-owner approval to assess customer impact beyond passing tests, with follow-up verification after deployment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking customer impact before changing an API
• Validating pricing or usage-limit changes
• Measuring the effects of filtering external data

Review dependency handling, package downloads, credentials, and deployed file cleanup in APM. The skill defines checks for safe paths, centralized credential access, and refusing content when its integrity or signature cannot be verified.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing dependency resolution and lockfile changes
• Checking package integrity and signature verification
• Inspecting token handling for possible leaks

Review OpenAPM specification changes through four specialist perspectives covering schemas, registries, dependency resolution, and web architecture. The skill combines findings and mechanical checks into one advisory comment, separating immediate fixes from work deferred to later versions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing OpenAPM specification changes
• Checking JSON Schemas and conformance fixtures
• Separating immediate fixes from future version work

Test local Tika changes with Jazzer, a tool that mutates inputs to uncover failures. Build parser fuzzers, check existing files, reproduce crashes, add starting samples, and retest fixes for memory exhaustion, hangs, and unexpected exceptions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fuzzing local Tika parser changes before merging
• Running existing files through a parser once each
• Reproducing and retesting an OSS-Fuzz crash

Inspect files with Apache Tika to identify their actual format, embedded content, revision traces, and risk indicators. Save extracted evidence and file hashes while distinguishing recorded claims from observed structure, without asserting authorship or validating signatures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Triaging suspicious files and misleading extensions
• Reviewing recorded authors, dates, and creating applications
• Comparing earlier PDF revisions with the final version

Compare Tika character encoding detection using one build and two configurations. Find files whose detected encoding changed, cross-check text quality signals, and inspect detector traces to investigate garbled text and identify which detector contributed to the result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating encoding changes after a detector configuration update
• Finding files misclassified from Western encodings to CJK
• Tracing which detector selected a file's encoding

Compare text and metadata extracted by two Tika builds from the same file collection. Generate reports to investigate content differences, encoding changes, new exceptions, and missing embedded documents, then repeat the evaluation after fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing extracted content before and after a Tika change
• Checking whether parser changes lose attachments
• Investigating new exceptions and large content differences

Checks whether work is truly complete before reporting success, committing changes, or creating a pull request. It runs the relevant checks, reads their full output, and ties status reports to current evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking results before reporting completion
• Confirming that a bug fix resolves the original problem
• Verifying work before a commit or pull request

Investigate bugs, failing tests, and unexpected behavior before proposing changes. Follow four stages to gather evidence, compare working examples, test a specific cause, and verify a focused fix with a test that reproduces the problem.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating failing tests
• Tracing production bugs to their source
• Finding failures across connected components

Scan a website for broken links, including links that return 404 or 500 errors. Crawl internal pages, identify broken outbound links, and report the pages containing them so you can locate and fix the references.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check a website for broken links
• Find links that return 404 or 500 errors
• Audit links pointing to external websites

Diagnose bugs, intermittent failures, and performance regressions through structured logging and reproduction. It ranks possible causes with confidence scores, tests competing explanations, and reports whether the evidence proves the cause or leaves the diagnosis incomplete.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trace the cause of a reproducible bug
• Investigate intermittent failures through repeated runs
• Compare possible causes of browser or device failures

Guide app automation on iOS, tvOS, macOS, and Android using help matched to the installed agent-device CLI. Tasks include screen inspection, taps, text entry, scrolling, and collecting logs, network information, or performance evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Navigate apps and verify the resulting screens
• Automate text entry and scrolling
• Capture screenshots and inspect interface information

Review a Marin access-change pull request by decrypting user identities and explaining their roles and resources. After explicit human confirmation, merge the request and apply only the verified permission changes through Pulumi.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking who receives access in an encrypted grant request
• Reviewing roles and resources before approving access
• Applying confirmed permission additions or revocations

Compare Zephyr changes using the same prepared dataset and matching execution settings. Analyze Finelog metrics for each processing stage to distinguish CPU efficiency, elapsed time, and peak memory changes, then report improvements, regressions, or tradeoffs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare Zephyr performance before and after a PR
• Assess speed gains against additional CPU usage
• Check peak memory and out-of-memory regressions

Evaluate whether a proposed LinkedIn integration fix addresses its linked issue by reviewing the report, code changes, and tests. Flag implementation concerns and optionally compare live results with a genuine recorded baseline after approval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether a PR addresses its linked issue
• Reviewing language-dependent detection and selectors
• Comparing live results with a recorded baseline

Investigate LinkedIn integration bugs by comparing issue reports with source code. Separate established facts from unverified claims, identify missing evidence, and optionally check reproduction in a live environment after explicit approval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a reported LinkedIn integration bug
• Identifying evidence missing from an issue report
• Checking live reproduction after approval

Review a git diff or selected files with parallel agents to find behavior regressions, security risks, reliability problems, and compatibility or test gaps. Receive filtered, evidence-backed findings and prioritized recommendations without changing files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check changed code for unintended behavior
• Review security and privacy risks
• Find performance and reliability problems

Check whether infrastructure code actually runs when a user triggers it. Trace calls from hooks or commands through scripts and modules, verify registration and permissions, and test the complete path to uncover unreachable code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether a newly added hook actually runs
• Tracing calls from a command to module execution
• Finding unused modules and missing registrations

Develop features and fix bugs through test-driven development: write a failing test, add minimal code to pass, then clean up. The workflow assigns agents to planning, test writing, implementation, and validation of the full test suite.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a new feature with tests written first
• Adding a regression test before fixing a bug
• Testing boundary conditions and error behavior

Run a staged testing workflow that checks type errors first, executes unit and integration tests in parallel, and runs end-to-end tests only after they pass. Receive pass and fail counts with details about failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running the full test suite before a release or merge
• Testing a specific feature
• Running a quick unit-test check