'diagnose' 검색 결과

Diagnose failures in an application or while it is running. Use it to investigate an application problem or a runtime error, meaning an error that occurs during execution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating an error during execution
• Diagnosing an application failure
• Asking an agent to examine a running application's problem

Diagnose and improve slow web interfaces by measuring loading, rendering, interactions, and animations. The skill addresses images, JavaScript bundles, page layout, and network requests, then compares before-and-after results to verify improvements across devices and connection speeds.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing slow initial page loads
• Improving sluggish scrolling and animations
• Reducing image and JavaScript download sizes

Diagnose why the dotnet-msbuild binlog MCP server will not start or connect. Check the selected SDK, package sources, and launch logs, then identify a recovery that respects organizational policies and verify that the host discovers the server’s tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating CONNECTION_CLOSED during server startup
• Checking SDK selection and package source settings
• Diagnosing Microsoft.AITools.BinlogMcp resolution failures

Diagnose why an existing skill fails evaluations or shows no clear improvement. Separate content problems from test data, execution failures, activation issues, and insufficient evaluation tasks, then apply targeted fixes and validate them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a regression after a skill change
• Diagnosing evaluations that return no results
• Fixing a skill that fails to activate

Diagnose and fix MSBuild property problems, including overwritten settings, ineffective conditions, and environment-dependent paths. Review defaults, list appending, and evaluation order so project files and shared build settings retain the intended values.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fix build settings overwritten by shared files
• Preserve existing compilation constants when adding new ones
• Correct conditions based on the target framework

Diagnose and fix .NET MAUI development environment problems involving SDKs, Java, Android tools, and platform requirements. The skill discovers required versions from NuGet metadata and checks the environment again after each fix.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a .NET MAUI development environment
• Investigating missing SDK or JDK build errors
• Checking the environment after SDK or OS updates

Analyze CLR activation logs to explain how .NET Framework selects and loads its runtime, the software that executes managed code. Diagnose loading failures, unexpected version choices, installation dialogs, and conflicting activation paths within a process.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating failures to load the .NET Framework runtime
• Explaining why an unexpected CLR version was selected
• Tracing .NET 3.5 installation dialogs or their absence

Diagnose MSBuild failures from an existing binary build log. Inspect errors, settings, project references, and execution details to explain failures that console output alone does not clarify, including failures across multiple projects.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating build errors with unclear console output
• Tracing cascading failures across multiple projects
• Checking MSBuild target execution order

Manage shared team skills, rules, and documents through TeamAI. This skill guides syncing, publishing, checking differences, and diagnosing configuration problems, while directing setup and knowledge-sharing requests to the appropriate workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sync shared team skills
• Publish local rules and documents
• Check differences between local and team resources

Diagnose missing language features in Kode by checking LSP, the protocol connecting code tools to language servers. Update plugin configuration, confirm servers are recognized, and test an operation such as jumping to a definition.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Diagnosing missing LSP results in Kode
• Adding a language server through a plugin
• Reviewing a plugin's language server configuration

Diagnose difficult bugs and performance regressions by first building a repeatable check for the exact symptom. Minimize the reproduction, test ranked hypotheses, apply a fix, and verify the original scenario with regression tests where suitable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating persistent errors or incorrect output
• Increasing reproduction rates for intermittent bugs
• Measuring and diagnosing performance regressions

Build and estimate economic models that represent underlying choices and incentives. Get guidance on demand, dynamic choice, and auction models, select estimation methods, and diagnose numerical problems such as failed convergence or sensitivity to starting values.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose an estimation method for a structural economic model
• Implement BLP demand estimation
• Estimate dynamic choice and auction models

Configure and diagnose Account Pooler in BB, including accounts, authentication, quota-based routing, and failover, which switches to another account. Inspect account and routing state, plus Provider Retry decisions after pooled rate-limit failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspect registered accounts and routing state
• Configure account login or credential import
• Investigate quota routing and account failover

Diagnose Codex behavior within BB, including question cards, MCP requests for user input or approval, Computer Use app access, model availability, service tiers, session options, and persistent goals, using thread and provider controls.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate a Codex turn waiting for an answer
• Review app access and MCP tool approvals
• Check models and service tiers on the execution host

Audit LinkedIn Ads accounts, diagnose campaign issues, and plan improvements to targeting, creatives, budgets, and bids. Use connected accounts through NotFair MCP or exported data for analysis, with support for approved campaign changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing LinkedIn Ads campaign performance
• Reviewing job-title and company targeting
• Assessing lead quality and lead-generation forms

Diagnose wasted paid advertising spend, budget pacing, and allocation, then propose evidence-backed adjustments. Use it to review exclusions, bids, acquisition costs, returns on ad spend, overspending, underspending, or decisions about expanding campaigns.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding wasted ad spend and reviewing exclusions
• Reviewing budgets and bids when ad performance is poor
• Investigating overspending or slow budget use

Diagnose Claude Code hooks, scripts triggered by events, when they fail to run or produce unexpected results. Follow checks for logs, registration, files, manual execution, hidden errors, and rebuilt TypeScript bundles to narrow down the cause.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate hooks that do not run
• Find causes of missing or incorrect output
• Check duplicate execution and session IDs

Investigate fast-agent session files and logs to diagnose unexpected endings, tool loops, and mismatched tool responses. Inspect conversation history, summarize model and tool execution times, and connect sub-agent traces with the corresponding main-session activity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate an unexpectedly ended session
• Check tool loops and missing tool responses
• Identify slow model calls and tool executions

Run existing Tutti scenarios against a live agent provider, audit the captured session records, and replay them in a fresh isolated environment. Check evidence for each tested action, diagnose mismatches, and prepare verified recordings for publication.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording existing scenarios against a live provider
• Diagnosing transport or session-state replay mismatches
• Checking replay evidence for each tested action

Diagnose file write failures by checking permissions, disk space, paths, and file locks. Get corrective steps before retrying, or check conditions before important writes to catch problems such as missing folders and read-only files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating permission errors when saving files
• Checking disk space before saving large files
• Resolving Windows path length problems

Detect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the report. Use when debugging illegal memory access, out-of-bounds, misaligned access, leaks, WAW/WAR/RAW races, __shared__ hazards, uninitialized reads, garbage results, hangs, divergent __syncthreads/__syncwarp, or cuda::barrier / wgmma issues. Do NOT use for host/CPU-side bugs (use valgrind or AddressSanitizer) or global-memory data races (out of scope). Trigger keywords - compute-sanitizer, memcheck, racecheck, initcheck, synccheck, CUDA memory error, OOB, race condition, uninitialized memory, __syncthreads, barrier, deadlock.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user asks why a reported NVFLARE job failure signal occurred: the job failed, stalled, timed out, lost clients, ended with EXECUTION_EXCEPTION, or produced suspicious errors. Diagnose in simulation, POC, or production by collecting bounded evidence and mapping failure patterns to recovery actions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Diagnose CCB runtime, mounted daemon graph, tmux namespace and panes, provider context, queue/inbox/trace, replies/artifacts, config drift, and storage boundaries. Use when the user asks what is broken, which agent is stuck, whether CCB is mounted, why a reply did not arrive, or what to check first.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Diagnose a named CCB managed agent using runtime, job-lineage, and provider evidence.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.