'destructive' 검색 결과

용도별 템플릿과 실행 호스트를 골라 AI 에이전트용 하네스의 기본 구조를 만듭니다. 기본값은 계획만 표시하며, 명시적으로 확인한 뒤 기존 프로젝트 밖에 생성합니다.

• 개발용 하네스의 기본 구조 생성
• 실행 호스트에 맞는 구성 준비
• 파일 쓰기 전 생성 계획 확인

Guide Git operations with explicit authorization for history changes and destructive actions. It defines recovery snapshots before discarding work, careful handling of locks and index corruption, and checks that keep unexplained changes out of commits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Keeping completed changes available for review before committing
• Saving a recovery snapshot before an authorized discard
• Handling Git locks or a corrupted index

Investigate active macOS connection failures without changing network settings. Uses built-in tools to distinguish local network, DNS name lookup, upstream path, and application problems, then reports evidence, confidence, and the next useful diagnostic check.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate API or MCP service timeouts
• Check failed or inconsistent DNS lookups
• Locate likely causes of video call lag

Create disk images for investigations using dd or dcfldd on Linux. The workflow covers write protection, bit-for-bit copying, hash checks to verify integrity, and documentation of the acquisition process.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserving a suspect drive before investigation
• Creating evidence copies of USB devices or memory cards
• Verifying that a disk image matches its source

Delete stored context-mode data for one session or an entire project after confirming the scope. Remove an unwanted session while preserving others, or clear project knowledge, session records, and statistics for a fresh start.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Remove data from one unwanted session
• Clear a project database containing outdated information
• Reset all stored project data for a fresh start

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Present clear choices when a task needs a human decision, then pause execution until the user replies. This reusable interaction pattern supports filing decisions, priority selection, and confirmation before destructive actions, with an option to decline.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying requests with several possible meanings
• Confirming before bulk deletion or overwriting
• Choosing where to file meeting notes

Design agents that read, update, summarize, or sync spreadsheet data. Define how they select the right table, check existing values, verify writes, request confirmation for destructive changes, and report the exact rows and ranges processed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Design an agent that refreshes a leads sheet each morning
• Build weekly sales reports from spreadsheet data
• Define an agent that syncs data between two systems

Create, configure, and troubleshoot Crush hooks, commands that run before tool execution. Use them to block or approve calls, rewrite tool input, or add context for the agent, with guidance on configuration and troubleshooting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Blocking destructive shell commands
• Automatically approving read-only tools
• Adding editing reminders for the agent

Prepare and run Google Cloud CLI commands with syntax checks, explicit project and location settings, and focused output. Guides agents through change previews and authorization requirements for destructive operations and sensitive infrastructure changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check command syntax and flags before execution
• List cloud resources with only the fields needed
• Review infrastructure changes before running commands

Inspect GKE TPU Dynamic Slices, diagnose provisioning failures, and validate workload configuration for single slices or JobSet workloads spanning multiple slices. Get cleanup commands, with confirmation required before destructive changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking TPU slice lifecycle states
• Diagnosing TPU slice provisioning failures
• Validating single-slice and multi-slice JobSet manifests

Manage separate local development environments for multiple branches using the project's pnpm worktree CLI. Each environment has its own ports and dependencies, with options to share Supabase or isolate database changes for testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running and testing multiple branches at the same time
• Testing database migrations in a separate database
• Reusing an existing worktree for related fixes

Assess dependency confusion, where a build retrieves a public package instead of an intended private one. Discover internal package names, review registry settings, plan callback-based proofs of execution, and document fixes across major package ecosystems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing package registry settings in CI/CD
• Finding internal package names in lock files
• Planning an authorized callback-based proof of concept

Assess weaknesses in the software supply chain, from dependency packages to build pipelines and distributed artifacts. Covers authorized proof-of-concept testing, package confusion, container image risks, signing abuse, and defensive checks for tampering.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assess dependency confusion risks in package registry settings
• Review tampering risks in CI/CD artifacts and container images
• Plan a non-destructive proof of concept and remediation report

Guide an AI agent through research, implementation, and verification with fewer interruptions. The skill emphasizes evidence, concise reporting, and saved progress notes, with three working modes that adjust how closely the user follows the work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Delegating engineering tasks through verification
• Reducing interruptions during focused work
• Resuming long tasks from saved progress notes

Set up Claude Code hooks that block specified Git commands before they run, including push and destructive cleanup operations. Choose project or global installation, adjust the blocked commands, and test that the hook rejects a sample command.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Blocking git push from Claude Code
• Preventing commands that discard local changes
• Installing Git guardrails across projects

Run and supervise DOCA applications directly on an x86 host or BlueField Arm hardware. Covers process launch, hardware resource assignment, isolation between workloads, and troubleshooting application failures or BlueField recovery problems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launching a DOCA application directly on hardware
• Investigating systemd restart loops
• Assigning CPU and device resources to multiple workloads

Bring up BlueField-3 hardware through RShim, its host management interface, and BFB system images. Follow installation and recovery workflows, diagnose management connectivity and boot state, and verify the installed system and version compatibility.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Install a BFB image on BlueField-3
• Diagnose a DPU that did not recover after installation
• Investigate working ping but failed SSH access

Build packet steering rules, which direct network traffic by matching its properties, with DOCA Flow on NVIDIA NICs or DPUs. Adapt shipped samples, validate rules against installed APIs and hardware capabilities, and investigate counters or runtime errors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Route traffic matching address and port conditions
• Bring up Flow ports
• Validate rules before programming hardware

Operate NVIDIA DOCA Management Service to read, change, and monitor BlueField or ConnectX settings locally or remotely. Get guidance on deployment, authentication, management requests, logs, and diagnosing failures across the service and its backend.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Read or change local BlueField settings
• Choose deployment and authentication for remote management
• Read, update, and subscribe to settings through gNMI

Archive and rebuild wiki knowledge from source, or restore a prior archive. Use for full restart/recovery when incremental repair is inappropriate; this is broader and more destructive than ordinary update or lint.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Detect and merge wiki pages representing the same concept under different names. Use for page-identity deduplication and consolidation. Destructive merges require confirmation; not for link repair or general linting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

[omh] Folder cleanup, renames, or deletions: policy overlay for local file tasks - add path scoping and destructive-action gates after preferring native file tools for ordinary list, search, organize, copy, move, and rename actions. Use when the user says: workspace-file-operator, workspace file operator, file operator, file operation, file operations, filesystem task, filesystem operation, file system task.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Provides authoritative guidance on Amazon Neptune Database and Neptune Analytics for graph, knowledge-graph, and relationship-heavy workloads — fraud detection / fraud rings, agentic memory / chatbot context across sessions, recommendations, identity resolution, Gremlin / openCypher / SPARQL queries, supernode / slow traversal, Neo4j to Neptune migration / APOC compatibility, Neptune Database vs Analytics engine selection, PageRank / community detection, GraphRAG, and connectivity from Lambda / EC2 / applications. Creates and modifies Neptune Database clusters/instances and Neptune Analytics graphs on explicit user confirmation; blocks destructive operations (delete, reset-graph, failover, major upgrade) and redirects to change-control.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.