Results for “destructive-commands”

波总口语输入 → 结构化任务记录 → 同步到副官系统。当波总说"记一下""记录下来""有个任务"或描述要做的事时使用。

Use when creating, writing, or organizing slash commands. Covers frontmatter, dynamic arguments, file references, and bash execution. Commands are instructions FOR Claude, not messages TO the user.

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Utilize Windows Management Instrumentation (WMI) to execute malicious payloads, establish lateral movement, and execute commands stealthily across an Active Directory environment without dropping binaries to disk or relying on traditional Service Creation (PsExec) mechanics.

Provides Git commands and workflows for commits, branches, rebases, merges, conflict resolution, history recovery, and team collaboration, with safety rules for force-pushing and destructive operations.

Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (gstack)

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Use this skill to prevent destructive operations when working on production systems or running agents autonomously.

Use when creating a note, document, script or project that shouldn't outlive a known date — interview prep, a migration, a course, a time-boxed experiment — so it gets deleted on time instead of rotting in the repository.

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Detect DCOM-based lateral movement by correlating Sysmon process creation and network connection events, WMI event analysis, and RPC endpoint mapper traffic to identify abuse of MMC20.Application, ShellBrowserWindow, and ShellWindows COM objects.

Prevents destructive operations on production systems and restricts file edits to a specific directory when running agents autonomously.

Designs chaos experiments, creates failure injection frameworks, and facilitates game day exercises for distributed systems — producing runbooks, experiment manifests, rollback procedures, and post-mortem templates.

Execute remote commands on Windows targets using WMI-based lateral movement techniques, including Impacket wmiexec.py, CrackMapExec, and native PowerShell WMI commands for red team engagements.

Write defensive, production-grade Bash scripts with strict error handling, safe patterns, and comprehensive testing.

Completely delete and rewrite a file or module from scratch when structural rot makes patching impossible, with enforced preservation of interfaces and blast radius verification.

Guiding workflows by decomposing complex tasks (Epics) into Atomic Steps under 15 minutes each, with progress tracking and drift prevention. Use when complex decomposition is needed.

Write defensive, portable Bash scripts for automation, CI/CD, and system utilities, with strict error handling, safe argument parsing, and testing.

Manages Detox end-to-end tests for React Native apps by discovering configuration, devices, and test files, then analyzing build setups and parsing test results into structured reports.

Debugging command. Activates DEBUG mode for systematic problem investigation.

This skill should be used when the user asks to "run pentest commands", "scan with nmap", "use metasploit exploits", "crack passwords with hydra or john", "scan web vulnerabilities with nikto", "enumerate networks", or needs essential penetration testing command references.

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.