'shell' 검색 결과

Scaffold, run, inspect, and evaluate model-agnostic agents that connect to MCP servers, skills, shell tools, and workflow packs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Add hard pre-execution guardrails to Claude Code so destructive shell commands are blocked before an agent can run them.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Start, watch, and restart a local stack of app processes together instead of juggling many terminals and ad hoc shell loops.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

IDA Pro 逆向分析辅助技能。当用户提到逆向、反编译、分析二进制/PE/ELF/APK/DLL/SO、破解、找密码、漏洞分析、病毒分析、firmware 固件分析，或需要分析 exe/dll/so/elf/macho/sys 等文件时，务必使用此技能。 Ensure to use this skill when the user wants to analyze any binary file, regardless of whether they explicitly mention "IDA" or "reverse engineering". This includes requests like "看看这个exe", "分析这个dll", "帮我破解", "找一下密码", "这个软件怎么注册", etc. Use the bundled scripts (scripts/start.ps1, scripts/open.ps1) for deterministic server management and file opening — do NOT write ad-hoc PowerShell commands for these operations.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create robust Python automation with full logging and safety checks. Use when tasks need complex data processing, authenticated API work, conditional file operations, or error handling beyond simple shell commands.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when evaluating, comparing, installing, or recommending a Claude Code plugin, Agent Skill, MCP server, agent toolkit, or GitHub-hosted AI extension, especially when popularity is weak evidence or the candidate requests shell, network, filesystem, or credential access.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

HTTP/HTTPS application-layer reconnaissance after a web service is identified: fingerprinting, content/API discovery, JS/source maps, proxy/cache topology, WAF, CMS, and known CVE/PoC candidates. Recon only — do not exploit, write files, or obtain a shell. Hand CVE candidates and attack surface to the operator, who may select /web-attack. Non-HTTP ports belong to /recon.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Windows local privilege escalation from a low-privilege shell to Administrator or SYSTEM. Covers quiet vs loud enumeration, SeImpersonate/Potato family including LocalPotato, token privileges (SeBackup/SeRestore/SeManageVolume/SeLoadDriver/SeDebug), service/DLL/COM/scheduled-task abuse, AlwaysInstallElevated and UAC boundary, KrbRelayUp-style domain-joined local admin, and version-gated kernel LPE. Use when the operator already has a Windows foothold and needs local SYSTEM. Endpoint blocks hand off to /edr-bypass then return here.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

HTTP/Web exploitation until a server shell or equivalent OS execution. Use after /web-recon has mapped the application. Covers injection, upload, LFI, SSRF/XXE, SSTI, deserialization, JWT/SAML, API logic, desync/cache/parser, and Web-controlled backend abuse. WAF stays here. Endpoint blocks after OS execution hand off to /edr-bypass then return. Direct non-HTTP service ports belong to /recon or /service-attack.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Linux local privilege escalation from a low-privilege shell to root. Covers quiet vs loud enumeration, sudo/GTFOBins, CVE-2025-32463 chwoot and CVE-2025-32462 host bypass, polkit/udisks CVE-2025-6018/6019, SUID/capabilities, systemd timers/units, cron/PATH/LD_PRELOAD, dangerous groups and docker.sock, host-local container escape, and version-gated kernel LPE including Copy Fail CVE-2026-31431. Use when the operator has a Linux foothold and needs root. Kubernetes RBAC stays in /k8s. Endpoint blocks hand off to /edr-bypass then return here.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

当用户明确要求并行或串行启用多个 Agent，或上游 Skill 声明需要统一的多 Agent 执行底座时使用。负责 Agent 的创建、隔离、调度、回收和汇总。⚠️ 不适用：普通 shell 并发、单元测试并发、下载任务，或要求强隔离的敏感数据处理。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Synthesizes exploration findings into unified analysis with deep investigation capabilities (shell commands, git history, dependency analysis) and completeness evaluation (converted from agent)

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Install, diagnose, and run the self-contained Red Card runtime through Codex in the ChatGPT macOS app from any task or project. Use when the user invokes $redcard or asks Codex to install, configure, troubleshoot, or run Red Card. Codex owns every shell command and requests scoped outside-sandbox execution for installation, dependency downloads, and real runs that need macOS hardware or app access; the user only handles required approval, macOS, Chrome, and Google-account UI actions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Post-implementation QA planning — independent of /review (the developer chooses whether to run them sequentially or in parallel), only when the change has a running surface worth driving. Interviews the developer to turn the specs and the diff into an executable QA specification (specs/qa/QA-<N>-<slug>.md) that /execute-qa runs. The agent drives browser and shell; the human steps in only at named handoff points. Use only when the user asks to plan manual QA — never trigger automatically.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Shell out to Claude Code CLI to invoke a second Claude session headlessly. Useful for cross-validation, second opinions, and isolated analysis without sharing current agent context. Requires Anthropic account.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Shell out to OpenAI Codex CLI for headless code generation, analysis, and question-answering. Optimized for code tasks. Requires OPENAI_API_KEY env var.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Shell out to Cursor Agent CLI for headless IDE-aware code tasks. Supports multi-model routing (auto mode routes to Claude, Gemini, GPT). Requires Cursor Pro/Business subscription.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Work with the @upstash/box SDK for sandboxed cloud containers with AI agents, shell, filesystem, and git. Use when building with Upstash Box, creating sandboxed environments, running AI agents in containers, or orchestrating parallel boxes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design, build, refactor, or review terminal interfaces—full-screen TUIs, interactive prompts, and command-line tools. Use for terminal-app layout and UX, CLI behavior, ncurses-style tools, dashboards, REPLs, fzf-like pickers, and libraries such as Bubble Tea, Ratatui, Textual, or Ink, including requests that name a known TUI such as lazygit, k9s, btop, helix, or yazi instead of saying “TUI.” Do not use for browser or web UI, native GUI, editor or font configuration, or backend and shell work that has no terminal interface.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when a command, adapter, or runtime smoke depends on proving an agent runtime's capabilities before trusting command routing, writes, shell access, or validation claims.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Research UI component patterns across the component.gallery corpus — 60 canonical component types, ~95 production design systems, 2,600+ examples — plus an AI-era overlay (prompt inputs, tool-call cards, streaming status, citations) and composite patterns (command palette, app shell, agent console). Compare implementations, find alternative component names, ground frontend decisions in real-world precedent. Pairs with minoan-frontend-design for research-then-build workflows. Triggers on component patterns, how do others implement X, design system research, component comparison, AI chat components, agent UI patterns.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use for Desktop Commander MCP capabilities — persistent shells and REPLs, long-running processes, filesystem beyond the workspace, structured files (.xlsx, .docx, .pdf, images) and large local data files such as CSVs, ripgrep search at scale, SSH, or cross-turn state.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Bun runtime, package manager, bundler, and test runner. Use when running scripts with bun, managing packages, serving HTTP with Bun.serve, querying databases with Bun.sql/bun:sqlite/Bun.redis, shell scripting with $, using S3/file I/O, writing tests with bun:test, bundling or compiling to executable, or using any Bun-specific API (spawn, glob, semver, FFI, workers, plugins, HTMLRewriter).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OpenTSC v2.1: Soul/Shell architecture for interpersonal intelligence. Local, offline-first, with event graphs, judgment engine (K7), self-creation (K8), three-layer attributes, calibrated predictions, 11 VSM professions, and a pluggable zvec memory index (semantic search, identity resolution, jieba segmentation, emotion scoring incl. batched+cached LLM) that runs with zero extra deps. Transforms implicit social judgment into explicit, queryable, auditable, evolving intelligence.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.