'tool' 검색 결과

Test Model Context Protocol (MCP) servers and tool-calling systems for security vulnerabilities including tool injection, parameter manipulation, privilege escalation, and data exfiltration through AI agent tool interfaces. Use this skill when assessing MCP server implementations, AI agent tool integrations, or any system that exposes tools to language models. Covers tool confusion attacks, cross-tool exploitation, and MCP server hardening assessment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create new scientific tools for ToolUniverse framework with proper structure, validation, and testing. Use when users need to add tools to ToolUniverse, implement new API integrations, create tool wrappers for scientific databases/services, expand ToolUniverse capabilities, or follow ToolUniverse contribution guidelines. Supports creating tool classes, JSON configurations, validation, error handling, and test examples.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build Claude Code hooks, automated checks triggered by events such as tool use or session start. The guidance covers prompt-based decisions, command scripts, configuration, testing, and debugging for validation and workflow automation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking commands and file writes before execution
• Verifying task completion before an agent stops
• Loading project context when a session starts

Manage command-line tools connected to OmniRoute through its API. Inspect tool status, read or change settings, manage Codex profiles and backups, and invoke tool plugins for automation tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing settings across connected tools
• Managing Codex profiles
• Checking tool status and logs

Review tooltips so their extra information is available to screen reader users. Check accessible names, meaning labels available to assistive technology, and links to the elements that trigger them, then suggest fixes and verification steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether tooltip information can be read aloud
• Reviewing links between tooltips and their triggers
• Auditing shared tooltip components

Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking dangerous commands before execution
• Verifying completion before the agent stops
• Loading project context when a session starts

Build and review ViewModels, objects that manage screen state and actions, with CommunityToolkit.Mvvm. Use attributes to generate change notifications and commands, add input validation, and handle asynchronous operations, cancellation, and command availability.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add properties that notify the screen when values change
• Create asynchronous commands with cancellation
• Validate registration forms and settings

Use the command line to discover and run tools on MCP servers, which connect agents to external systems. Inspect required inputs, pass JSON arguments, and retrieve results as JSON or raw text for scripts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Listing available MCP servers and tools
• Searching for tools by name
• Checking tool inputs before calling an external API

Audit MCP servers, which provide external tools to AI agents, for hidden instructions, changes after approval, unsafe internal requests, and missing authentication. Use mcp-scan and manual checks to document risks and recommended fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing an MCP server before adding it to an agent
• Auditing an internally developed MCP server
• Checking approved tools for unexpected changes

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

Connect TanStack Table instances to developer tools for inspecting options, state, features, columns, rows, and row models. Diagnose missing connections, assign unique table keys, and manage registration replacement and cleanup.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspect table options, state, columns, and rows
• Diagnose tables missing from developer tools
• Assign distinct keys to multiple tables

Design AI agents and chatbots in n8n, choosing suitable nodes and connecting models, tools, conversation memory, and structured JSON output. Includes guidance on document retrieval and human approval before tool execution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a chatbot with conversation memory
• Connecting external tools to an AI agent
• Returning data in a defined JSON format

Add and configure an inspection panel for Vue json-render apps. This skill guides setup and troubleshooting so you can inspect UI definitions, edit state, review action and stream timelines, browse catalogs, and select page elements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding an inspection panel to a Vue app
• Inspecting UI definitions and editing state
• Reviewing action and stream timelines

Add and troubleshoot the json-render inspection panel in SolidJS applications. This skill covers panel setup for examining specifications, editing state, reviewing action and stream timelines, browsing component catalogs, and selecting page elements for inspection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add an inspection panel to a SolidJS app
• Inspect JSON specifications and edit application state
• Review action and stream timelines

Set up an inspection panel in React json-render apps to examine UI definitions, edit state, and review action and stream timelines. The skill also covers opening or toggling the panel and recording events from React code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding an inspection panel to a React app
• Inspecting UI definitions, state, and action history
• Opening or toggling the panel from React code

Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op instead of a double-send. The load-bearing premise: the LM cannot promise it'll call exactly once; the tool must promise the second call is safe. Framework-agnostic — applies to LangGraph node bodies that re-run on resume, MCP tools, OpenAI tool-calling retries, CrewAI delegated tool invocations, and direct HTTP wrappers. Search keywords: duplicate email sent, charged twice, exactly-once, idempotency key, tool called twice, retry side effect, double-send, at-least-once delivery.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call. The load-bearing premise: the *tool surface* is an LM-friendly subset of the *API surface* — one tool per user intent, not one per endpoint. Activates when a coder agent must expose an external HTTP API to a model (function calling, tool_use, MCP, LangChain `@tool`, CrewAI `BaseTool`). Encodes the *what to surface, how to name, how to shape, how to fail* — not any single framework's API. ~80% of agent tools in production are HTTP wrappers; this is the SOP for getting them right.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Implement circuit breaker logic for agentic tool calls — tracking tool health, transitioning between closed/open/half-open states, reducing task scope when tools fail, routing to alternatives via capability maps, and enforcing failure budgets to prevent error accumulation. Separates orchestration (deciding what to attempt) from execution (calling tools), following the expeditor pattern. Use when building agents that depend on multiple tools with varying reliability, designing fault-tolerant agentic workflows, recovering gracefully from tool outages mid-task, or hardening existing agents against cascading tool failures.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Install bioinformatics tools for ENCODE data analysis. Covers CLI tools (BWA, STAR, samtools, MACS2), R/Bioconductor packages (DESeq2, Seurat, ChIPseeker), Python packages (Scanpy, deeptools), and Nextflow pipeline infrastructure. Generates conda environments, R install scripts, and Python requirements. Use when the user needs to set up a bioinformatics workstation, install tools for a specific assay, create reproducible environments, or troubleshoot dependency issues. Trigger on: install tools, set up environment, conda create, bioinformatics setup, install R packages, install Bioconductor, install pipeline tools.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Rework an existing NV oOS Pro toolkit from a single-tenant demo into a universal product — currency-neutral schema with legacy aliases, a Tenant Profile + token renderer shared across the two assistant-delivery surfaces (packs via Portability vs blueprints via Blueprint Installer), demo-mode inversion, a universal single-folder ingestor (header-alias dictionary + dry_run + JSON), report export to CSV/PDF (DomPDF vs html_to_pdf choice), the add-a-tool drift checklist (TOOLS_LIST, coverage manifest, admin tool list, presets), and the re-seed-on-settings-save gotcha. Use when asked to 'universalise', 'de-demo', 'multi-tenant', 're-tenant', 'remove LKR/Surf Club', 'point the toolkit at a single Drive folder', 'export reports as CSV/PDF', or 'avoid re-installing assistants on save'. First case study: food-beverage (F&B Management, 2026-10-16). Complements mcp-ai-wpoos-toolkit-creation (build new) and mcp-ai-wpoos-toolkit-audit (harden existing).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Add custom local tools to ToolUniverse alongside the 1000+ built-in tools. Covers JSON-config tools (simplest, no code), Python class tools (REST/SOAP/GraphQL APIs, computational logic), and best-practices for return schemas. Use for wrapping new APIs, adding domain-specific computations, or contributing tools to the registry.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Install and configure ToolUniverse for any use case — MCP server (chat-based), CLI (command line with 9 subcommands), or Python SDK (Coding API with 3 calling patterns). Covers uv/uvx setup, MCP configuration for 12+ AI clients (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, etc.), full CLI reference (tu list/grep/find/info/run/test/status/build/serve), Coding API quickstart, agentic tools, code executor, API key walkthrough, skill installation, and upgrading. Use when user asks how to set up ToolUniverse, which access mode to use (MCP vs CLI vs SDK), configuring MCP servers, using the CLI, troubleshooting installation, upgrading, or mentions installing ToolUniverse or setting up scientific tools. Also triggers for "how do I use ToolUniverse", "what's the best way to access tools", "command line", "tu command", "coding API", "tu build".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Code quality patterns and guidelines for ToolUniverse tool development. Apply when writing, fixing, or refactoring tool Python code in the ToolUniverse project. Encodes lessons from 80+ debug rounds. Use alongside devtu-fix-tool and devtu-self-evolve. Triggers: implementing tool fixes, writing new tool classes, reviewing tool code quality, checking schema correctness, looking up API-specific bug fixes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.