'multi-step' 검색 결과

Organize multi-step agent tasks with persistent Markdown files for plans, findings, and progress. Records decisions, errors, and test results, then reloads the selected task's planning files to resume work after an interruption.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning research that involves many tool calls
• Resuming work after an interruption
• Recording errors and test results

Organize multi-step agent tasks with persistent Markdown files for plans, findings, and progress. Records decisions, errors, and test results, then reloads the selected task's planning files to resume work after an interruption.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning research that involves many tool calls
• Resuming work after an interruption
• Recording errors and test results

Keep plans, research findings, and progress in Markdown files for complex agent work. Separate task plans and automatic planning reminders help the agent recover saved context, track decisions, and identify the next action.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resuming long research tasks
• Tracking phases and the next action
• Separating plans for concurrent tasks

Use German-language guidance to organize multi-step agent work in Markdown files. Store plans, findings, and progress by task, then revisit those records to resume research, review decisions, and track unfinished phases.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Managing research with German-language guidance
• Recovering task context after a break
• Separating plans for concurrent tasks

Build reusable parts for n8n workflows instead of copying shared logic. This skill guides typed inputs, consistent outputs, naming, and execution settings so workflows and AI agents can call the same processing steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sharing common logic across workflows
• Splitting a large workflow into reusable parts
• Exposing shared processing as an AI agent tool

Run untrusted or AI-generated code in temporary microVMs, small virtual machines isolated from the host. Execute a snippet in one call, manage multi-step sessions, and read or edit files inside the sandbox.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run AI-generated code in an isolated environment
• Execute a snippet and collect its output
• Perform temporary builds or integration tests

Automate Anthropic Admin tasks involving API keys, usage, workspaces, and organization management through Rube MCP, a connection to external tools. The skill guides tool discovery, connection checks, multi-step workflows, and bulk operations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Manage Anthropic Admin API keys
• Check Anthropic usage
• Handle workspace and organization management tasks

Manage isolated working environments in OpenShell using its command-line tool. Register gateways, create and connect to sandboxes, configure credential providers, and reuse workload templates with shared images, environment settings, and computing resources.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create and connect to a sandbox
• Configure and refresh provider credentials
• Inspect and import provider profiles

Build and update Convex backend code, including schemas, queries, authentication, storage, and scheduled jobs. Apply input and output validation, indexed data access, and deployment checks to verify the implementation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing schemas and indexed queries
• Implementing queries, mutations, and actions
• Wiring authentication, storage, and scheduled jobs

Hand complex document generation or data processing to shell_agent when direct tools repeatedly fail. Define the required output, let the tool choose libraries and recover from errors, then verify the resulting files and content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resuming work after repeated tool failures
• Delegating PDF or DOCX document generation
• Handing off multi-step data processing

Troubleshoot CSV and XLSX processing when execute_code_sandbox fails. The workflow locates input files, saves processing code as a Python script, captures execution errors, checks dependencies and file access, and confirms output exists before reading it.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recovering spreadsheet processing after sandbox errors
• Locating CSV and XLSX input files
• Diagnosing dependency, path, and encoding errors

Recover from repeated web search failures by delegating information gathering to shell_agent. Define the required data and output format, allow retries and alternative collection methods, then check source citations and completeness before using the results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continuing research after search_web repeatedly fails
• Collecting market data from multiple sources
• Checking sources and coverage before writing a report

Create and edit Excel workbooks by running a complete Python script through the shell. Covers multiple sheets, data entry, formatting, formulas, and saving files when other file-reading or code-execution tools fail.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create an Excel report with multiple sheets
• Apply data and formatting in one script
• Update cells in an existing XLSX file

Download PDFs from web URLs or process local files, verify their format, and extract text with pdftotext. If extraction fails or looks poor, try PyMuPDF, check the results, and document any remaining source limitations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Download a PDF from a web URL and extract its text
• Convert a local PDF into a text file
• Try another method after failed or garbled extraction

Test application business rules by mapping workflows and checking unexpected actions, inputs, identities, and repetition. The skill helps investigate checkout, refunds, subscriptions, permissions, and concurrency flaws, then document reproduction steps and financial impact.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking checkout and refund workflows
• Testing price, quantity, and coupon rules
• Reviewing role and tenant boundaries

Find and run Refly skills that match a task, then track the workflow through completion. Retrieve generated files or text, or check whether an action finished, using results verified by the Refly command-line tool.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find an installed skill for a task
• Run an image or video generation workflow
• Retrieve research results as text

Review a product experience by walking through its steps and capturing screenshots. Produces an illustrated assessment of usability, design, and accessibility risks, with findings tied to specific screens and clear limits on what was checked.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a registration or onboarding flow
• Inspect a checkout flow for usability issues
• Assess settings screens and navigation

Create specialized assistants for Cursor that work with their own context, separate from the main conversation. Define responsibilities, instructions, output formats, model choices, and execution settings for reusable workflows such as verification, debugging, and documentation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an assistant to verify completed work
• Defining a specialist for debugging and test failures
• Creating a read-only security audit assistant

Design specialized assistants that work with their own separate context. Define responsibilities, delegation conditions, working steps, and report formats for reusable subagents handling verification, debugging, security audits, or code reviews.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an independent agent to verify completed work
• Defining a debugging specialist
• Creating a security audit agent

Model ongoing requests and multi-step agent work to estimate capacity, latency, and cost per completed task. Break execution into stages, account for queues and retries, and produce workload tables with average and peak resource budgets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Estimate capacity for ongoing AI requests
• Analyze queues and tool waits in agent workflows
• Compare resource costs per completed task

Build reusable parts for n8n workflows instead of copying shared logic. This skill guides typed inputs, consistent outputs, naming, and execution settings so workflows and AI agents can call the same processing steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sharing common logic across workflows
• Splitting a large workflow into reusable parts
• Exposing shared processing as an AI agent tool

Build workflows with Vercel's Workflow DevKit that preserve progress and resume after restarts. Structure operations as persistent steps, wait for external events, retry temporary failures, and inspect runs to understand how a process is progressing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building processes that resume after restarts
• Pausing a workflow until an external event arrives
• Retrying temporary failures in individual steps

Identify repeated NuGet package restores across .NET build, test, and publish steps. Check whether earlier restores cover each later step, apply targeted changes, and validate the pipeline without removing required dependency restoration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Remove repeated package restores from CI pipelines
• Check where --no-restore can safely be added
• Investigate NETSDK1004 or NETSDK1047 after skipping restore

Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.