'multi-step' 검색 결과

사진, 영상, 공개 기록의 적은 단서를 연결해 장소, 일시, 조직 관계를 검증합니다. 근거와 가설을 구분하고 반증과 미확인 사항도 정리하는 조사 스킬입니다.

• 공공장소 사진의 촬영 위치를 확인합니다
• 공개 기록으로 사건의 시간순서를 조사합니다
• 기업과 도메인의 관계를 조사합니다

AI 에이전트가 정확성·완전성·명확성·실행 가능성·간결성의 다섯 기준으로 결과물을 자체 평가합니다. 근거가 있는 점수와 평균, 우선순위별 개선안을 제공합니다.

• 여러 파일에 걸친 구현 후 자체 평가
• 여러 작업 단계를 마친 결과물 점검
• 설계 문서와 분석 보고서 평가

정규 표현식과 문법 규칙으로 로컬 언어 모델의 출력을 제한해 JSON과 날짜 형식을 맞춥니다. 고정 라벨 분류와 Python을 이용한 재사용 가능한 다단계 생성도 다룹니다.

• 지정 스키마에 맞는 JSON 생성
• 날짜와 이메일 주소 형식 통일
• 고정 라벨로 텍스트 분류

OpenHands CLI에 코드 수정과 여러 단계의 개발 작업을 맡깁니다. LiteLLM 지원 모델을 선택하고, 대화형 화면 없이 일괄 실행과 진행 확인, 대화 재개를 할 수 있습니다.

• OpenHands에 코드 수정 위임
• LiteLLM 지원 모델로 개발
• 오래 걸리는 개발 작업의 진행 확인

AI의 조언·계획·견적·분석 뒤에 짧은 질문 두세 개를 덧붙입니다. 답변의 구체적인 내용을 바탕으로 행동 전에 숫자·논리·누락 정보를 검토하도록 돕습니다.

• 비용·납기 추정의 전제 확인
• 추천 계획의 근거 검토
• 제안서·메일 초안의 누락 정보 확인

Create a phased implementation plan for a feature or complex development task. It investigates documentation and existing examples, identifies supported APIs, and records concrete tasks, references, and verification checks for each phase.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a feature before implementation
• Checking documented APIs before choosing an approach
• Splitting development work across separate chat sessions

Design and build AI agents for business, research, operations, or creative work. Define essential actions and knowledge, start with a simple execution loop, and add progress tracking or separate child agents as needs emerge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing an assistant for business tasks
• Building a research agent
• Choosing essential actions and knowledge

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

Fill web forms from a JSON list of field names and values, using saved templates or page labels to locate inputs. Optionally submit the form, save new field mappings, and redact values from recorded actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Filling signup and contact forms
• Reusing templates for recurring submissions
• Saving field mappings for a new form

Review multi-step forms to find information users must enter more than once. Suggest automatic filling, reuse options, and preserving data between steps, while explaining relevant accessibility requirements and exceptions for security or validity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking repeated fields during checkout
• Reviewing signup and onboarding forms
• Reusing information in support flows

Adapt agent replies for readers with ADHD by putting the next action first, numbering steps, and restating progress across turns. Replies include concrete time estimates, visible completed work, and fewer tangents to make tasks easier to follow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Make the first action clear when starting a task
• Follow numbered steps through a task
• Keep track of progress across conversation turns

Manage WireMock from the command line to create mock HTTP responses, inspect and count received requests, change scenario states, and record real backend traffic. These operations support integration tests with controlled responses.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create mock API responses for integration tests
• Check request counts and unmatched requests
• Switch states in a multi-step test scenario

Run molecular property predictions, explore molecular shapes, and estimate how compounds bind to proteins through a cloud Python API. Process compound batches and connect modeling steps without maintaining local high-performance computing infrastructure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Predicting properties across a compound library
• Exploring molecular shapes and tautomeric forms
• Estimating how compounds bind to proteins

Audit an AI agent's completion claims using existing logs, artifacts, approvals, and deployment records. Reconstruct the run and assess each claim separately, distinguishing proven results, partial support, contradictory evidence, and missing proof without rerunning the work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether an agent's completion report has supporting evidence
• Reviewing tool calls, retries, and checkpoint recovery
• Matching approvals and deployments to the same artifact

Use natural-language requests with Aomi CLI to check crypto prices and balances or prepare swaps, staking, and transfers between chains. Review queued transactions and simulate multi-step batches before separately authorizing wallet signing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check crypto prices and wallet balances
• Prepare and simulate a Uniswap swap
• Prepare an ETH stake with Lido

Add browser automation to Vercel apps by running agent-browser and headless Chrome in temporary, isolated virtual machines. Capture screenshots, inspect page structure, and complete multi-step forms while preserving browser state between commands.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add website screenshot capture to a Vercel app
• Fill and submit forms across multiple browser commands
• Run recurring browser tasks with Vercel Cron Jobs

Helps agents manage long tasks by checking for forgotten instructions and drifting conventions. It guides progress summaries, rule checks after context compaction, and handoff notes when work should continue in a fresh session.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Keeping rules consistent during long agent sessions
• Rechecking decisions after context compaction
• Preparing handoff notes for a fresh session

Retrieve past operational experience from OpenViking before or during coding, configuration, deployment, or recovery work. It reads relevant records, checks whether their assumptions match the current environment, and applies suitable procedures and checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Consulting past experience before code changes
• Checking prior procedures for configuration changes
• Finding diagnostic steps after a deployment failure

Use OpenViking MCP tools to retrieve relevant knowledge before substantial tasks and save lasting preferences, decisions, and lessons during or after work. Import documents as searchable resources so later tasks can draw on previous findings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retrieve previous fixes before debugging
• Save lasting preferences and working conventions
• Record decisions and their rationale

Make Copilot CLI easier to follow with plain-English explanations of approval requests, errors, and command results. The skill adds color-coded risk levels, step-by-step plans, explanations of technical terms, and summaries of changes with undo guidance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understand an approval request before deciding
• Interpret errors and command results
• Follow a multi-step task and compare options

Break a development task into small requirements with explicit acceptance criteria, then repeat implementation and verification while saving progress. Completion depends on evidence for each requirement and reviewer approval, with configurable reviewers and a final cleanup check.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Carrying a multi-step implementation through verification
• Resuming work with recorded progress
• Tracking evidence for each requirement

Manage multi-step financial research with a clear objective, acceptance criteria, and linked evidence. Track findings across turns, audit whether each criterion is supported, and report unresolved gaps while keeping the workflow limited to research.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare strategies or assets against shared criteria
• Review the evidence supporting an investment thesis
• Resume a research task across multiple turns

Review contact, lead capture, quote, survey, and checkout forms to identify obstacles to completion. Get prioritized recommendations for fields, layout, wording, mobile usability, and error messages, plus ideas for comparing alternative designs through tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing where visitors abandon a contact form
• Reconsidering required fields in a demo request form
• Planning a multi-step quote request form

Design collaborative AI teams with CrewAI by defining each agent’s role, goals, tasks, and expected results. Covers passing work between agents, manager-led coordination, memory settings, and execution planning for workflows such as research and writing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a team that researches and writes articles
• Coordinate specialists through a manager agent
• Define agent roles and expected task outputs