'uv' 검색 결과

Implement core TypeScript modules for claude-flow v3 using domain-driven design, which organizes code around distinct responsibilities. Build task and session domains, connect storage and services, and add unit and integration tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build the core structure for claude-flow v3
• Implement task assignment and status rules
• Connect SQLite storage through dependency injection

AgentDB로 대화 기록과 사용자 선호를 저장하고 검색하는 단기·장기 기억을 구현해, AI 에이전트가 다음 세션에서도 해당 정보를 참조하도록 돕습니다.

• 채팅에 대화 기록 추가
• 세션 간 사용자 선호 기억
• 성공한 상호작용 패턴 재사용

Improve the MCP server that connects claude-flow v3 to tools. It guides connection reuse, faster tool lookup, request distribution, and communication changes, with monitoring to evaluate response times, errors, memory use, and cache performance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Analyze slow MCP startup and tool responses
• Reuse connections and clean up idle ones
• Improve tool lookup and distribute requests

Build advanced AgentDB workflows with database synchronization, multiple databases, and search that combines meaning with attribute filters. Covers similarity measures, diverse search results, and operational patterns for distributed AI applications.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sharing stored patterns across multiple AgentDB instances
• Filtering semantic search by date or category
• Separating knowledge and conversation databases

Implement agents that use recorded task outcomes to choose future approaches. ReasoningBank supports matching past patterns, comparing strategies, retaining experience in AgentDB, and tracking how strategy success and learning change over time.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose task strategies using past outcomes
• Compare approaches to code review or bug fixing
• Match current situations to learned patterns

요구 사항 정리부터 설계, 테스트를 먼저 쓰는 구현, 검토, 배포까지 개발을 단계별로 진행하고 여러 AI 에이전트가 작업과 지식을 나누는 절차를 다룹니다.

• 새 기능 계획 및 구현
• 기존 코드 수정과 테스트 추가
• 코드 보안 및 성능 검토

agent-browser로 버튼과 입력란을 식별하는 스냅샷을 확인하여 로그인, 폼 입력과 제출, 웹 정보 수집, 스크린샷 촬영을 자동화합니다.

• 로그인 과정을 자동화합니다
• 웹 폼을 작성하고 제출합니다
• 상품명, 가격, 링크를 수집합니다

Review a Homecore server operation plan before startup. Check authentication, restoration order, feature tests, speech provider configuration, and handling of pairing secrets. The skill reviews the plan without starting the server.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a Homecore server startup plan
• Check restoration order and bounded limits
• Verify feature tests before enabling Wasmtime or HAP

Create AgentDB learning plugins that use recorded experience to improve agent decisions. Choose a learning method, store states, actions, and rewards, train models, and evaluate suggested actions through CLI and API workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train agents from historical experience
• Build decision-making for games and navigation
• Combine experience from multiple agents for training

Coordinate multiple AI agents for research, development, testing, and system analysis. It guides role assignment, communication structures, parallel and sequential tasks, shared memory, progress monitoring, and recovery, bringing separate contributions into reports or coordinated development workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Gather research in parallel and compile a report
• Coordinate application design, implementation, and review
• Run unit, integration, security, and performance tests in parallel

Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build agent memory that reuses past experiences
• Record and assess sequences of agent actions
• Consolidate similar experiences into reusable patterns

Coordinate multiple AI agents with agentic-flow to run tasks in parallel or through ordered stages. Configure shared memory, team structure, workload distribution, retries, and task reassignment, then monitor how the group performs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run API, interface, and test work in parallel
• Build a design-to-review workflow with ordered stages
• Share specifications and state across agents

Build document search with AgentDB that finds related content by meaning. Store documents as numerical representations, combine similarity search with metadata filters, and retrieve relevant passages for systems that generate answers using source material.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build answers grounded in retrieved documents
• Add meaning-based search to a knowledge base
• Find documents with similar content

Measure and optimize claude-flow v3 startup, search, attention processing, and memory use. Compare benchmarks against performance targets, track changes over time, and identify regressions to guide further optimization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare performance before and after v3 optimization
• Evaluate vector search speed and memory use
• Track performance regressions over time

Review Home Assistant migration behavior for input validation, configuration preservation, and output that does not overwrite existing files. Check storage schema versions, keep secrets out of diagnostics, and identify incomplete automation or integration behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing supported storage schema versions
• Checking preservation of unfamiliar configuration fields
• Reviewing writes that must not overwrite existing files

Work with AI as a coding partner, choosing who writes code and who guides the work. Supports role switching, test generation, ongoing code review, debugging, and step-by-step explanations for learning.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Write code with ongoing AI review
• Direct AI implementation while reviewing its output
• Develop features by writing tests first

Run the smallest relevant Homecore test profile against a specified repository checkout. Choose core, Wasmtime, HAP, or full tests to validate the selected software paths, while keeping the limits of passing results clear.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running Homecore core tests
• Checking the Wasmtime software paths
• Running the HAP test profile

Homecore 기능의 소스, 테스트, 승인된 설계 결정을 추적해 구현 상태와 제약을 확인하고, 구현 유무와 배포 환경 호환성을 구분합니다.

• 기능 관련 소스와 설계 결정 조사하기
• 구현 상태와 제약 확인하기
• 코드 변경 전 관련 테스트 읽기

claude-flow v3의 보안 설계를 검토하고 의존 패키지, 비밀번호 저장, 인증 정보, 입력 검증, 명령 실행의 대책과 테스트를 마련합니다.

• 보안 경계와 위협을 정리합니다
• 의존 패키지를 갱신하고 점검합니다
• 비밀번호 저장과 인증 정보 생성을 검토합니다

Check code and agent outputs, track reliability scores, and roll back changes that fail a chosen threshold. Includes quality reports, live monitoring, and integration with automated build and deployment workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking code produced by AI agents
• Rolling back changes that fail verification
• Tracking quality trends over time

Refactor claude-flow into an extension of agentic-flow@alpha to reduce duplicate implementations. Plan adapter layers, migrate agent and task management, and connect learning, shared memory, and tools while checking compatibility with existing functionality.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Consolidate duplicate agent and task management code
• Design an adapter that preserves existing APIs
• Integrate learning, shared memory, and MCP tools

Review Homecore plugins by distinguishing built-in native code from external Wasm packages. Check signatures, publisher identity, paths, resource limits, and host permissions, then use the documented verification command to assess the plugin’s trust boundaries.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review an external Wasm plugin before use
• Check built-in native plugin registration
• Inspect plugin resource limits and host permissions

Connect work from multiple AI agents to GitHub Projects. Synchronize task cards and statuses, assign work based on expertise and workload, and generate progress reports so teams can track assignments, priorities, and blockers on shared boards.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Synchronize agent tasks with GitHub Projects cards
• Assign work based on expertise and workload
• Track sprint progress and blocked tasks

Review GitHub pull requests with specialized AI agents that check security, performance, architecture, and coding conventions. Generate actionable comments with suggested fixes, and connect review findings to automated approval or change requests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing authentication changes for security issues
• Checking database changes for performance regressions
• Reviewing UI accessibility and coding conventions