'decision' 검색 결과

Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logging decisions after a board meeting, reviewing past decisions with /cs:decisions, or checking overdue action items with /cs:review. Invoked automatically by the board-meeting skill after Phase 5 founder approval.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Architecture Decision Records (ADR) — a lightweight method for capturing important architectural decisions with context, trade-offs, and rationale. Based on Michael Nygard's ADR pattern and Google/Meta/ByteDance's design documentation culture. USE WHEN: deciding between technology choices, designing new architecture, changing existing architecture, documenting why a decision was made, onboarding new team members, or preserving design context for future maintainers. Triggered by terms like "tech choice", "architecture decision", "why did we choose", "design rationale", "ADR", or "architectural decision record".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

여러 관점으로 정리한 중요한 의사결정 초안에 Codex의 외부 비평을 한 차례 추가합니다. 결론의 약점, 누락된 실패 가능성, 반대 의견의 반영 여부를 확인합니다.

• 판단이 어려운 중요 초안 검토
• 초안에 빠진 실패 가능성 확인
• 강한 반대 의견의 누락 확인

혼자 결정하기 어려운 문제를 전문가나 관계자에게 전달할 질문지로 정리합니다. 상대의 지식과 필요한 답변을 확인해 회의나 개별 응답에 쓸 Markdown 문서를 만듭니다.

• 전문가에게 물어볼 질문 준비
• 결정 전 관계자 의견 수집
• 회의에서 구체적인 답변 확보

설계 결정의 이유와 비교한 대안을 기록하고 README, API 문서, 변경 이력을 정리합니다. 새 담당자와 AI 에이전트가 구현 배경을 이해하도록 돕습니다.

• 설계 결정과 채택하지 않은 대안 기록
• 공개 API 변경 문서화
• README의 시작 절차 정리

도시 녹지와 나무의 수관 면적 확대 정책을 시의회와 행정 심사용 HTML 슬라이드로 만듭니다. 공공의 필요성, 근거, 정책 선택지, 자금 결정을 정리합니다.

• 시의회에 제출할 도시 녹화 제안서 제작
• 행정 심사용 근거와 선택지 정리
• 정책 자금 결정에 필요한 설명 자료 제작

OpenDesign에서 자신의 API 키로 모델을 선택하는 방법을 설명하는 HTML 슬라이드를 만듭니다. 터미널형 템플릿으로 비용, 품질, 모델별 용도 판단을 돕습니다.

• 엔지니어와 정보 기술 부서에 모델 선택 설명
• 비용, 품질, 모델별 용도 비교 자료 작성
• 발표자 노트가 있는 터미널형 슬라이드 제작

인터뷰, 문의, 설문을 정리해 제품과 디자인 결정에 쓸 HTML 화면을 만듭니다. 근거, 주제, 확신 수준, 개선안 비교와 다음 실험을 함께 제시합니다.

• 인터뷰와 고객 문의를 함께 분석합니다
• 초기 설정 개선안을 비교합니다
• 관계자에게 근거와 불확실성을 공유합니다

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

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

Work through project decisions one question at a time, with a recommendation and brief reasoning. Record each settled answer immediately in project documentation, keeping unresolved questions visible and documents marked as drafts until explicitly accepted.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarify goals and boundaries before implementation
• Record decisions as an interview progresses
• Preserve decisions when discussions are interrupted

Work through project decisions one question at a time, with a recommended answer and a short explanation. Record settled choices in project documentation, including scope, completion criteria, constraints, risks, and unresolved questions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarify project goals through a decision interview
• Agree on deliverables and completion criteria
• Record settled decisions in project documentation

Make system architecture decisions by clarifying requirements and constraints, comparing benefits and drawbacks, and considering simpler alternatives. Record the reasoning in ADRs, architecture decision records, so significant choices and their rationale are documented.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying requirements before system design
• Comparing architecture patterns
• Documenting decisions and rationale in ADRs

Make system design decisions by clarifying requirements, identifying constraints, and comparing the benefits and drawbacks of different approaches. Record the reasoning in architecture decision records, or ADRs, while considering simpler alternatives and the team's experience.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Organizing requirements before designing a system
• Comparing architectural patterns and trade-offs
• Documenting the reasons behind design decisions

Guide an agent through searching past decisions before work, saving new decisions with their reasons, and treating corrections as lessons. The workflow helps distinguish useful long-term knowledge from temporary details, code facts, and routine activity already captured by hooks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking earlier decisions before starting a task
• Saving a resolved issue with its underlying reason
• Preserving lessons from corrections

Examine strategic decisions through a structured meeting of AI agents representing executive roles. Gather independent recommendations, challenge assumptions, summarize disagreements, and record approved decisions with action owners and deadlines after the founder reviews the proposal.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Evaluate market expansion from several executive perspectives
• Compare views on product direction or pricing
• Review hiring plans and organizational choices

Store phase documents verbatim in MemPalace, organized as decisions, plans, or milestones. Avoid duplicate entries and mirror decision or delivery facts into a knowledge graph that records when those facts became valid.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserve decision documents with their source information
• File plans and summaries by document type
• Record dated decision and delivery facts in a knowledge graph

Design a GenLayer review workflow for agents acting on a blockchain. Define evaluation criteria, evidence formats, decision outputs, and the connection needed to turn review decisions into restrictions or revocation of delegated authority.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Define review criteria for delegated agents
• Structure action logs, receipts, and spending evidence
• Design decisions to continue, warn, constrain, or revoke

Coordinate work across AI agents with shared rules for locating team files, recording decisions and their reasons, and requesting help. It also defines who owns revisions after a reviewer rejects an artifact.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Locate team files across separate working directories
• Record decisions that affect other agents
• Request input from another specialist

Turn existing research notes into an authoritative knowledge article after a team has made its decision. Records the outcome, rationale, trade-offs, and rejected alternatives while preserving source notes and links showing which documents the article replaces.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Documenting a decision after research
• Combining several research notes into one reference
• Updating an authoritative article with replacement links

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

Work through sixteen open questions in four rounds to clarify major product decisions, risky changes, or large refactors. The agent adapts later questions to earlier answers, then turns your decisions into a step-by-step implementation plan.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying decisions before a major product change
• Planning a large refactor
• Deciding rollout order for a risky change

Review important choices the agent made during the current work and identify those it remains unsure about. It considers overlooked alternatives and returns a concise list in plain English when explicitly requested by name.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing uncertain choices during ongoing work
• Checking for alternatives that were overlooked
• Finding decisions that need further discussion

[omh] Previously rejected options to revisit: recall scoped reviewed rejected decisions without elevating them to approved memory. Use when the user says: decision-recall, rejected decision recall, rejected decisions, why was this rejected, previously rejected alternative, 거절된 결정, 기각된 대안.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.