'delegation' 검색 결과

Route a task through SIPS commands, agents, scripts, MCP tools, or bounded delegation. Use when asked to route, split, fan out, escalate, or choose the right SIPS path.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with Azure Lighthouse — azure Lighthouse delegated resource management. Covers delegation assignments, managed service offers, customer tenant access, cross-tenant resource visibility, role assignments, and delegation auditing. Use when managing multi-tenant Azure environments, reviewing delegated access, auditing cross-tenant permissions, or configuring managed service registrations.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Delegate routine work to subagents — boilerplate generation, data transformation, file analysis, documentation drafting. Use when splitting tasks into independent subtasks for parallel subagent execution.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Bulk-create hundreds of AI agent skills for the Agency Roster repo — naming, conflict resolution, batch delegation, GitHub sync, and monetization prep.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Kerberos 委派攻击（非约束/约束/RBCD）。当 BloodHound 发现委派配置、或已获取有 SPN 的服务账号/机器账号控制权时使用。通过 S4U 协议滥用可实现跨服务模拟任意用户，常用于域内权限提升和横向移动。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Herdr（コーディングエージェント向けターミナルマルチプレクサ）の操作と、herdr CLI の構文・ID 規約・agent 状態モデル（idle / working / blocked / done）の真実源。pane・tab・workspace・terminal・command の確認や操作、別 pane での agent 起動、pane 上の agent との通信の時に使用。HERDR_ENV=1 必須。境界: pane へ委譲するかどうか・経路・モデル・指示書・結果回収の方針は context/delegation.md（本スキルは CLI のみ）。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Implement Agent-to-Agent (A2A) protocol for inter-agent communication. Use for agent discovery, agent cards, task delegation, and multi-agent orchestration. Triggers on "A2A protocol", "agent-to-agent", "agent discovery", "agent card", "multi-agent", "agent delegation", "agent communication", or when implementing spec/api/017-a2a-protocol.md.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

/coach-me と入力されたときだけ起動する、Learning by Doing コーチングスキル。現在の会話を分析し、Anthropicの4D AIフルーエンシーフレームワーク（Delegation / Description / Discernment / Diligence）に基づいて「うまくできていた点」「改善できる点」「次回に使えるプロンプト例」をフィードバックする。オプションで /coach-me 詳細 または /coach-me --detail と入力すると次元ごとの深掘りフィードバックを提供。自動起動は一切しない。ユーザーが /coach-me と明示的に入力した場合のみ使用すること。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

/ai-fluency-check と入力されたときだけ起動するAIフルーエンシー自己評価スキル。Anthropicの4D AI Fluency Framework（Delegation / Description / Discernment / Diligence）に基づく18項目のルーブリックを使い、対話的に自己評価する。過去の評価記録と比較して成長を可視化し、研究根拠にもとづく改善アドバイスと参考文献を提供する。ユーザーが /ai-fluency-check と明示的に入力した場合のみ使用すること。自動起動・推測起動は一切しない。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Personal leadership development for founders and first-time CEOs. Covers founder archetype identification, delegation frameworks, energy management, CEO calendar audits, leadership style evolution, blind spot identification, imposter syndrome, founder mental health, and succession planning. Use when a founder feels like the bottleneck, struggles to delegate, is burning out, transitioning from IC to executive, managing a board, or when user mentions founder mode, CEO growth, leadership development, delegation, burnout, or imposter syndrome.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

You are helping a penetration tester exploit Kerberos delegation misconfigurations

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative instruction design. Use when: creating custom agents, designing agent descriptions for auto-delegation, troubleshooting agent memory issues, or building agent pipelines.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Hermes에서 Claude Code CLI에 기능 개발, 버그 수정, 코드 검토를 맡기는 절차를 안내합니다. 단발 실행과 대화 세션을 구분하고 권한과 실행 횟수를 조정합니다.

• 기능 개발과 버그 수정 위임
• 코드 변경 사항과 PR 검토
• 리팩터링과 테스트 반복

Paperclip 작업 계획에 목표 성과, 제약, 진행 방식과 성공 확인 방법을 정리합니다. 실행 전 불확실성과 결정 사항을 기록하고 기존 계획의 현재 버전을 갱신합니다.

• 성과와 확인 방법을 담은 계획 작성
• 착수 전 불확실한 사항 정리
• 중복 생성 없이 기존 계획 갱신

Review a reusable Agent Skill package before implementation. Validate its identity fields, separate instructions from external capabilities and execution timing, and receive a validation report with a minimal set of building blocks and reasons for each choice.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a workflow before turning it into a reusable skill
• Checking SKILL.md identity fields
• Choosing instructions, scripts, or delegation

Clarify unresolved product decisions before implementation, such as scope, supported platforms, or API agreements. Use a small set of focused questions to establish the intended outcome, while leaving routine technical choices to the agent.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarify an unresolved product scope
• Confirm which platforms a product should support
• Resolve open decisions about data or API agreements

Set up and customize Pi, a terminal coding agent framework. This skill guides model configuration, extension development, terminal interfaces, and integration with other applications through its SDK, a software development kit, or process messaging.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Install Pi and configure model access
• Create custom tools and terminal interfaces
• Embed Pi in another application

Let the host AI agent review Git changes while ocr selects files and resolves review rules. Receive findings grouped by severity, plus coverage details showing which files were reviewed or skipped and why.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing changes with the current AI agent
• Checking branch differences or a single commit
• Reviewing files against their applicable rules

Control terminals and coding agents inside Herdr, a tool that groups multiple terminals. Create split panes, run commands, send agent prompts, read output, and wait for status changes while coordinating work across the current session.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting another coding agent in a neighboring pane
• Running tests or a server in a separate terminal pane
• Reading agent output and checking whether input is needed

Trace movement between Windows hosts in a CTF sandbox using credentials and Kerberos tickets, which carry authentication information. Connect recovered artifacts to the service that accepted them and document the resulting access or privileges.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trace movement between Windows hosts
• Identify services that accept recovered credentials
• Connect Kerberos tickets to resulting access

Split multi-step coding, research, or testing into focused assignments for sub-agents, which are agents handling specific parts of a task. The parent agent retains design decisions, integration, and final verification while independent work runs in parallel.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Exploring separate groups of files in parallel
• Assigning code changes with clear file ownership
• Running focused tests alongside other work

Add controls to AI agents that use APIs, databases, and files. Use Python patterns for tool permissions, approval requirements, call limits, suspicious input checks, audit logs, and trust scores that guide delegation between agents.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Restrict which tools an agent can call
• Check suspicious inputs before execution
• Require human approval for sensitive operations

Build collaborating AI teams with CrewAI by defining roles, tasks, and shared context. Configure ordered execution or manager-led delegation, add memory and tools, and create workflows that branch based on events or results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a research-to-writing agent workflow
• Coordinate specialists through a manager agent
• Create workflows with conditional branches

Screens incoming nondisclosure agreements against an organization's criteria or stated defaults. Classifies each agreement into three review levels and produces a report covering flagged clauses, risks, suggested fixes, and recommended next steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Screen an NDA received by sales or business development
• Check for non-compete and non-solicitation clauses
• Identify missing exceptions to confidentiality obligations