메뉴
ISO 42001, NIST AI RMF, EU AI Act, responsible AI, LLM evaluation standards. Reference material (non-actionable knowledge).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | ai-standards-landscape |
| description | ISO 42001, NIST AI RMF, EU AI Act, responsible AI, LLM evaluation standards. Reference material (non-actionable knowledge). |
Load and follow the instructions from the canonical file at .vaibe/skills/ai-standards-landscape/SKILL.md
as if they were written here. Do not act on this wrapper — it holds only metadata; the full
skill logic lives in the canon.
@.vaibe/skills/ai-standards-landscape/SKILL.md
Mandatory prerequisite for any skill work — load this FIRST and build from it whenever authoring, reviewing, or changing a skill, instead of pattern-completing from another skill as a template. "Reference" names its content type, not its priority: it is not optional. The sourced reference for how agent skills are composed — the cross-tool open standard (agentskills.io) and the deltas for Cursor, Claude Code, OpenCode, and Codex, plus Anthropic authoring best practices, and how it maps onto the vAIbe-OS canon (model A — .vaibe/ canon + generated native layer). Triggers: skill authoring, creating a skill, editing a skill, SKILL.md, frontmatter, native layer, agentskills.
Mandatory prerequisite for any skill work — load this FIRST and build from it whenever authoring, reviewing, or changing a skill, instead of pattern-completing from another skill as a template. "Reference" names its content type, not its priority: it is not optional. The sourced reference for how agent skills are composed — the cross-tool open standard (agentskills.io) and the deltas for Cursor, Claude Code, OpenCode, and Codex, plus Anthropic authoring best practices, and how it maps onto the vAIbe-OS canon (model A — .vaibe/ canon + generated native layer). Triggers: skill authoring, creating a skill, editing a skill, SKILL.md, frontmatter, native layer, agentskills.
Mandatory prerequisite for any skill work — load this FIRST and build from it whenever authoring, reviewing, or changing a skill, instead of pattern-completing from another skill as a template. "Reference" names its content type, not its priority: it is not optional. The sourced reference for how agent skills are composed — the cross-tool open standard (agentskills.io) and the deltas for Cursor, Claude Code, OpenCode, and Codex, plus Anthropic authoring best practices, and how it maps onto the vAIbe-OS canon (model A — .vaibe/ canon + generated native layer). Triggers: skill authoring, creating a skill, editing a skill, SKILL.md, frontmatter, native layer, agentskills.
Mandatory prerequisite for any skill work — load this FIRST and build from it whenever authoring, reviewing, or changing a skill, instead of pattern-completing from another skill as a template. "Reference" names its content type, not its priority: it is not optional. The sourced reference for how agent skills are composed — the cross-tool open standard (agentskills.io) and the deltas for Cursor, Claude Code, OpenCode, and Codex, plus Anthropic authoring best practices, and how it maps onto the vAIbe-OS canon (model A — .vaibe/ canon + generated native layer). Triggers: skill authoring, creating a skill, editing a skill, SKILL.md, frontmatter, native layer, agentskills.
Mandatory prerequisite for any skill work — load this FIRST and build from it whenever authoring, reviewing, or changing a skill, instead of pattern-completing from another skill as a template. "Reference" names its content type, not its priority: it is not optional. The sourced reference for how agent skills are composed — the cross-tool open standard (agentskills.io) and the deltas for Cursor, Claude Code, OpenCode, and Codex, plus Anthropic authoring best practices, and how it maps onto the vAIbe-OS canon (model A — .vaibe/ canon + generated native layer). Triggers: skill authoring, creating a skill, editing a skill, SKILL.md, frontmatter, native layer, agentskills.
Create or update project management plan with task statuses and priorities. Triggers: plan, sprint plan, plan-update, обновить план, план проекта, точка сборки, личный план, план работ, сохрани план, сохрани в планы.
