메뉴
Load when writing or reviewing agent .md files. Covers agent artifact shape, frontmatter, and Meridian-specific agent conventions.
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
Load when writing or reviewing prompts, skills, or agents. Gives the core heuristics for writing prompts that steer LLM behavior reliably.
Load when writing or reviewing skills. Covers SKILL.md shape, loading mechanics, and how to structure bundled resources.
Load when an agent, skill, or prompt needs strict review. Focuses on failure modes, severity, and clear feedback.
| name | agent-artifacts |
| type | reference |
| description | Load when writing or reviewing agent .md files. Covers agent artifact shape, frontmatter, and Meridian-specific agent conventions. |
| model-invocable | false |
Use /prompt-principles for broader prompt design guidance. This skill covers how agent artifacts are structured in Meridian.
Agent definitions are markdown files with YAML frontmatter. The body below the frontmatter is the system prompt. For the full frontmatter schema, see the mars agent profile reference.
Descriptions serve callers: they should help someone decide when to use the agent and what to pass. Bodies should stay caller-agnostic so the agent works from whatever context it receives, and harness-agnostic so they survive a harness swap — state intent, and leave CLI flags and tool mechanics to the environment (see /prompt-principles).
Managers and leads coordinate through spawns. They should not implement directly.
Load resources/meridian.md for Meridian-specific subagent, handoff, staffing, and package-target conventions. Load resources/model-policies.md for fallback patterns that keep agents usable across different model availability.
